公开记录良好
软件健康报告模式 0.31.0 · 指标 2.5.0 · 2026-08-05 09:14 UTC
kage-core / Kage
Persistent, verified memory for coding agents — so they stop re-explaining your codebase and never act on stale knowledge. Every memory is checked against your actual code; lives in your repo as plain files, shared via git. No account, no DB. Install: npx -y @kage-core/kage-graph-mcp install
kage-core/Kage 的健康指数为 100 分中的 71 分，处于「良好」区间。 其得分最高的类别是Vitality（86/100），最低的是Sustainability & Governance（43/100）。 最近一次更新在 7 天前。 近期的大部分工作由 1 位贡献者完成。
71
总分 / 100软件健康指数
指标归入加权类别，统一采用 1–100 量表。总体分先取类别加权平均，再依据公开记录的分布进行校准，使各等级具有百分位含义；当公开证据触发高风险司法辖区政策时，评级会按政策调整，并设置 34（存在风险）的上限。
71
卓越93-100公开记录中的最高层级（约前 5%）；基本满足所有检验标准
优秀80-92各方面均表现强劲；仅有少量不足
良好65-79健康；不足之处有限且可控
中等50-64可接受，但存在明显不足；建议进行审查
薄弱35-49多个领域存在实质性薄弱环节
存在风险20-34存在重大薄弱环节；采用时应保持审慎
危急1-19问题严重（项目被弃置、仅有单一维护者、缺乏基本工程规范）
评分画像
每条轴代表一个类别。形状比平均值更重要——健康的对象会填满整个图形，而“一峰一谷”式画像意味着某一维度的优势正掩盖另一维度的风险。
加权总体分 63 经校准后在公布的指数量表上为 71（记录校准 2026-08-02）。
所有权
软件包生态系统
| 注册表 | 软件包 | 版本 | 月下载量 | 版本数 | 最近发布 | 标签 |
|---|---|---|---|---|---|---|
| npm | @kage-core/kage-graph-mcp | 4.0.6 | 2,407 | 79 | 11 天前 | mcpkagememoryknowledge-graphcodexclaudeai-agentscode-graphokfagent-memory |
按类别列示的指标
活力
项目是否仍有生命——是否仍在编写代码，是否仍在发布版本？
86
开发活跃度
76良好
评分方式
| 36/36 | 推送新近度 — 最近一次推送于 7 天前 |
| 11.8/36 | 提交节奏 — 52 周中有 17 周有提交 |
| 18/18 | 提交量 — 最近一年 1,136 次提交 |
| 10/10 | OpenSSF Scorecard：Maintained — 30 commit(s) and 6 issue activity found in the last 90 days -- score normalized to 10 |
所用输入
| commits_last_year | 1,136 |
| human_commit_share | 1 |
| days_since_last_push | 7 |
| active_weeks_last_year | 17 |
发布纪律
100卓越
评分方式
| 27/27 | 有发布版本 — 已发布 11 个发布版本 |
| 36/36 | 发布时效 — 最近一次发布版本于 43 天前 |
| 27/27 | 发布节奏 — 约每 5.7 天发布一次 |
| 0/10 | OpenSSF Scorecard：Signed-Releases — 无数据 |
所用输入
| releases_count | 11 |
| latest_release_tag | v2.5.7 |
| releases_from_tags | 否 |
| days_since_latest_release | 43 |
| mean_days_between_releases | 5.7 |
已排除计分（无数据或不适用）：OpenSSF Scorecard：Signed-Releases。 其余权重已重新归一化。
社区与采用
项目是否拥有用户、下载量与关注度，并具备欢迎贡献者参与的配置？
56
流行度与采用
24存在风险
评分方式
| 24.2/60 | 星标 — 32 个星标 |
| 0/25 | 复刻 — 1 个复刻 |
| 0/15 | 关注者 — 0 位关注者 |
所用输入
| forks | 1 |
| stars | 32 |
| watchers | 0 |
| growth_state | unverified |
| growth_factor_pct | 100 |
| growth_unverified_reason | no_history |
社区健康
92优秀
评分方式
| 22.5/22.5 | README |
| 22.5/22.5 | 许可证 — 可识别的许可证（GPL-3.0） |
| 18/18 | CONTRIBUTING 指南 |
| 13.5/13.5 | 行为准则 |
| 0/7.2 | 议题模板 |
| 6.3/6.3 | PR 模板 |
所用输入
| has_readme | 是 |
| has_license | 是 |
| readme_badges | 5 |
| has_contributing | 是 |
| has_issue_template | 否 |
| has_code_of_conduct | 是 |
| readme_badge_services | shields.io |
| has_pull_request_template | 是 |
生态采用（下载量）
56中等
评分方式
| 45.1/80 | 月度下载量 — npm 合计每月 2,407 次下载 |
| 0/20 | 注册表被依赖数 — 该生态系统不报告此项 |
所用输入
| packages | @kage-core/kage-graph-mcp |
| dependents | — |
| ecosystems | npm |
| total_downloads | — |
| monthly_downloads | 2,407 |
已排除计分（无数据或不适用）：注册表被依赖数。 其余权重已重新归一化。
可持续性与治理
项目能否在其成员之外延续——巴士系数、响应能力、由谁支持，以及软件包的维护状况？
43
维护者韧性（巴士系数）
20存在风险
评分方式
| 9/54 | 巴士系数 — 1 位贡献者贡献了半数提交 |
| 5.2/22.5 | 提交分布 — 头号贡献者编写了 77% 的提交 |
| 2.7/13.5 | 贡献者广度 — 2 位贡献者 |
| 3/10 | OpenSSF Scorecard：Contributors — project has 1 contributing companies or organizations -- score normalized to 3 |
所用输入
| bus_factor | 1 |
| contributors_sampled | 2 |
| top_contributor_share | 0.769 |
议题与 PR 响应能力
33存在风险
评分方式
| 0/42 | 议题解决 — 0% 的议题已关闭 |
| 29.1/30 | PR 接受 — 已裁定的 PR 中 92/95 已合并 |
| 0/13 | Newcomer PR acceptance — 30 天内没有首次贡献者的 PR 得到裁决 |
| 0/15 | OpenSSF Scorecard：Code-Review — Found 0/1 approved changesets -- score normalized to 0 |
所用输入
| merged_prs | 92 |
| open_issues | 6 |
| closed_issues | 0 |
| prs_merged_7d | 0 |
| prs_decided_7d | 0 |
| prs_merged_30d | 9 |
| prs_decided_30d | 9 |
| issue_closed_ratio | 0 |
| closed_unmerged_prs | 3 |
| first_time_authors_30d | 0 |
| first_time_prs_merged_30d | 0 |
| first_time_prs_decided_30d | 0 |
已排除计分（无数据或不适用）：newcomer_pr_acceptance。 其余权重已重新归一化。
所有权与托管责任
34存在风险
评分方式
| 30/30 | 所有权背书 — 组织持有 |
| 0/20 | 已验证域名 |
| 0/25 | 所有者影响力 — kage-core 有 0 位关注者 |
| 4.1/25 | 既往记录 — 2 个公开仓库，账户约 0 年 |
所用输入
| followers | 0 |
| owner_type | Organization |
| is_verified | — |
| owner_login | kage-core |
| public_repos | 2 |
| account_age_days | 114 |
软件包维护
100卓越
评分方式
| 25/25 | 已发布且可解析 — npm 上有 1 个软件包 |
| 35/35 | 发布时效 — 最近一次发布于 11 天前 |
| 20/20 | 版本历史 — 79 个已发布版本 |
| 20/20 | 未被弃用 — 活跃，未被弃用或撤回 |
所用输入
| packages | @kage-core/kage-graph-mcp |
| ecosystems | npm |
| any_deprecated | 否 |
| min_days_since_publish | 11 |
工程质量
基础的工程与文档实践是否到位？
77
工程实践
68良好
评分方式
| 24/24 | CI 工作流 — 7 个工作流 |
| 24/24 | 存在测试 |
| 0/16 | Linter 配置 |
| 0/9.6 | Pre-commit 钩子 |
| 0/6.4 | .editorconfig |
| 20/20 | OpenSSF Scorecard：CI-Tests — 1 out of 1 merged PRs checked by a CI test -- score normalized to 10 |
所用输入
| has_ci | 是 |
| has_tests | 是 |
| has_editorconfig | 否 |
| has_linter_config | 否 |
| has_precommit_config | 否 |
文档
90优秀
评分方式
| 30/30 | README |
| 25/25 | 文档目录 |
| 15/15 | 文档 / 主页站点 — https://kage-core.com |
| 10/10 | 仓库描述 |
| 10/10 | 主题标签 — 10 个主题标签 |
| 0/10 | Wiki |
所用输入
| topics | agent-memory, ai-agents, claude-code, code-graph, codex, cursor, developer-tools, knowledge-graph, mcp, mcp-server |
| has_wiki | 否 |
| homepage | https://kage-core.com |
| has_readme | 是 |
| has_docs_dir | 是 |
| has_description | 是 |
安全
可见的安全与供应链实践是否稳固，且不存在未解决的高风险司法辖区暴露？
47
安全态势
36薄弱
评分方式
| 7.5/7.5 | Binary-Artifacts — no binaries found in the repo |
| 0/7.5 | Branch-Protection — branch protection not enabled on development/release branches |
| 2.5/2.5 | CI-Tests — 1 out of 1 merged PRs checked by a CI test -- score normalized to 10 |
| 0/2.5 | CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected |
| 0/7.5 | Code-Review — Found 0/1 approved changesets -- score normalized to 0 |
| 0.8/2.5 | Contributors — project has 1 contributing companies or organizations -- score normalized to 3 |
| 10/10 | Dangerous-Workflow — no dangerous workflow patterns detected |
| 0/7.5 | Dependency-Update-Tool — no update tool detected |
| 0/5 | Fuzzing — project is not fuzzed |
| 2.5/2.5 | 许可证 — license file detected |
| 7.5/7.5 | Maintained — 30 commit(s) and 6 issue activity found in the last 90 days -- score normalized to 10 |
| 0/5 | Packaging — 无数据 |
| 2.5/5 | Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 5 |
| 0/5 | SAST — SAST tool is not run on all commits -- score normalized to 0 |
| 0/5 | Security-Policy — security policy file not detected |
| 0/7.5 | Signed-Releases — 无数据 |
| 0/7.5 | Token-Permissions — detected GitHub workflow tokens with excessive permissions |
| 0/7.5 | Vulnerabilities — 36 existing vulnerabilities detected |
所用输入
| source | openssf_scorecard |
| checks_evaluated | 16 |
| scorecard_version | v5.5.0 |
| checks_inconclusive | 2 |
| scorecard_aggregate | 3.6 |
已排除计分（无数据或不适用）：packaging, signed_releases。 其余权重已重新归一化。
依赖安全公告
89优秀
评分方式
| 35/35 | 直接依赖不含已知公告 — 没有直接依赖携带已知公告 |
| 14.4/25 | 间接依赖不含已知公告 — 1 个受影响：hono 4.12.33 (moderate 5.3) |
| 40/40 | 没有长期未处理的公告 — 没有公告公开超过 90 天 |
所用输入
| source | osv |
| advisories | 1 |
| affected_packages | 1 |
| assessed_packages | 114 |
| unassessed_packages | 0 |
| affected_by_severity | moderate 1 |
| direct_affected_packages | 0 |
比对的是 npm:@kage-core/kage-graph-mcp@4.0.6 的运行时依赖闭包——安装已发布的软件包时真正被拉取进来的内容——共 114 个软件包。 未对可达性进行分析。
AI 就绪度
该仓库在多大程度上具备与 AI 编码代理协同开发与维护的条件？权重刻意设小（4%）：代理工具链是一项真实的维护信号，但完全不具备的仓库仍可达到 100/100。
74
AI 代理上下文与指引
85优秀
评分方式
| 45/45 | 代理指令 — AGENTS.md, CLAUDE.md |
| 0/15 | 机器可读文档（llms.txt） |
| 40/40 | 可读的提交历史 — 100 次人类提交中有 100 次说明了意图（结构化标题或解释性正文） |
所用输入
| has_llms_txt | 否 |
| legible_history_share | 1 |
| agent_instruction_files | AGENTS.md, CLAUDE.md |
| agent_instruction_max_bytes | 4,797 |
评分方式
| 18/18 | 一条命令的引导启动 — benchmark/Makefile |
| 22/22 | 自动化测试 |
| 0/11 | Lint / 格式化配置 |
| 11/11 | 静态类型检查 — mcp/tsconfig.json, platform/web/tsconfig.json |
| 10/10 | 可复现环境 — Dockerfile, lockfile |
| 10/10 | 已体现的代理实践 — 最近 100 次提交中有 69 次由代理编写或署名代理 |
| 0/8 | 自动化维护 — 未观察到自动依赖更新 |
| 5/10 | OpenSSF Scorecard：Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 5 |
所用输入
| has_nix | 否 |
| has_tests | 是 |
| lockfiles | package-lock.json |
| has_dockerfile | 是 |
| typed_language | 是 |
| bootstrap_files | benchmark/Makefile |
| has_devcontainer | 否 |
| has_linter_config | 否 |
| typecheck_configs | mcp/tsconfig.json, platform/web/tsconfig.json |
| agent_commit_share | 0.69 |
| toolchain_manifests | — |
| dependency_bot_commit_share | 0 |
面向模型的代码可读性
99卓越
评分方式
| 45/45 | 可类型检查的代码 — TypeScript（静态类型） |
| 53.9/55 | 可控的文件大小 — 采样的 386 个源文件中有 8 个超过 60KB |
所用输入
| primary_language | TypeScript |
| largest_source_bytes | 1,034,526 |
| source_files_sampled | 386 |
| oversized_source_files | 8 |
机器可读接口
20存在风险
评分方式
| 0/40 | API 模式（OpenAPI/GraphQL/proto） |
| 20/20 | MCP 服务器 |
| 0/40 | 可运行示例 |
所用输入
| example_dirs | — |
| has_mcp_signal | 是 |
| api_schema_files | — |
关键数据
32GitHub 星标
2贡献者
1,136最近 12 个月提交数
7距最近推送天数
11发布版本数
1巴士系数（bus factor）
6开放议题
npm, PyPI软件包生态系统数
数据采集警告
- Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
- GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository
更多细节
OpenSSF Scorecard 3.6 / 10
3.6综合
来自开源项目 OpenSSF Scorecard 的独立、工具无关的安全评估。每项检查奖励的是安全实践本身，而非特定供应商的工具。Scorecard 无法判定的检查项标记为 不适用，并从安全评分中剔除（绝不按零分计）。
| 10 | Binary-Artifacts | no binaries found in the repo |
| 0 | Branch-Protection | branch protection not enabled on development/release branches |
| 10 | CI-Tests | 1 out of 1 merged PRs checked by a CI test -- score normalized to 10 |
| 0 | CII-Best-Practices | no effort to earn an OpenSSF best practices badge detected |
| 0 | Code-Review | Found 0/1 approved changesets -- score normalized to 0 |
| 3 | Contributors | project has 1 contributing companies or organizations -- score normalized to 3 |
| 10 | Dangerous-Workflow | no dangerous workflow patterns detected |
| 0 | Dependency-Update-Tool | no update tool detected |
| 0 | Fuzzing | project is not fuzzed |
| 10 | License | license file detected |
| 10 | Maintained | 30 commit(s) and 6 issue activity found in the last 90 days -- score normalized to 10 |
| 不适用 | Packaging | packaging workflow not detected |
| 5 | Pinned-Dependencies | dependency not pinned by hash detected -- score normalized to 5 |
| 0 | SAST | SAST tool is not run on all commits -- score normalized to 0 |
| 0 | Security-Policy | security policy file not detected |
| 不适用 | Signed-Releases | no releases found |
| 0 | Token-Permissions | detected GitHub workflow tokens with excessive permissions |
| 0 | Vulnerabilities | 36 existing vulnerabilities detected |
直接依赖 8
| 注册表 | 软件包 | 版本约束 | 清单文件 |
|---|---|---|---|
| npm | @modelcontextprotocol/sdk | ^1.10.2 | mcp/package.json |
| npm | jose | ^6.2.3 | mcp/package.json |
| npm | pg | ^8.22.0 | mcp/package.json |
| npm | stripe | ^22.3.2 | mcp/package.json |
| npm | three | ^0.184.0 | mcp/package.json |
| npm | tree-sitter-wasms | ^0.1.13 | mcp/package.json |
| npm | typescript | ^5.0.0 | mcp/package.json |
| npm | web-tree-sitter | ^0.24.7 | mcp/package.json |
全部依赖 未采集
本报告未能采集到解析后的依赖集合：GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository
依赖安全公告 1
安装 npm:@kage-core/kage-graph-mcp@4.0.6 会引入 114 个包（直接与传递）：其中 1 个存在已知公告，0 个为直接依赖。
| 软件包 | 版本 | 关系 | 严重程度 | 公告数 | 修复版本 |
|---|---|---|---|---|---|
| hono | 4.12.33 | 间接 | 中 | 1 | 4.12.34 |
公告表示依赖图中记录的版本落入某条公告的受影响范围。可达性未经分析，且依赖图包含开发与测试的版本固定——某项发现可能只涉及工具链而非交付的软件。
原始 JSON 报告 机器可读
{
"data": {
"icon": {
"bytes": 876,
"width": 96,
"height": 96,
"rejected": [],
"collected": true,
"media_type": "image/svg+xml",
"source_url": "https://kage-core.com/assets/kage-eye.svg",
"source_type": "homepage",
"content_hash": "3c43749985d267d7bcce1cac68c225bd082ab1632dbc0220ff582caa1c5ef698",
"candidates_considered": 1
},
"repo": {
"topics": [
"agent-memory",
"ai-agents",
"claude-code",
"code-graph",
"codex",
"cursor",
"developer-tools",
"knowledge-graph",
"mcp",
"mcp-server"
],
"is_fork": false,
"size_kb": 38766,
"has_wiki": false,
"homepage": "https://kage-core.com",
"languages": {
"CSS": 42914,
"HTML": 31953,
"Shell": 106938,
"Python": 26076,
"PLpgSQL": 12037,
"Makefile": 733,
"Dockerfile": 4649,
"JavaScript": 645076,
"TypeScript": 4523091
},
"pushed_at": "2026-07-28T20:54:17Z",
"created_at": "2025-07-19T09:40:15Z",
"owner_type": "Organization",
"updated_at": "2026-08-04T00:40:10Z",
"description": "Persistent, verified memory for coding agents — so they stop re-explaining your codebase and never act on stale knowledge. Every memory is checked against your actual code; lives in your repo as plain files, shared via git. No account, no DB. Install: npx -y @kage-core/kage-graph-mcp install",
"is_archived": false,
"is_disabled": false,
"license_spdx": "GPL-3.0",
"default_branch": "master",
"license_spdx_raw": "GPL-3.0",
"primary_language": "TypeScript",
"significant_languages": [
"TypeScript",
"JavaScript"
]
},
"owner": {
"blog": null,
"name": null,
"type": "Organization",
"login": "kage-core",
"company": null,
"location": null,
"followers": 0,
"avatar_url": "https://avatars.githubusercontent.com/u/275632069?v=4",
"created_at": "2026-04-13T07:15:31Z",
"is_verified": null,
"public_repos": 2,
"account_age_days": 114
},
"license": {
"state": "standard",
"spdx_id": "GPL-3.0",
"raw_spdx": "GPL-3.0",
"file_present": true,
"scorecard_found": true,
"profile_has_license": true
},
"activity": {
"releases": [
{
"tag": "v2.5.7",
"kind": "patch",
"published_at": "2026-06-22T12:20:15Z"
},
{
"tag": "v2.5.6",
"kind": "patch",
"published_at": "2026-06-22T07:58:22Z"
},
{
"tag": "v2.5.5",
"kind": "patch",
"published_at": "2026-06-21T17:13:41Z"
},
{
"tag": "v2.5.4",
"kind": "patch",
"published_at": "2026-06-21T16:31:03Z"
},
{
"tag": "v2.5.3",
"kind": "patch",
"published_at": "2026-06-21T15:52:05Z"
},
{
"tag": "v2.5.2",
"kind": "patch",
"published_at": "2026-06-21T14:26:44Z"
},
{
"tag": "v2.5.0",
"kind": "minor",
"published_at": "2026-06-21T05:43:52Z"
},
{
"tag": "v2.0.0",
"kind": "major",
"published_at": "2026-06-11T15:23:15Z"
},
{
"tag": "v1.4.0",
"kind": "minor",
"published_at": "2026-06-05T19:06:08Z"
},
{
"tag": "v1.1.0",
"kind": "minor",
"published_at": "2026-05-02T13:07:21Z"
},
{
"tag": "v1.0.0",
"kind": "major",
"published_at": "2026-04-13T12:06:48Z"
}
],
"recent_commits": [
{
"oid": "d22cad56b28a26bb514ecede4ee0dbd509a46c3f",
"body": "Reform: memory truth + the orchestrator vertical slice",
"is_bot": false,
"headline": "Merge pull request #106 from kage-core/reform/p0-truth",
"author_name": "Kushal",
"author_login": "Kage18",
"committed_at": "2026-07-28T15:21:34Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ca27292e2a15b8f7a900ddb8dcab2cce6107590b",
"body": "…checkout never has\n\n`Kage PR Check` has been red on EVERY commit of this branch, and the cause was one packet:\nthe change-memory for reform/p0-truth grounded itself to fifteen paths under `.agents/skills/`\nand `.superpowers/` — all UNTRACKED. They exist in my working tree, so the gate passed\nlocall\n[…]\nocally, and master is green. Noted, not chased — but it\nis exactly why the perf guards I added this session count PROCESS SPAWNS instead of time.\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(memory): unblock the PR gate — change-memory cited files a clean …",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-28T15:15:52Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "be461176538a811e1bf78d6d58d7f727dedaa05a",
"body": "Six UI defects that 1574 passing tests could not see. The pattern is worth keeping: tests\nassert data correctness and are blind to layout, cascade collisions, element defaults, and a\nlabel attached to the wrong field.\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "chore(memory): capture the visual-sweep learning from the app pass",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-28T14:24:32Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "3d96a1ee65e5158516dc4ea82850bb5fb2ef0f60",
"body": "…ting a widget\n\nTwo more found by opening pages rather than by reading tests.\n\nThere were NO element-level styles for `input` or `button` anywhere in the stylesheet, so\nevery control that lacked a class fell back to the browser default — a white box with square\ncorners — against a dark theme. The Wo\n[…]\nd twice — once as a control, once as prose. Moved into\nthe page header where it belongs, stated once.\n\nmcp: 1574 pass / 0 fail. portal: 123 pass.\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(app): controls look like controls, and the review page stops floa…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-28T14:22:52Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "58a028b4b14c93f27dd3a87cde5cb799b6bdf02c",
"body": "A product that calls itself a memory orchestrator made you scroll 164 decision cards to find\none. There was no search and no filter on any of the twelve knowledge tabs.\n\nSearch plus health filters, added once to the shared browse list so every kind gets it: 44\ncomponents, 164 decisions, runbooks, fl\n[…]\na-pressed rather than a parallel class, so\nthe visual state and the accessible state cannot disagree.\n\nmcp: 1574 pass / 0 fail. portal: 123 pass.\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(knowledge): you can actually find memory now",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-28T14:17:38Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "c1402a75a8c45c4378db0210d33511641066f698",
"body": "… the tests\n\nSYSTEM MAP — empty lanes were reserving columns. The six lanes are a fixed vocabulary but\nmost repositories populate only some: this one has zero features, data models and owners. Each\nempty lane still consumed 240px, so the diagram wasted 40% of its width on blank canvas and\npushed the\n[…]\n — both read the same ledger, and my Proof\nfigure was simply hours older. The label was the real bug.\n\nmcp: 1574 pass / 0 fail. portal: 118 pass.\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(map, overview): three defects found by looking at the app, not at…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-28T14:13:15Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "a1e1d76b0462713d081de593b444ce7b61e04810",
"body": "…lf of the product\n\nFair criticism: the pages were functionally right and visually thin, the nav was a flat list\nof seventeen links (that is a wiki, not an operating surface), and the product calls itself an\norchestrator of memory AND AGENTS while having no agent surface at all.\n\nLIVE. The daemon st\n[…]\n restyling both. Namespaced to\n`.proof-*` and `.agent-status` so the shared components are untouched.\n\nmcp: 1573 pass / 0 fail. portal: 118 pass.\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(app): make it an app — live state, grouped IA, and the agents ha…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-28T13:37:13Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "c1a88d8191056c854b376ee1dd8329899c8f09bd",
"body": "…tself\n\nThere was no work item detail view at all — the board showed cards and clicking a title did\nnothing. That leaves the obvious question unanswerable: every card carries a stage NOBODY\nTYPED, so \"why does it say verifying\" has to be inspectable transition by transition, or\nderivation is just a \n[…]\n encodes on\nthe way out but not on the way in would 404 every real item while passing a one-way test.\n\nmcp: 1567 pass / 0 fail. portal: 118 pass.\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(work): a work item you can open, and a stage log that explains i…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-28T13:24:54Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "3802a8c49144b4b0bc51b6a6ac9445ea66609787",
"body": "Two defects visible the moment this repo planned its own work and the results hit the board.\n\nA work item titled \"… — .\" — the cluster key for root-level files was the literal string \".\",\nso anything grounded to README.md or package.json produced a title ending in a full stop that\ntells the reader n\n[…]\ngs, and the saturating-ranking trap — each with the\nmeasured before/after that makes it checkable rather than folklore.\n\nmcp: 1564 pass / 0 fail.\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(plan): work items get titles a human can read",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-28T12:27:10Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "76e152395c7c78d20286d984482f2ff71e6cfde5",
"body": "… a click is enough\n\nThe landing page listed \"reverify · supersede · retire\" as plain text. Naming a decision you\ncannot take is not a decision surface — the page whose entire thesis is \"act from here\" had\nno way to act.\n\nReverify is now one click, end to end: POST /v2/attention/reverify re-anchors \n[…]\ntale_reasons went to zero, the repo's stale count went 54 ->\n53, and the packet file changed on disk.\n\nmcp: 1563 pass / 0 fail. portal: 117 pass.\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(attention): the queue's decisions are actionable, and only where…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-28T12:21:51Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "c2562a311de561ca284f454d8ebe18287f8bc29c",
"body": "… acted on\n\nLooking at the landing page on this repo showed ten rows all reading \"severity 55\". A page\nwhose whole promise is \"decisions ranked by cost of delay\" was not ranking anything — and\nthe module's own comment claimed severity was \"a base per kind, aged upward\" while\nstale_critical and contr\n[…]\nat saturates is not a ranking.\n\nLive on this repo, the queue now runs 85 down to 67 in recall order instead of ten 55s.\n\nmcp: 1563 pass / 0 fail.\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(attention): the queue ranks by cost of delay, and its rows can be…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-28T12:16:11Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "c77301b8038ff5f761e7a4f60d1fc4e5ab916b4e",
"body": "…ogfooding it\n\nLoading the Work board took 6-10 SECONDS on every single request, and the page sat on\n\"Deriving…\" long enough to look broken. Three separate causes, all found by pointing the\nproduct at its own repository:\n\n1. `observedCommits` forked a `git diff-tree` per commit to learn which files \n[…]\nanch's own open\nPR moved it to verifying. Every step names its evidence and no status was ever typed.\n\nmcp: 1560 pass / 0 fail. portal: 113 pass.\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "perf(board): 6-10s per page load -> 33ms, and fix two bugs found by d…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-28T12:09:11Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "38d27594d05779374d443540051ff2ba56cf527d",
"body": "Created by `kage plan` from the intent, then claimed — dogfooding the loop the branch\nitself builds.\n\n[kage:repo:https-github-com-kage-core-kage:proposal:close-the-orchestrator-p0-truth-loop-one-writer-for-stage-d-benchmarks-178523906]",
"is_bot": false,
"headline": "chore(memory): track this branch's orchestrator work as a real work item",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-28T11:58:26Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "740a6b0052322e2597e5f38d2da884da2f46a1ea",
"body": "…rning to 5.9s\n\n`kage plan` — the command that turns an intent into work items — did not return. Not slowly:\nat all. I killed it at eight minutes. The cause was `kageRisk` at 118 SECONDS, and the cause\nof THAT was not slow git but the shape of the queries:\n\n gitCoChangePartnersForPath 1 + 80 spaw\n[…]\ncesses does one call fork\" is exactly the property\nthat regressed. It fails at 57 spawns for 3 targets on the old code.\n\nmcp: 1557 pass / 0 fail.\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "perf(kernel): one git history pass — `kage plan` goes from never retu…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-28T11:57:46Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "6ee312d0da9b67923e78efe94b38cc4deebb23ff",
"body": "…ublish a real verdict\n\nTwo GitHub-side gaps from the audit, both of which had passing tests around them.\n\n1. `publishCheck` sent NO BODY. head_sha, conclusion, title and summary were accepted by the\n signature and silently dropped, so a check that reported \"published\" said nothing at all on\n th\n[…]\n and from\nthe actions condition, which would have stripped Release and Approve off an item in review.\n\nmcp: 1555 pass / 0 fail. portal: 113 pass.\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(orchestrator): `verifying` derives from an open PR, and checks p…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-28T11:43:52Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "234e465dc0e673f871fd7cfc017c4dc4a48891bb",
"body": "The Proof page was in the design and existed nowhere: no page, no route, and no data\nbehind it. Cycle time, estimate accuracy, and attention burn-down had zero hits anywhere\nin the repo. This builds the whole column — engine, route, DTOs, page — on this rule:\n\n A metric is measured, or it is absent\n[…]\nts, and the\nmeasured cards had no card chrome at all because `.entity-card` turns out to be unstyled.\n\nmcp: 1552 pass / 0 fail. portal: 113 pass.\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(proof): the fourth surface — what Kage measurably did",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-28T11:31:52Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "030331640831668ebcdddffb8d61fcf416c951fe",
"body": "…, not a click\n\n`done` previously required a gate command, so an item whose work actually shipped\nsat at `building` forever unless someone remembered to approve it. Merging is\nobservable, and nothing about a merge needs a human to assert it.\n\nThe subtlety that made this more than a one-liner: once a\n[…]\nt cannot see — it needs PR events from\nthe GitHub App. The header comment now says that instead of the stale claim that\n`done` comes from a gate.\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(orchestrator): merging closes the loop — `done` derives from git…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-28T11:20:20Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "237ef5c0b3e87b242741383a76e5cbf8e5b35502",
"body": "…decisions\n\nTwo gaps, one commit, because the second was found by exercising the first.\n\nMCP verbs — agents are the orchestrator's primary consumer and had no way in.\nkage_queue (claimable work with derived stage and blast paths), kage_brief (what\nthe team already knows about that code, before the f\n[…]\nfabricate a review nobody\nperformed. A failed stored write never loses the decision: derivation reads the\nlog, which remains the source of truth.\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(orchestrator): agents can reach the board; one writer for stage …",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-28T10:50:41Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "1d53be27c7a51d7e77f78c328a98a4d6117b4253",
"body": "…ame gate\n\nCorrecting a claim I repeated for several turns: capture does NOT only fire at\nsession end. CompilerScheduler.notify() runs on every event append, debounced to\na setImmediate tick, and buildEpisodes already closes an episode on fail->pass,\nsession_end, or a 30-minute gap. Mid-session comp\n[…]\nnnot. A model that\nis down, slow, or simply absent degrades the compiler to exactly its previous\ndeterministic behaviour — never to a failed run.\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(compiler): the semantic pass runs in the pipeline, through the s…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-28T10:47:11Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "c984ac7db7d4f3ac0e28d3e6737eaa9014d188dd",
"body": "Four reverified with evidence — their claims re-read as accurate against the new\norchestrator surfaces (the same-origin-API gotcha is in fact reinforced by\nmounting /v2/work and /v2/commands on the daemon that serves the SPA).\n\nOne superseded rather than reverified: the merge-driver bug_fix asserted\n[…]\nlonger true, so\nre-stamping it would have laundered a false claim. Replaced by a packet\ndescribing the field-level three-way merge that fixed it.\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "chore(memory): reconcile the five packets this branch's code moved under",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-28T05:09:30Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "f4e87dd6a1b7f3764d830658937c2a72f82626db",
"body": "model-extractor.ts has been written, tested and CALLERLESS since it landed: the\nseam existed, no provider ever filled it, so the semantic pass never ran once.\n\nKage already sits between the agent and the model, so it can borrow rather than\nown. When a /v1/messages request passes through, the proxy r\n[…]\nindistinguishable from an empty episode.\ncost_usd is null, never a computed zero: the loopback measures tokens and does\nnot know the user's rate.\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(compiler): the proxy-loopback provider — AI without holding a key",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-28T05:07:24Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "f1c52e144cb0cc53bcdbe051de1ad9a72d34f73c",
"body": "The orchestrator engine had no product on top of it — stages, briefs and\nestimates were reachable only from the CLI. This adds the two surfaces the\ndesign calls for:\n\n- GET /v2/work: derived board (stage + evidence + brief knowledge + estimate),\n kernel-side so it works on any Node build\n- POST /v2\n[…]\nefused\nin the UI with 'self-approval blocked'. The same event log drives kage work,\nso the app and the CLI derive identical state from one truth.\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(app): the Work board and the command loop",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-28T03:55:43Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "1f762ee6f548bb78714d8a3a4e604b0d64e20cdf",
"body": "CI caught a shipped change-memory packet citing untracked local tool dirs\n(.superpowers/, .agents/) — paths that exist in one working tree and no clean\ncheckout, so the packet was hard-stale on arrival. Grounding paths now filter\nthrough git ls-files (tracked or staged): a file grounds a proposal on\n[…]\ngenerates this branch's change-memory packet with clean grounding and\nreverifies the five packets whose cited files gained orchestrator surfaces.\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(memory): change-memory grounds only to commit-adjacent paths",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-27T19:05:31Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "342d05715138ef511b609160b484720ad21f492d",
"body": "The audit-mode onboarding copy lived on a page that could never render\n(needsOnboarding is unsatisfiable); the landing is now the Attention queue,\nwhich states its own goal condition. Shell and keyboard journeys unchanged.\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "test(e2e): the fresh-operator journey lands on Attention",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-27T18:47:00Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "fd21375dd975612c56593e5428d5da8205dc3362",
"body": "Attention leads and is the root; the five stored-but-unsurfaced knowledge kinds\nare in the nav; Costs/Integrations/Settings/Billing left it because they render\nno live data (their routes still resolve for bookmarks). These tests encoded the\nold IA on purpose — updated deliberately with the product decision, not deleted.\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "test(portal): information architecture tests assert the new contract",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-27T18:45:18Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "c9e6339b4132f5310a6de9ce09e6cfb9e525e839",
"body": "Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "chore: memory reconciliation for the reform branch",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-27T18:41:38Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "b6e39041a0a9f45137de596af713213d3a2e0db8",
"body": "Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "docs: product plan, technical design, and Graphify parity analysis",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-27T18:40:08Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "b126da9748579d27f5b185bdcf97aefb0d5d0f3b",
"body": "…s on Attention\n\n- kage plan: intent -> grounded, estimated work items\n- kage work: the derived board with the attention queue on top\n- kage claim also emits the command event the reducer reads\n- daemon: GET /v2/attention (kernel-side, works without node:sqlite) and the\n portal's POST write path mo\n[…]\n serves the SPA\n- app: Attention is the landing page; knowledge tabs for the five surfaced\n kinds; nav lists only surfaces that render live data\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(surfaces): kage plan/work, claim events, /v2/attention, app land…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-27T18:39:41Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "e52bee37fdcf6ceecc35bf713f7c7cd8676c3c89",
"body": "…core\n\n- command events: append-only JSONL, two decision kinds, self-approval rejected\n at append\n- correlator: [kage:id] trailer > branch slug > blast overlap; confidence-ranked;\n ambiguity is null; weak NEVER fires a transition\n- reducer: stages derived from commands + git evidence, every step c\n[…]\ninvent a number\n- plan: intent -> bearing memory surfaced -> grounded paths clustered by repo\n area -> claimable proposals with blast + estimate\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(orchestrator): derived stages, attention, estimation, plan loop …",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-27T18:39:11Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "4d8e5aca4a7c65bbd0a4c8e18189eae5541a44d8",
"body": "…knowledge routes\n\n- packet-importer imports grounded live packets as verified, with evidence rows\n built from their cited paths (createClaim refuses verified without evidence);\n ungrounded stays proposed. 0 -> 259 injectable claims on this store\n- merge path upgrades claims stranded at proposed b\n[…]\nl memory)\n- /v2 routes for contracts, data-models, invariants, incidents, documents +\n generic entity_detail; AttentionItemDto/AttentionQueueDto\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(model): grounding gates injection, not approval; document kind; …",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-27T18:38:32Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "ff73a508d698221449d323fd56b8c44fd93d54c9",
"body": "…erges\n\n- observations resolve against the project dir; host paths outside it are\n dropped (110 of 110 recorded paths were outside the repo)\n- ANCHOR_SYMBOL_KINDS now matches what extractSymbols emits: constants anchor\n (2089 stored anchors vs 427 functions), dead kinds removed — whether a memory\n\n[…]\nlls\n- workItemBrief: what the team knows + blast radius for a work item\n- .gitignore tracks .agent_memory/conflicts/ so a lost edit is reviewable\n\nCo-Authored-By: Claude Opus 5 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(memory): symbol-accurate staleness, honest provenance, lossless m…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-27T18:38:04Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "3a8373fc841cf259fa3520d01b478962d5ac2891",
"body": null,
"is_bot": false,
"headline": "chore: kage sync — rebuild graphs and update memory [skip ci]",
"author_name": "kage-bot",
"author_login": "Kage-Bot",
"committed_at": "2026-07-25T05:45:45Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "28da603acfa89a795a7ec49380cca268f25b1526",
"body": "Capture fixes + one-command onboarding (published as v4.0.6)",
"is_bot": false,
"headline": "Merge pull request #105 from kage-core/codex/kage-vnext-implementation",
"author_name": "Kushal",
"author_login": "Kage18",
"committed_at": "2026-07-25T05:43:03Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "80098784ae1ee422387cb19100c6b641f3f2d641",
"body": null,
"is_bot": false,
"headline": "merge: master under the 4.0.6 capture + onboarding work",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-25T05:37:00Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4800de570754097ef48ec6fe6d00fb36a77dde37",
"body": "…mand one\n\nThe npm README is the page people actually land on when they find the package,\nand it documented the HARDER path — six commands (global install, init, setup,\nverify, context) — while the root README documented one. It also pointed at stale\nkage-core.github.io URLs.\n\nIt now leads with `npx\n[…]\ngent's stated\nintent is now recorded (ingestion was blind), and the derivability gate that was\nswitched off by its own guard now actually runs.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "docs: the npm page now shows the one-command install, not the six-com…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-25T05:33:44Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "232822bed52feade2a28b38013141e105c8c1c29",
"body": "The store audit reported ~44% non-derivable content — more than half of memory\nrestating code an agent could just read. T2 had already built the check that is\nsupposed to prevent this. Measuring showed why it never fired.\n\nThe check is skipped when a body carries \"trigger language\", and that guard\nm\n[…]\nenough to real bodies that the two cannot be varied\nindependently inside a fixture — hence the pure predicate.\n\nSuite: 1447 passing, 0 failing.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: the derivability gate existed and was switched off by its own guard",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-25T05:21:14Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "a8ee6a2ad7360d544b05e64d46a342e813cf3514",
"body": "…ruction\n\nCapture could not decide what was worth saving because the deciding signal was\nnever on disk. Audited on a real session store: 624 evidence events, of which\n498 tool_result carried the entire payload {tool, path, outcome} and ZERO events\ncarried assistant prose — no such event type existed\n[…]\nailing.\n\nScope note: this lands the Anthropic gateway only. The OpenAI and Gemini\ngateways need their own prose parsers for the same treatment.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: capture the agent's stated intent — ingestion was blind by const…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-25T04:56:22Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "a3688a2b06ee23c83324455c170d9b6c532f4812",
"body": null,
"is_bot": false,
"headline": "chore: kage sync — rebuild graphs and update memory [skip ci]",
"author_name": "kage-bot",
"author_login": "Kage-Bot",
"committed_at": "2026-07-23T19:13:06Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d2be7beb7ac3905b7758b5dd32fd79daa17b65a0",
"body": "Fix: kage-sync silently deletes concurrently-added memory packets",
"is_bot": false,
"headline": "Merge pull request #104 from kage-core/codex/kage-vnext-implementation",
"author_name": "Kushal",
"author_login": "Kage18",
"committed_at": "2026-07-23T19:10:26Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "82f02e147e0c4faa448dc46ff4c3dc51d2c5bfde",
"body": null,
"is_bot": false,
"headline": "merge: master under the kage-sync memory-loss fix",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-23T19:04:11Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "39d0951354bf98e3e3153219354ba8ac69d1d235",
"body": "The Kage Sync workflow runs on EVERY push to master, so its own push routinely\nloses the race to a concurrent commit (a `kage learn` write, a PR merge). Its\nreconciliation — `git reset --soft origin/master` then `git add .agent_memory/`\n— re-staged THIS job's older working tree, which never had the \n[…]\nconcurrent packet survives — it passes\nwith the fix and FAILS without it. The three lost packets are recovered from git\nhistory in this commit.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: kage-sync no longer deletes concurrently-added memory packets",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-23T19:03:43Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "b5719dddf2d9939e67ed7ab7a4945d28e319dc72",
"body": null,
"is_bot": false,
"headline": "chore: kage sync — rebuild graphs and update memory [skip ci]",
"author_name": "kage-bot",
"author_login": "Kage-Bot",
"committed_at": "2026-07-23T10:35:09Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2dca7c0a9c61ff908551f957b843cd32a57c9c0d",
"body": "…me unlock CTAs [skip ci]\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "memory: value dashboards lead with measured value; empty metrics beco…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-23T10:31:34Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "839e96ddcd6330124d748f9229b767afd114bf91",
"body": "Overview leads with measured value, not eight Unavailable cards (published as v4.0.5)",
"is_bot": false,
"headline": "Merge pull request #103 from kage-core/codex/kage-vnext-implementation",
"author_name": "Kushal",
"author_login": "Kage18",
"committed_at": "2026-07-23T10:31:12Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a0cc24d0de7f42fbe691a81ac8356b4f837c8dbd",
"body": null,
"is_bot": false,
"headline": "merge: master (sync-bot) under the 4.0.5 Overview redesign",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-23T10:26:28Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "31dcae982183f8c10b26ceadba86e5f3ea886ca8",
"body": "…ds (4.0.5)\n\nThe Overview — the portal's value dashboard — led with eight Unavailable/0%\nmetric cards and buried the genuinely measured value below the fold. A user\nasked why everything was unavailable and why the UX was so bad; both were fair.\nThe cards are honest (Kage never fabricates), but leadi\n[…]\n workspace-team behaviours still pinned), backend 1434/0. Browser\nverified: leads with real numbers, unlock hints show, git identity populates.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: Overview leads with measured value, not eight \"Unavailable\" car…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-23T10:21:50Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "588ee49bce89a79639a1c8e76463342aeed28944",
"body": null,
"is_bot": false,
"headline": "chore: kage sync — rebuild graphs and update memory [skip ci]",
"author_name": "kage-bot",
"author_login": "Kage-Bot",
"committed_at": "2026-07-23T09:47:28Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "15d938e95391b595757cddd5322763c48e5fbdbb",
"body": "…kip ci]\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "memory: capture the relative-vite-base deep-link blank-page gotcha [s…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-23T09:44:18Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "7075f1f07d672c0106e80973a25167dca4f3442f",
"body": "Portal browse tabs built for real + blank-detail-deep-link fix (published as v4.0.4)",
"is_bot": false,
"headline": "Merge pull request #102 from kage-core/codex/kage-vnext-implementation",
"author_name": "Kushal",
"author_login": "Kage18",
"committed_at": "2026-07-23T09:43:57Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4b94a97bfe5612c079dd6393cdaca8c08d99b402",
"body": null,
"is_bot": false,
"headline": "merge: master (sync-bot) under the 4.0.4 browse-tabs work",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-23T09:37:24Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "26cd3ca0c41c28c70ee9f422838cc3f85ba7a3b9",
"body": "…-links (4.0.4)\n\nThe portal's five core browse tabs — Features, Components, Flows, Runbooks,\nDecisions — were PagePlaceholder stubs that rendered \"arrives in a later Phase C\ntask\". Phase C was marked complete but shipped them as placeholders; a user\nasked why the portal was empty, and it was half-bu\n[…]\nCosts re-renders Agent Tasks; Billing is\n\"no workspace\" locally; Overview money metrics read Unavailable until receipts\nare priced. Follow-ups.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: build the portal's browse tabs for real + fix blank detail deep…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-23T09:33:16Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "372247ab2f4553709a9103154e4f089c7ed61723",
"body": null,
"is_bot": false,
"headline": "chore: kage sync — rebuild graphs and update memory [skip ci]",
"author_name": "kage-bot",
"author_login": "Kage-Bot",
"committed_at": "2026-07-23T08:53:34Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b7cd68749e508731cab57a34d19797a5e6195380",
"body": "Portal: serve its API (4.0.2) + survive a first open — populate, de-noise, one surface (4.0.3)",
"is_bot": false,
"headline": "Merge pull request #101 from kage-core/codex/kage-vnext-implementation",
"author_name": "Kushal",
"author_login": "Kage18",
"committed_at": "2026-07-23T08:48:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "edf7aa54d197ee1d2adca3f6615d658b770540a8",
"body": null,
"is_bot": false,
"headline": "merge: master (sync-bot) under the 4.0.2/4.0.3 portal work",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-23T08:43:10Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2ba61ca8b210e75d1d2dd7c1958aeca1615b00f1",
"body": "A SPA served by one server needs its API mounted on THAT server; a route\nexisting on a different server does not satisfy a same-origin fetch.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "memory: capture the same-origin portal API gotcha [skip ci]",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-23T08:40:10Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "a85233a90872f03aa0af36c1611fab39e5dfdc9f",
"body": "… one surface (4.0.3)\n\nDirection: the knowledge portal is the surface Kage sells on, so it has to look\nright the first time a prospect opens it. Three changes toward that:\n\n1. Never empty. bootstrapPortalModelIfEmpty() populates the repository model\n from the repo's approved packets the first time\n[…]\n-heavy repos, packet->entity labels beyond\nchange-memory are still rough, and a demo should run on a product repo not\nKage-on-Kage. Follow-ups.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: make the portal survive a first open — auto-populate, de-noise,…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-23T08:39:36Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "cc57da35a38153a30d8b6b42ba3900866daa6c73",
"body": "4.0.1 fixed the portal SHELL (assets ship, /app/ serves). But the SPA fetches\nits data from `/v2/...` SAME-ORIGIN (main.tsx: new KageApi(\"\", token)), and the\n`kage viewer` daemon served no /v2 routes — so the shell loaded and every panel\nshowed \"Repository knowledge is unavailable: Kage API 404\".\n\nT\n[…]\n\nstale-withheld, packet composition, live injection gate) with no console errors.\n3 new tests pin the dispatch. Suite: 1427 passing, 0 failing.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: serve the portal's /v2 read API from the viewer daemon (4.0.2)",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-23T08:10:36Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "868777611176ab182d12f6036e3a2c621c83c345",
"body": null,
"is_bot": false,
"headline": "chore: kage sync — rebuild graphs and update memory [skip ci]",
"author_name": "kage-bot",
"author_login": "Kage-Bot",
"committed_at": "2026-07-22T22:59:17Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b648293ce912cb3372f24152ed44abeacb065d82",
"body": "…e-checkout test [skip ci]\n\nVerify packaged features from an installed tarball, not a source checkout.\nFull context in the v4.0.1 portal fix. [[gotcha-a-packaged-feature-...]]\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "memory: a packaged feature can 404 from npm while passing every sourc…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-22T22:56:36Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "f9d26cae905bdb58137f386b795c0d183b11c918",
"body": "Fix: ship the knowledge portal so kage viewer /app/ works (published as v4.0.1)",
"is_bot": false,
"headline": "Merge pull request #100 from kage-core/codex/kage-vnext-implementation",
"author_name": "Kushal",
"author_login": "Kage18",
"committed_at": "2026-07-22T22:55:42Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "692a8fa011eb2f2f89c582cb3ad84b59048bd314",
"body": null,
"is_bot": false,
"headline": "merge: master (sync-bot) under the 4.0.1 portal fix",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-22T22:34:06Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "571b45a3cf7d42107c301b8c259f7ea9fa5a4615",
"body": "…rks (4.0.1)\n\n4.0.0 shipped the portal (`/app/`) broken for every npm user. Two faults:\n\n 1. the daemon resolved the portal ONLY from the monorepo path\n `../../platform/web/dist`, which does not exist in an installed package, and\n 2. the build was never bundled into the tarball — `files` white\n[…]\n the installed `kage viewer` — `/app/` returns HTTP 200, assets 200,\nSPA deep links 200. 5 new tests in portal-serving.test.ts pin both halves.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: ship the knowledge portal in the package so kage viewer /app/ wo…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-22T22:30:02Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "178226d7978dcf9fa372ec93b12734a363016f5d",
"body": null,
"is_bot": false,
"headline": "chore: kage sync — rebuild graphs and update memory [skip ci]",
"author_name": "kage-bot",
"author_login": "Kage-Bot",
"committed_at": "2026-07-22T22:12:23Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b78f776b8b1e212976a8d91b1fdc318306225de8",
"body": "Auto-attach, honest attach status, and the how-to docs (published as v4.0.0)",
"is_bot": false,
"headline": "Merge pull request #99 from kage-core/codex/kage-vnext-implementation",
"author_name": "Kushal",
"author_login": "Kage18",
"committed_at": "2026-07-22T22:08:59Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "04e9352b49f6969c32323581c6440aeb2e4a8281",
"body": "Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "memory: capture the GitHub packet-merge-driver gotcha from the v4.0.0 PR",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-22T22:03:50Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "29572cce7ab8dddfbe068742bebc16e09c98a1fb",
"body": "Only a single auto-generated change-memory packet overlapped; the repo's\nkage merge-packet driver resolved it newest-wins and preserved the losing\nside under .agent_memory/conflicts/ for review. No code or docs conflicts.",
"is_bot": false,
"headline": "merge: bring master's sync-bot graph rebuild under the v4.0.0 work",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-22T22:01:15Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "528386a4f597c2285b74e54c9d352f3803897c10",
"body": "Adds docs/USING_KAGE.md (the practical manual: setup, proxy, daily use, team\nworkflow, troubleshooting, a command map by intent) and docs/HOW_IT_WORKS.md\n(the mechanism: the two delivery channels, proxy modes and cache safety, what\nis stored and what is refused, the trust model, how recall ranks). L\n[…]\n1419 passing / 0 failing; portal 109/109; kage check 0 drift, exit 0;\nfull install -> index -> learn -> context loop exercised in a fresh repo.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "docs: a manual for using Kage, and one for how it works",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-22T21:41:54Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "c65a60699dc21f44851706ba7391f682121122e4",
"body": "Two honesty bugs, both found by asking why a restart did not attach.\n\n1. attach status read the settings file alone. The Claude desktop app injects\n ANTHROPIC_BASE_URL itself and never reads project settings, so a correct\n settings file attaches nothing there and no restart ever will. Reporting\n\n[…]\ntract is asserted with explicit budgets in\n adapters/adapter.test.ts, which drives fail-open at 50/60/80 ms.\n\nSuite: 1416 passing, 0 failing.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: kage status said \"wired\" when the host had overridden it",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-22T19:51:59Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "7fe7f90f7e5b2631d0e867aa27e654873ed4d2ed",
"body": "A healthy proxy proves nothing on its own. Attach is per-directory\n(env.ANTHROPIC_BASE_URL in .claude/settings.local.json, read by the agent at\nstartup from the directory it was launched in), so wiring one directory while\nrunning the agent from another attaches NOTHING — silently. Everything looks\nh\n[…]\n, never silently claimed as attached;\n- unreadable/malformed settings say so instead of being read as either state.\n\n6 tests. Suite: 1484/1484.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: kage status reports whether sessions here are ACTUALLY attached",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-22T19:30:58Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "3e865aea362168d06f0cd6f128afd5b4a81661fd",
"body": null,
"is_bot": false,
"headline": "memory: capture auto-attach decision + hook set-e/resolver gotchas",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-22T15:33:27Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "0a6659e0bf560133018db8448e16ed1e517109ab",
"body": "'kage run -- claude' was the wrong UX: attach should be zero-thought.\nkage setup claude-code --write (and therefore kage install) now wires\nANTHROPIC_BASE_URL=http://localhost:8788 into the project's PERSONAL\n.claude/settings.local.json (uncommitted, this machine only), so every\nClaude Code session \n[…]\ngenerated (drift guard enforced it). 4 new tests\n(auto-attach wiring, user-value preservation, idempotence, ensure-up\nblock). Suite: 1478/1478.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: sessions auto-attach to the kage proxy — no kage run, no export",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-22T15:33:01Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "890ee6115b010af15528a31d5e957fdd5b0de4cb",
"body": null,
"is_bot": false,
"headline": "chore: kage sync — rebuild graphs and update memory [skip ci]",
"author_name": "kage-bot",
"author_login": "Kage-Bot",
"committed_at": "2026-07-22T15:02:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "866e51e578abf95e917f03ac39d978481b2a35a6",
"body": "Kage v4.0.0 — the verified OKF memory layer, complete: all-agent proxy, history digestion, team workspace, measured end-to-end",
"is_bot": false,
"headline": "Merge pull request #98 from kage-core/codex/kage-vnext-implementation",
"author_name": "Kushal",
"author_login": "Kage18",
"committed_at": "2026-07-22T14:59:39Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e2f3d577b46d7f2d68a70eb747706479a94edd0d",
"body": "…otspot packets (kage loop before merge)\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "memory: capture viewer-startup + site-narrative learnings; reverify h…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-22T14:58:52Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "ce705a39abb6b1057410469bcd4775d904a38e22",
"body": "… v6 design\n\nChecked the old site (fee6059^) side by side and ported every marketing asset\nthe redesign had dropped, updated only where the product truth moved:\n- Hero: the 'Built on Open Knowledge Format · Google Cloud' badge, the exact\n old headline ('Google shipped OKF. Kage keeps it true.'), th\n[…]\napability sections (proxy wires, honesty gates, history digestion, team\nreport, honest limits) retained. Page parses; hero verified in-browser.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(site): restore the full pre-redesign customer narrative into the…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-22T13:48:54Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "d72ffa6ee193bbb8244f872b209ef0a6edba2400",
"body": "… narrative\n\nThe redesign dropped the strategic product placement — 'Google shipped OKF;\nKage is the verification layer that keeps it true' — and led with benchmark\nreceipts instead. A homepage's job is customer appeal: the anchor to a known\nstandard, the why-now, the story. Restored:\n- Title/descri\n[…]\n\n Kage's deterministic verification does) / the reach (one layer, every\n agent). Metrics remain in full on benchmarks.html where they belong.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix(site): restore the OKF verification-layer positioning as the lead…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-22T13:28:43Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "42c41aeb9900fedb07584b62dc403dd73bda46bb",
"body": "…e to a child process)\n\nstartViewer pre-generated ~25 JSON reports SYNCHRONOUSLY before listen() — on\na loaded repository (this one) that is minutes of xray/capabilities/benchmark\nwork with the port dead the whole time; users ran kage open and stared at\nnothing. Moving the grind after listen() was n\n[…]\neload).\n\nVerified live: viewer + portal both 200 within ~3s of launch (previously 000\nafter 90+ seconds); daemon tests 15/15; full suite green.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "fix: kage open serves the viewer in seconds, not minutes (reports mov…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-22T13:01:02Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "af148f3d74a28910ac2620bf7618ba649bf7400e",
"body": "…era rows, web surfaces)\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "docs: refresh the capstone to the v4.0.0 shipped state (1474/1474, T-…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-22T08:29:12Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "0acef31e5950f932269e28fe5d124ef74cca6a6f",
"body": "…ify viewer + portal\n\nCompletes the web redo the v6 design commit (fee6059) started, hand-built\nafter the workflow's page agents were killed by the session limit:\n\n- guide.html: the real journey — install (bootstrap first win), kage up\n (three wires named: Anthropic, OpenAI-compatible, Gemini), the\n[…]\neen.\n\nAll internal links resolve, ?v=6 on all five pages, every page parses,\nverified rendering in-browser (screenshots of index + benchmarks).\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(web): retell guide/benchmarks/releases/demo on the v6 system; un…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-22T08:27:19Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "fee6059b4830736d5ced58b290754564b674f1af",
"body": "site.css v6: documented class contract (receipt with measured tag, term,\ngrid-2/3/4, cta, footnote, skip-link), dark-first tokens kept, focus-visible\nstates, reduced-motion, anchor scroll-margin; legacy aliases (.terminal,\n.cards*) preserved so existing pages keep rendering.\n\nindex.html: proxy-prima\n[…]\nt called out, and a what-we-will-not-claim footnote (no pilots yet,\nconditional value). All numbers from this repo's benchmarks; none invented.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat(site): v6 design system + honest measured home page",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-21T18:56:16Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "0247df22a189822f48da03cbdc8a068b12a91606",
"body": null,
"is_bot": false,
"headline": "memory: capture T1-T6 product-honesty pass learnings",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-21T17:28:46Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "db30629d5aaf153a5a9d12cec0d9a03ffe47560a",
"body": "…sparency (T5)\n\n/v2/team-report serves the kage-report-team payload through the portal\n(assembled lazily only for its own route; a failure returns report: null —\nthe portal renders an honest unavailable state, never a fake healthy one).\nTeamReportDto joins the backend DTO source of truth; frontend t\n[…]\ned/estimated separation, injected-nothing\nrendering, unexercised-gate honesty, null report). Frontend 109/109 + build\nclean; backend 1474/1474.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: portal persona views — lead value dashboard + IC injection tran…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-21T17:28:18Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "8b6131559b4c1cbd1dda8c32582c33b97b55915e",
"body": "…erride (T4)\n\nDAY-ONE UX: a fresh repo answered its first recalls with nothing, hiding the\nvalue exactly when a new user is judging the tool. kage install now\nbootstraps ONE honest starter runbook derived from package.json scripts\n(verifiable ground truth; runbook-shaped — the highest-demand class a\n[…]\nlity as assertions: first recall\nhits the runbook at rank 1 and clears the injection gate on an empty-history\nrepo. Suite: 1474/1474 aggregate.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: day-one value — bootstrap runbook + query-coverage injection ov…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-21T17:22:56Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "bea9fafa5334a224054eef1f3244392ac3c1c0f3",
"body": "Every claimed gain tied to its re-runnable proof (the tribal-knowledge A/B,\ninjection gate 0 false rate, kage report team, staleness withholding, ~93%\nhistory digestion, all-agent proxy, real-PG isolation gate, OKF-in-git no\nlock-in) plus the honest boundary: no pilots run, fixture-vs-live interop\nnamed, and the conditional-value truth stated plainly — Kage pays where\nknowledge is tribal, not where it's already in the code.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "docs: WHY_TEAMS — the team pitch with receipts (T6)",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-21T17:11:08Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "0df0cf2aca682c29d839e643fd8de6f5d6ddcf16",
"body": "Aggregates only what is measured, labels what is estimated, and says\n'unavailable' instead of fabricating:\n- Value: recalls served + stale withheld (measured counts) vs read-vs-source\n and replay tokens (kept _estimated, never mixed).\n- Injection gate (LIVE): composeInjection now records every corp\n[…]\nnew tests (aggregation, honest-unavailable -> live population through the\nREAL injectMemory path, manual events, classifier). Suite: 1471/1471.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: kage report team — the lead-facing 'is this helping?' report (T3)",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-21T17:10:18Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "8e435c38da5dfeabd5fa21f2c6c5893199d333d2",
"body": "The reuse A/B measured memory's value at ~zero when the fact is in code and\ntransformative when not; the 367-packet store audit confirmed it in usage\n(reference dumps 0.00 uses/packet, code explanations 0.12, vs ops/rationale\ncarrying all demand). Admission now:\n- BOOSTS non-derivable knowledge (got\n[…]\n gate exists to catch).\n\n4 new tests (restatement penalized + not auto-approved; rationale untouched;\nboost fires). Suite: 1467/1467 aggregate.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: derivability-aware capture — store what code cannot say (T2)",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-21T17:03:34Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "03538edf37514a2681c6249a1f8f3ea74d15940b",
"body": "Audited the production 367-packet store: 71.4% is non-derivable high-value\n(decisions+rationale 39%, gotchas 25%, ops recipes 7%); usage ranks ops/verify\nrecipes highest (0.96-1.43 uses/packet) while reference dumps measure 0.00 and\ncode explanations 0.12 — empirical confirmation that derivable-from\n[…]\nefines the three personas, the question->metric->source map for each, the\nhonest alternatives comparison, and the four metric gaps T3-T5 close.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "docs: personas + team metrics, grounded in a real-store audit (T1)",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-21T16:54:35Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "dda51d026026656e51f0f9149073ce5041ee236f",
"body": "…, v4.0.0 packaged",
"is_bot": false,
"headline": "docs: finalize program checkpoint — all phases + workstreams complete…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-21T16:33:28Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "14b8a8a96456f3ac3b61107758e20325c4ef818c",
"body": "…d (W5)\n\nVersion 3.3.0 -> 4.0.0 (matching the shipped v4 surface + migration docs).\nCHANGELOG entry covers the full program with its measured numbers. Verified\nat release: suite 1463/1463 aggregate, npm pack clean (693 kB, 171 files).\nPublishing to npm requires the maintainer's auth (npm publish from mcp/) —\ndeliberately not performed by the agent.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "release: v4.0.0 — collaborative repository memory, measured end-to-en…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-21T16:33:08Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "0c27cd13aa29c7ee3ba76ce7951b15bbc8cfabda",
"body": "…red proofs (W4)\n\nOne document for the invented framework: the evidence->episodes->claims->\ntrust-gated-injection->tenant-workspace model, the six pain points it was\nbuilt to kill, and the re-runnable proof behind every claim (provider\nbindings, ~93% history digestion, injection false-rate 0, dedup,\n[…]\nn;\nunproven external-world items explicitly not claimed. The v0 git-native\ndesign notes are preserved under docs/history/ with a heritage note.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "docs: the collaborative-memory framework — invariants mapped to measu…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-21T16:30:57Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "ebd4be55d937e8e490c09c73892c1037d0efe4ab",
"body": "…iew (W3)\n\nCapture-time dedup was Jaccard-on-token-sets only: a reworded near-duplicate\nthat keeps its core vocabulary but pads different filler dilutes set overlap\nbelow the 0.58 threshold and lands as a 'new' packet, splitting recall mass.\nThe dedup scorer now takes max(jaccard, tf-cosine) — prove\n[…]\nxisting reference-recall test, which stays green\n— below the floor the set view alone decides, exactly as before).\n\nSuite: 1463/1463 aggregate.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: catch reworded near-duplicates with a guarded TF-cosine dedup v…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-21T16:28:54Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "a21f61bada753273543ca298331343d1c437abcc",
"body": "…rpus-normalized decision (W3)",
"is_bot": false,
"headline": "memory: supersede injection-floor negative result with the shipped co…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-21T16:24:17Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8b80f3cead5a8946f1cacb7f79f8f5fc0e6fc195",
"body": "…first-class outcome (W3)\n\nThe 'pong problem' measured 2026-07-16: composeInjection injected whatever\nrecall returned, so content-free prompts attached 4 lexical accidents on a\n325-packet store, while genuine small-store matches scored BELOW the big\nstore's junk band — score sums are not corpus-norm\n[…]\ne decision shapes; the\n17 proxy-mechanics fixtures pass through the real gate — their direct-match\nseeds inject on evidence, not on eagerness).\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: corpus-normalized injection decision — inject nothing is now a …",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-21T16:23:44Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "1417d006ba5192e61407055b65822cc2723ebd04",
"body": "…~93%)",
"is_bot": false,
"headline": "memory: capture W1+W2 (provider-neutral pipeline + history digestion …",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-21T16:06:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f09754b7d32dab0b9d44c12653f547e0f705bff9",
"body": "Single-body compression honestly nets ~0% on real traffic (measured in this\nbenchmark since Phase D). The real context-window waste is HISTORY: old\ntool_results re-sent verbatim on every turn. This adds deterministic history\ndigestion to the transform pipeline: tool payloads OLDER than the live zone\n[…]\nR-NEUTRAL: Anthropic tool_result blocks + OpenAI role:tool strings\n (Gemini text parts flow through the W1 view).\n\nSuite: 1452/1452 aggregate.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: reversible history digestion — the measured savings (W2)",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-21T16:05:48Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "5848f0f843fc4eafb764b50a94f95947fb6d49bf",
"body": "…W1 — all agents)\n\nThe Phase D transform pipeline (assist injection + reversible lossy compression,\nbyte-preserving on failure) was wired only to Anthropic. This registers OpenAI\nand Gemini pipeline adapters so every proxy-fronted agent gets the same value:\n\n- providers/openai.ts: POST /v1/chat/comp\n[…]\n\n The old 'Phase D is Anthropic-only' registry test updated to the new\n contract (unknown providers still null).\n\nSuite: 1444/1444 aggregate.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "feat: bind OpenAI and Gemini to the reversible compression pipeline (…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-21T15:58:57Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "7bdc3b87bba2ec4a8e07dca02a6fea8b59ffa8ac",
"body": "… honest commercial NO-GO)\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "docs: checkpoint Phase E complete (11 tasks, 1423/1423, GA gate pass,…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-21T15:54:13Z",
"body_truncated": false,
"is_coding_agent": true
},
{
"oid": "06429a8b239f17c1524b321dafd5d729815dff83",
"body": "…ssert\n\nThe Phase E/GA gate's cross-tenant-write sub-check and self_approvals counter\ntested HTTP status === 200, but a successful team review write returns 202\n(review.ts reviewClaim, and the gate's own positive-control assert). So neither\ncounter could ever be incremented by an actual cross-tenant\n[…]\ne fails 202!==403.\n\nreview.ts unchanged; test-only hardening. Backend dist 1375/1375, deploy 36/36,\ndogfood 12/12 green vs embedded PostgreSQL.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "test: harden Phase E gate — real 202 success + backing cross-tenant a…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-21T15:46:35Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "ac0a4954114f5e45c06185df66e8842694baad84",
"body": "Add the real end-to-end Phase E/GA technical gate and the honest GA decision\nreport.\n\n- mcp/vnext/phase-e-gate.test.ts: one end-to-end run against a real embedded\n PostgreSQL — two workspaces, three users, two local replicas, a GitHub\n fixture, a billing fixture, a restricted repository — assertin\n[…]\ne), ci.yml (hard technical gate +\n informational GA report) wired in.\n\nBackend: dist 1375/1375, deploy 36/36, dogfood 12/12. Frontend 105/105.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>",
"is_bot": false,
"headline": "test: enforce Kage vNext commercial readiness gate (Phase E Task 11)",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-21T15:34:27Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "a7f64efd437a2be60bf4b99392385f06f199842c",
"body": "…everify cli.ts packets",
"is_bot": false,
"headline": "memory: supersede core=12 MCP-surface packet after Task 10 cutover; r…",
"author_name": "Kushal Jain",
"author_login": "Kage18",
"committed_at": "2026-07-21T15:19:54Z",
"body_truncated": false,
"is_coding_agent": false
}
],
"releases_count": 11,
"commits_last_year": 1136,
"latest_release_at": "2026-06-22T12:20:15Z",
"latest_release_tag": "v2.5.7",
"releases_from_tags": false,
"days_since_last_push": 7,
"active_weeks_last_year": 17,
"days_since_latest_release": 43,
"mean_days_between_releases": 5.7
},
"artifacts": {
"collected": true,
"structure": [
"tree.compose",
"tree.dockerfile",
"tree.migrations"
],
"declarations": [
{
"name": "@kage-core/kage-graph-mcp",
"path": "mcp/package.json",
"tokens": [
"npm.bin",
"npm.entry"
],
"ecosystem": "npm"
}
]
},
"community": {
"has_readme": true,
"has_license": true,
"readme_badges": {
"hosts": [
"shields.io"
],
"total": 5,
"header": 5,
"collected": true,
"has_inspect_badge": false
},
"has_description": true,
"has_contributing": true,
"health_percentage": 75,
"has_issue_template": false,
"has_code_of_conduct": true,
"has_pull_request_template": true
},
"ecosystem": {
"packages": [
{
"name": "@kage-core/kage-graph-mcp",
"exists": true,
"license": "GPL-3.0-only",
"keywords": [
"mcp",
"kage",
"memory",
"knowledge-graph",
"codex",
"claude",
"ai-agents",
"code-graph",
"okf",
"agent-memory"
],
"ecosystem": "npm",
"categories": [],
"matches_repo": true,
"registry_url": "https://www.npmjs.com/package/@kage-core/kage-graph-mcp",
"declared_type": null,
"is_deprecated": false,
"latest_version": "4.0.6",
"repository_url": "https://github.com/kage-core/Kage",
"versions_count": 79,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": 1,
"monthly_downloads": 2407,
"first_published_at": "2026-04-18T07:38:50.602000Z",
"latest_published_at": "2026-07-25T05:35:04.580000Z",
"latest_version_yanked": null,
"days_since_latest_publish": 11
}
]
},
"popularity": {
"forks": 1,
"stars": 32,
"watchers": 0,
"fork_history": {
"days": [
{
"date": "2026-05-03",
"count": 1
}
],
"complete": true,
"collected": 1,
"total_forks": 1
},
"star_history": null,
"open_issues_and_prs": 8
},
"ai_readiness": {
"has_nix": false,
"example_dirs": [],
"has_llms_txt": false,
"has_dockerfile": true,
"has_mcp_signal": true,
"bootstrap_files": [
"benchmark/Makefile"
],
"api_schema_files": [],
"has_devcontainer": false,
"typecheck_configs": [
"mcp/tsconfig.json",
"platform/web/tsconfig.json"
],
"toolchain_manifests": [],
"largest_source_bytes": 1034526,
"source_files_sampled": 386,
"oversized_source_files": 8,
"agent_instruction_files": [
"AGENTS.md",
"CLAUDE.md"
],
"agent_instruction_max_bytes": 4797
},
"dependencies": {
"manifests": [
"benchmark/requirements.txt",
"mcp/package.json"
],
"advisories": {
"error": null,
"scope": "published_package",
"source": "osv",
"findings": [
{
"name": "hono",
"direct": false,
"version": "4.12.33",
"severity": "moderate",
"ecosystem": "npm",
"cvss_score": 5.3,
"advisory_ids": [
"GHSA-8j4g-w8fx-2239"
],
"fixed_version": "4.12.34",
"advisory_count": 1,
"oldest_advisory_days": 1
}
],
"collected": true,
"malicious": [],
"truncated": false,
"by_severity": {
"moderate": 1
},
"advisory_count": 1,
"affected_count": 1,
"assessed_count": 114,
"malicious_count": 0,
"assessed_package": "npm:@kage-core/kage-graph-mcp@4.0.6",
"unassessed_count": 0,
"direct_affected_count": 0
},
"ecosystems": [
"npm",
"pypi"
],
"dependencies": [
{
"name": "@modelcontextprotocol/sdk",
"manifest": "mcp/package.json",
"ecosystem": "npm",
"version_constraint": "^1.10.2"
},
{
"name": "jose",
"manifest": "mcp/package.json",
"ecosystem": "npm",
"version_constraint": "^6.2.3"
},
{
"name": "pg",
"manifest": "mcp/package.json",
"ecosystem": "npm",
"version_constraint": "^8.22.0"
},
{
"name": "stripe",
"manifest": "mcp/package.json",
"ecosystem": "npm",
"version_constraint": "^22.3.2"
},
{
"name": "three",
"manifest": "mcp/package.json",
"ecosystem": "npm",
"version_constraint": "^0.184.0"
},
{
"name": "tree-sitter-wasms",
"manifest": "mcp/package.json",
"ecosystem": "npm",
"version_constraint": "^0.1.13"
},
{
"name": "typescript",
"manifest": "mcp/package.json",
"ecosystem": "npm",
"version_constraint": "^5.0.0"
},
{
"name": "web-tree-sitter",
"manifest": "mcp/package.json",
"ecosystem": "npm",
"version_constraint": "^0.24.7"
}
],
"all_dependencies": {
"error": "GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository",
"source": null,
"packages": [],
"collected": false,
"truncated": false,
"total_count": null,
"direct_count": null,
"indirect_count": null
}
},
"maintainership": {
"issues": {
"open_prs": 2,
"merged_prs": 92,
"open_issues": 6,
"closed_ratio": 0,
"closed_issues": 0,
"closed_unmerged_prs": 3
},
"bus_factor": 1,
"bot_contributors": 0,
"top_contributors": [
{
"type": "User",
"login": "Kage18",
"commits": 874,
"avatar_url": "https://avatars.githubusercontent.com/u/39442065?v=4"
},
{
"type": "User",
"login": "Kage-Bot",
"commits": 262,
"avatar_url": "https://avatars.githubusercontent.com/u/23263770?v=4"
}
],
"contributors_sampled": 2,
"top_contributor_share": 0.769
},
"quality_signals": {
"has_ci": true,
"has_tests": true,
"ci_workflows": [
"ci.yml",
"claude.yml",
"kage-benchmark.yml",
"kage-pr.yml",
"kage-sync.yml",
"pages.yml",
"release.yml"
],
"has_docs_dir": true,
"linter_configs": [],
"has_editorconfig": false,
"has_linter_config": false,
"has_precommit_config": false
},
"security_signals": {
"lockfiles": [
"package-lock.json"
],
"scorecard": {
"checks": [
{
"name": "Binary-Artifacts",
"score": 10,
"reason": "no binaries found in the repo",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#binary-artifacts"
},
{
"name": "Branch-Protection",
"score": 0,
"reason": "branch protection not enabled on development/release branches",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#branch-protection"
},
{
"name": "CI-Tests",
"score": 10,
"reason": "1 out of 1 merged PRs checked by a CI test -- score normalized to 10",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#ci-tests"
},
{
"name": "CII-Best-Practices",
"score": 0,
"reason": "no effort to earn an OpenSSF best practices badge detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#cii-best-practices"
},
{
"name": "Code-Review",
"score": 0,
"reason": "Found 0/1 approved changesets -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#code-review"
},
{
"name": "Contributors",
"score": 3,
"reason": "project has 1 contributing companies or organizations -- score normalized to 3",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#contributors"
},
{
"name": "Dangerous-Workflow",
"score": 10,
"reason": "no dangerous workflow patterns detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dangerous-workflow"
},
{
"name": "Dependency-Update-Tool",
"score": 0,
"reason": "no update tool detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dependency-update-tool"
},
{
"name": "Fuzzing",
"score": 0,
"reason": "project is not fuzzed",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#fuzzing"
},
{
"name": "License",
"score": 10,
"reason": "license file detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#license"
},
{
"name": "Maintained",
"score": 10,
"reason": "30 commit(s) and 6 issue activity found in the last 90 days -- score normalized to 10",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#maintained"
},
{
"name": "Packaging",
"score": null,
"reason": "packaging workflow not detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#packaging"
},
{
"name": "Pinned-Dependencies",
"score": 5,
"reason": "dependency not pinned by hash detected -- score normalized to 5",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#pinned-dependencies"
},
{
"name": "SAST",
"score": 0,
"reason": "SAST tool is not run on all commits -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#sast"
},
{
"name": "Security-Policy",
"score": 0,
"reason": "security policy file not detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#security-policy"
},
{
"name": "Signed-Releases",
"score": null,
"reason": "no releases found",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#signed-releases"
},
{
"name": "Token-Permissions",
"score": 0,
"reason": "detected GitHub workflow tokens with excessive permissions",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#token-permissions"
},
{
"name": "Vulnerabilities",
"score": 0,
"reason": "36 existing vulnerabilities detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#vulnerabilities"
}
],
"commit": "d22cad56b28a26bb514ecede4ee0dbd509a46c3f",
"ran_at": "2026-08-05T09:13:47Z",
"aggregate_score": 3.6,
"scorecard_version": "v5.5.0"
},
"has_codeql_workflow": false,
"has_security_policy": false,
"has_dependabot_config": false
},
"contribution_flow": {
"collected": true,
"recent_prs": {
"merged_7d": 0,
"decided_7d": 0,
"merged_30d": 9,
"authors_30d": 1,
"decided_30d": 9,
"sample_size": 60,
"window_days": 30,
"sample_exhausted": false,
"authors_probed_30d": 1,
"newcomer_merged_30d": 0,
"bot_prs_excluded_30d": 0,
"newcomer_authors_30d": 0,
"newcomer_decided_30d": 0
},
"ci_last_run_at": "2026-07-28T15:21:40Z",
"oldest_open_prs": [
{
"number": 8,
"created_at": "2026-05-15T18:33:20Z",
"last_comment_at": "2026-05-15T18:33:54Z",
"last_comment_author": "github-actions"
},
{
"number": 107,
"created_at": "2026-07-28T15:29:03Z",
"last_comment_at": "2026-07-28T20:57:37Z",
"last_comment_author": "github-actions"
}
],
"last_merged_pr_at": "2026-07-28T15:21:34Z",
"ci_last_conclusion": null,
"oldest_open_issues": [
{
"number": 74,
"created_at": "2026-06-12T05:52:17Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 88,
"created_at": "2026-06-15T21:17:42Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 89,
"created_at": "2026-06-15T21:17:44Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 90,
"created_at": "2026-06-15T21:17:46Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 91,
"created_at": "2026-06-15T21:17:48Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 92,
"created_at": "2026-06-15T21:17:49Z",
"last_comment_at": null,
"last_comment_author": null
}
]
}
},
"config": {
"disabled_metrics": [],
"disabled_categories": [],
"disabled_components": {}
},
"source": {
"url": "https://github.com/kage-core/Kage",
"host": "github.com",
"name": "Kage",
"owner": "kage-core"
},
"metrics": {
"overall": {
"key": "overall",
"band": "good",
"name": "Overall health",
"note": "The weighted overall 63 is calibrated to 71 on the published index scale (record calibration 2026-08-02).",
"notes": [
{
"code": "overall_calibration",
"params": {
"raw": 63,
"calibrated": 71,
"calibration": "2026-08-02"
}
}
],
"value": 71,
"inputs": {
"security": 47,
"vitality": 86,
"community": 56,
"governance": 43,
"calibration": "2026-08-02",
"engineering": 77,
"ai_readiness": 74,
"weighted_overall_raw": 63
},
"components": []
},
"categories": [
{
"key": "vitality",
"band": "excellent",
"name": "Vitality",
"value": 86,
"weight": 0.21,
"metrics": [
{
"key": "development_activity",
"band": "good",
"name": "Development activity",
"note": null,
"notes": [],
"value": 76,
"inputs": {
"commits_last_year": 1136,
"human_commit_share": 1,
"days_since_last_push": 7,
"active_weeks_last_year": 17
},
"components": [
{
"key": "push_recency",
"name": "Push recency",
"detail": "last push 7 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "push_recency",
"params": {
"days": 7
}
}
],
"max_points": 36
},
{
"key": "commit_cadence",
"name": "Commit cadence",
"detail": "17/52 weeks with commits",
"points": 11.8,
"status": "partial",
"details": [
{
"code": "commit_cadence_weeks",
"params": {
"weeks": 17
}
}
],
"max_points": 36
},
{
"key": "commit_volume",
"name": "Commit volume",
"detail": "1136 commits in the last year",
"points": 18,
"status": "met",
"details": [
{
"code": "commits_last_year",
"params": {
"count": 1136
}
}
],
"max_points": 18
},
{
"key": "openssf_scorecard_maintained",
"name": "OpenSSF Scorecard: Maintained",
"detail": "30 commit(s) and 6 issue activity found in the last 90 days -- score normalized to 10",
"points": 10,
"status": "met",
"details": [],
"max_points": 10
}
]
},
{
"key": "release_discipline",
"band": "exceptional",
"name": "Release discipline",
"note": "Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Signed-Releases. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"openssf_scorecard_signed_releases"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 100,
"inputs": {
"releases_count": 11,
"latest_release_tag": "v2.5.7",
"releases_from_tags": false,
"days_since_latest_release": 43,
"mean_days_between_releases": 5.7
},
"components": [
{
"key": "ships_releases",
"name": "Ships releases",
"detail": "11 releases published",
"points": 27,
"status": "met",
"details": [
{
"code": "releases_published",
"params": {
"count": 11
}
}
],
"max_points": 27
},
{
"key": "release_recency",
"name": "Release recency",
"detail": "latest release 43 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "release_recency",
"params": {
"days": 43
}
}
],
"max_points": 36
},
{
"key": "release_cadence",
"name": "Release cadence",
"detail": "a release every ~5.7 days",
"points": 27,
"status": "met",
"details": [
{
"code": "release_cadence",
"params": {
"gap": 5.7
}
}
],
"max_points": 27
},
{
"key": "openssf_scorecard_signed_releases",
"name": "OpenSSF Scorecard: Signed-Releases",
"detail": "no releases found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 10
}
]
},
{
"key": "abandonment",
"band": "exceptional",
"name": "Abandonment",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"cap": null,
"state": "maintained",
"guards": [],
"signals": [],
"red_flag": false,
"multiplier_pct": 100,
"declared_reason": null,
"unverified_reason": null,
"unanswered_open_prs": null,
"unanswered_open_issues": null,
"days_since_last_merged_pr": null,
"days_since_last_human_commit": 7,
"days_since_last_human_commit_is_floor": false
},
"components": [
{
"key": "project_is_still_maintained",
"name": "Project is still maintained",
"detail": "last human commit 7 days ago",
"points": 100,
"status": "met",
"details": [
{
"code": "abandonment_maintained",
"params": {
"days": 7
}
}
],
"max_points": 100
}
]
}
],
"description": "Is the project alive — is code being written and are releases shipping?"
},
{
"key": "community",
"band": "moderate",
"name": "Community & Adoption",
"value": 56,
"weight": 0.17,
"metrics": [
{
"key": "popularity",
"band": "at_risk",
"name": "Popularity & adoption",
"note": null,
"notes": [],
"value": 24,
"inputs": {
"forks": 1,
"stars": 32,
"watchers": 0,
"growth_state": "unverified",
"growth_factor_pct": 100,
"growth_unverified_reason": "no_history"
},
"components": [
{
"key": "stars",
"name": "Stars",
"detail": "32 stars",
"points": 24.2,
"status": "partial",
"details": [
{
"code": "stars",
"params": {
"count": 32
}
}
],
"max_points": 60
},
{
"key": "forks",
"name": "Forks",
"detail": "1 forks",
"points": 0,
"status": "missed",
"details": [
{
"code": "forks",
"params": {
"count": 1
}
}
],
"max_points": 25
},
{
"key": "watchers",
"name": "Watchers",
"detail": "0 watchers",
"points": 0,
"status": "missed",
"details": [
{
"code": "watchers",
"params": {
"count": 0
}
}
],
"max_points": 15
}
]
},
{
"key": "community_health",
"band": "excellent",
"name": "Community health",
"note": null,
"notes": [],
"value": 92,
"inputs": {
"has_readme": true,
"has_license": true,
"readme_badges": 5,
"has_contributing": true,
"has_issue_template": false,
"has_code_of_conduct": true,
"readme_badge_services": [
"shields.io"
],
"has_pull_request_template": true
},
"components": [
{
"key": "readme",
"name": "README",
"detail": null,
"points": 22.5,
"status": "met",
"details": [],
"max_points": 22.5
},
{
"key": "license",
"name": "License",
"detail": "recognized license (GPL-3.0)",
"points": 22.5,
"status": "met",
"details": [
{
"code": "license_standard",
"params": {}
},
{
"code": "license_spdx",
"params": {
"spdx": "GPL-3.0"
}
}
],
"max_points": 22.5
},
{
"key": "contributing_guide",
"name": "CONTRIBUTING guide",
"detail": null,
"points": 18,
"status": "met",
"details": [],
"max_points": 18
},
{
"key": "code_of_conduct",
"name": "Code of conduct",
"detail": null,
"points": 13.5,
"status": "met",
"details": [],
"max_points": 13.5
},
{
"key": "issue_template",
"name": "Issue template",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.2
},
{
"key": "pr_template",
"name": "PR template",
"detail": null,
"points": 6.3,
"status": "met",
"details": [],
"max_points": 6.3
}
]
},
{
"key": "ecosystem_adoption",
"band": "moderate",
"name": "Ecosystem adoption (downloads)",
"note": "Excluded from scoring (no data or not applicable): Registry dependents. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"registry_dependents"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 56,
"inputs": {
"packages": [
"@kage-core/kage-graph-mcp"
],
"dependents": null,
"ecosystems": "npm",
"total_downloads": null,
"monthly_downloads": 2407
},
"components": [
{
"key": "monthly_downloads",
"name": "Monthly downloads",
"detail": "2,407 downloads/month across npm",
"points": 45.1,
"status": "partial",
"details": [
{
"code": "downloads_monthly",
"params": {
"count": 2407,
"ecosystems": "npm"
}
}
],
"max_points": 80
},
{
"key": "registry_dependents",
"name": "Registry dependents",
"detail": "not reported by this ecosystem",
"points": 0,
"status": "excluded",
"details": [
{
"code": "not_reported_by_this_ecosystem",
"params": {}
}
],
"max_points": 20
}
]
}
],
"description": "Does the project have users, downloads, attention, and a welcoming setup for contributors?"
},
{
"key": "governance",
"band": "weak",
"name": "Sustainability & Governance",
"value": 43,
"weight": 0.23,
"metrics": [
{
"key": "maintainer_resilience",
"band": "at_risk",
"name": "Maintainer resilience (bus factor)",
"note": null,
"notes": [],
"value": 20,
"inputs": {
"bus_factor": 1,
"contributors_sampled": 2,
"top_contributor_share": 0.769
},
"components": [
{
"key": "bus_factor",
"name": "Bus factor",
"detail": "1 contributor(s) cover half of all commits",
"points": 9,
"status": "partial",
"details": [
{
"code": "bus_factor",
"params": {
"count": 1
}
}
],
"max_points": 54
},
{
"key": "commit_distribution",
"name": "Commit distribution",
"detail": "top contributor authored 77% of commits",
"points": 5.2,
"status": "partial",
"details": [
{
"code": "top_contributor_share",
"params": {
"share": 77
}
}
],
"max_points": 22.5
},
{
"key": "contributor_breadth",
"name": "Contributor breadth",
"detail": "2 contributors",
"points": 2.7,
"status": "partial",
"details": [
{
"code": "contributors_sampled",
"params": {
"count": 2
}
}
],
"max_points": 13.5
},
{
"key": "openssf_scorecard_contributors",
"name": "OpenSSF Scorecard: Contributors",
"detail": "project has 1 contributing companies or organizations -- score normalized to 3",
"points": 3,
"status": "partial",
"details": [],
"max_points": 10
}
]
},
{
"key": "responsiveness",
"band": "at_risk",
"name": "Issue & PR responsiveness",
"note": "Excluded from scoring (no data or not applicable): Newcomer PR acceptance. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"newcomer_pr_acceptance"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 33,
"inputs": {
"merged_prs": 92,
"open_issues": 6,
"closed_issues": 0,
"prs_merged_7d": 0,
"prs_decided_7d": 0,
"prs_merged_30d": 9,
"prs_decided_30d": 9,
"issue_closed_ratio": 0,
"closed_unmerged_prs": 3,
"first_time_authors_30d": 0,
"first_time_prs_merged_30d": 0,
"first_time_prs_decided_30d": 0
},
"components": [
{
"key": "issue_resolution",
"name": "Issue resolution",
"detail": "0% of issues closed",
"points": 0,
"status": "missed",
"details": [
{
"code": "issues_closed_share",
"params": {
"share": 0
}
}
],
"max_points": 42
},
{
"key": "pr_acceptance",
"name": "PR acceptance",
"detail": "92/95 decided PRs merged",
"points": 29.1,
"status": "partial",
"details": [
{
"code": "decided_prs_merged",
"params": {
"merged": 92,
"decided": 95
}
}
],
"max_points": 30
},
{
"key": "newcomer_pr_acceptance",
"name": "Newcomer PR acceptance",
"detail": "no first-time contributor's PR decided in 30d",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_newcomer_prs",
"params": {
"days": 30
}
}
],
"max_points": 13
},
{
"key": "openssf_scorecard_code_review",
"name": "OpenSSF Scorecard: Code-Review",
"detail": "Found 0/1 approved changesets -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 15
}
]
},
{
"key": "stewardship",
"band": "at_risk",
"name": "Ownership & stewardship",
"note": null,
"notes": [],
"value": 34,
"inputs": {
"followers": 0,
"owner_type": "Organization",
"is_verified": null,
"owner_login": "kage-core",
"public_repos": 2,
"account_age_days": 114
},
"components": [
{
"key": "ownership_backing",
"name": "Ownership backing",
"detail": "organization-owned",
"points": 30,
"status": "met",
"details": [
{
"code": "owner_organization",
"params": {}
}
],
"max_points": 30
},
{
"key": "verified_domain",
"name": "Verified domain",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 20
},
{
"key": "owner_reach",
"name": "Owner reach",
"detail": "0 followers of kage-core",
"points": 0,
"status": "missed",
"details": [
{
"code": "owner_followers",
"params": {
"count": 0,
"login": "kage-core"
}
}
],
"max_points": 25
},
{
"key": "track_record",
"name": "Track record",
"detail": "2 public repos, account ~0 yr old",
"points": 4.1,
"status": "partial",
"details": [
{
"code": "public_repos",
"params": {
"count": 2
}
},
{
"code": "account_age_years",
"params": {
"years": 0
}
}
],
"max_points": 25
}
]
},
{
"key": "package_maintenance",
"band": "exceptional",
"name": "Package maintenance",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"packages": [
"@kage-core/kage-graph-mcp"
],
"ecosystems": "npm",
"any_deprecated": false,
"min_days_since_publish": 11
},
"components": [
{
"key": "published_resolvable",
"name": "Published & resolvable",
"detail": "1 package(s) on npm",
"points": 25,
"status": "met",
"details": [
{
"code": "packages_published",
"params": {
"count": 1,
"ecosystems": "npm"
}
}
],
"max_points": 25
},
{
"key": "publish_recency",
"name": "Publish recency",
"detail": "latest publish 11 days ago",
"points": 35,
"status": "met",
"details": [
{
"code": "publish_recency",
"params": {
"days": 11
}
}
],
"max_points": 35
},
{
"key": "version_history",
"name": "Version history",
"detail": "79 published versions",
"points": 20,
"status": "met",
"details": [
{
"code": "published_versions",
"params": {
"count": 79
}
}
],
"max_points": 20
},
{
"key": "not_deprecated",
"name": "Not deprecated",
"detail": "active, not deprecated or yanked",
"points": 20,
"status": "met",
"details": [
{
"code": "package_not_deprecated",
"params": {}
}
],
"max_points": 20
}
]
}
],
"description": "Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?"
},
{
"key": "engineering",
"band": "good",
"name": "Engineering Quality",
"value": 77,
"weight": 0.19,
"metrics": [
{
"key": "engineering_practices",
"band": "good",
"name": "Engineering practices",
"note": null,
"notes": [],
"value": 68,
"inputs": {
"has_ci": true,
"has_tests": true,
"has_editorconfig": false,
"has_linter_config": false,
"has_precommit_config": false
},
"components": [
{
"key": "ci_workflows",
"name": "CI workflows",
"detail": "7 workflow(s)",
"points": 24,
"status": "met",
"details": [
{
"code": "ci_workflows",
"params": {
"count": 7
}
}
],
"max_points": 24
},
{
"key": "tests_present",
"name": "Tests present",
"detail": null,
"points": 24,
"status": "met",
"details": [],
"max_points": 24
},
{
"key": "linter_config",
"name": "Linter config",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 16
},
{
"key": "pre_commit_hooks",
"name": "Pre-commit hooks",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 9.6
},
{
"key": "editorconfig",
"name": ".editorconfig",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 6.4
},
{
"key": "openssf_scorecard_ci_tests",
"name": "OpenSSF Scorecard: CI-Tests",
"detail": "1 out of 1 merged PRs checked by a CI test -- score normalized to 10",
"points": 20,
"status": "met",
"details": [],
"max_points": 20
}
]
},
{
"key": "documentation",
"band": "excellent",
"name": "Documentation",
"note": null,
"notes": [],
"value": 90,
"inputs": {
"topics": [
"agent-memory",
"ai-agents",
"claude-code",
"code-graph",
"codex",
"cursor",
"developer-tools",
"knowledge-graph",
"mcp",
"mcp-server"
],
"has_wiki": false,
"homepage": "https://kage-core.com",
"has_readme": true,
"has_docs_dir": true,
"has_description": true
},
"components": [
{
"key": "readme",
"name": "README",
"detail": null,
"points": 30,
"status": "met",
"details": [],
"max_points": 30
},
{
"key": "documentation_directory",
"name": "Documentation directory",
"detail": null,
"points": 25,
"status": "met",
"details": [],
"max_points": 25
},
{
"key": "documentation_homepage_site",
"name": "Documentation / homepage site",
"detail": "https://kage-core.com",
"points": 15,
"status": "met",
"details": [],
"max_points": 15
},
{
"key": "repository_description",
"name": "Repository description",
"detail": null,
"points": 10,
"status": "met",
"details": [],
"max_points": 10
},
{
"key": "topics",
"name": "Topics",
"detail": "10 topics",
"points": 10,
"status": "met",
"details": [
{
"code": "topics_count",
"params": {
"count": 10
}
}
],
"max_points": 10
},
{
"key": "wiki",
"name": "Wiki",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
}
]
}
],
"description": "Are baseline engineering and documentation practices in place?"
},
{
"key": "security",
"band": "weak",
"name": "Security",
"value": 47,
"weight": 0.16,
"metrics": [
{
"key": "security_posture",
"band": "weak",
"name": "Security posture",
"note": "Excluded from scoring (no data or not applicable): Packaging, Signed-Releases. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"packaging",
"signed_releases"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 36,
"inputs": {
"source": "openssf_scorecard",
"checks_evaluated": 16,
"scorecard_version": "v5.5.0",
"checks_inconclusive": 2,
"scorecard_aggregate": 3.6
},
"components": [
{
"key": "binary_artifacts",
"name": "Binary-Artifacts",
"detail": "no binaries found in the repo",
"points": 7.5,
"status": "met",
"details": [],
"max_points": 7.5
},
{
"key": "branch_protection",
"name": "Branch-Protection",
"detail": "branch protection not enabled on development/release branches",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "ci_tests",
"name": "CI-Tests",
"detail": "1 out of 1 merged PRs checked by a CI test -- score normalized to 10",
"points": 2.5,
"status": "met",
"details": [],
"max_points": 2.5
},
{
"key": "cii_best_practices",
"name": "CII-Best-Practices",
"detail": "no effort to earn an OpenSSF best practices badge detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 2.5
},
{
"key": "code_review",
"name": "Code-Review",
"detail": "Found 0/1 approved changesets -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "contributors",
"name": "Contributors",
"detail": "project has 1 contributing companies or organizations -- score normalized to 3",
"points": 0.8,
"status": "partial",
"details": [],
"max_points": 2.5
},
{
"key": "dangerous_workflow",
"name": "Dangerous-Workflow",
"detail": "no dangerous workflow patterns detected",
"points": 10,
"status": "met",
"details": [],
"max_points": 10
},
{
"key": "dependency_update_tool",
"name": "Dependency-Update-Tool",
"detail": "no update tool detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "fuzzing",
"name": "Fuzzing",
"detail": "project is not fuzzed",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "license",
"name": "License",
"detail": "license file detected",
"points": 2.5,
"status": "met",
"details": [],
"max_points": 2.5
},
{
"key": "maintained",
"name": "Maintained",
"detail": "30 commit(s) and 6 issue activity found in the last 90 days -- score normalized to 10",
"points": 7.5,
"status": "met",
"details": [],
"max_points": 7.5
},
{
"key": "packaging",
"name": "Packaging",
"detail": "packaging workflow not detected",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 5
},
{
"key": "pinned_dependencies",
"name": "Pinned-Dependencies",
"detail": "dependency not pinned by hash detected -- score normalized to 5",
"points": 2.5,
"status": "partial",
"details": [],
"max_points": 5
},
{
"key": "sast",
"name": "SAST",
"detail": "SAST tool is not run on all commits -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "security_policy",
"name": "Security-Policy",
"detail": "security policy file not detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "signed_releases",
"name": "Signed-Releases",
"detail": "no releases found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 7.5
},
{
"key": "token_permissions",
"name": "Token-Permissions",
"detail": "detected GitHub workflow tokens with excessive permissions",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "vulnerabilities",
"name": "Vulnerabilities",
"detail": "36 existing vulnerabilities detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
}
]
},
{
"key": "dependency_advisories",
"band": "excellent",
"name": "Dependency advisories",
"note": "Matched the npm:@kage-core/kage-graph-mcp@4.0.6 runtime dependency closure — what installing the published package pulls in — 114 packages. Reachability is not analyzed.",
"notes": [
{
"code": "advisories_scope_published",
"params": {
"package": "npm:@kage-core/kage-graph-mcp@4.0.6",
"assessed": 114
}
},
{
"code": "advisories_reachability",
"params": {}
}
],
"value": 89,
"inputs": {
"source": "osv",
"advisories": 1,
"affected_packages": 1,
"assessed_packages": 114,
"unassessed_packages": 0,
"affected_by_severity": "moderate 1",
"direct_affected_packages": 0
},
"components": [
{
"key": "direct_dependencies_free_of_known_advisories",
"name": "Direct dependencies free of known advisories",
"detail": "no direct dependency carries a known advisory",
"points": 35,
"status": "met",
"details": [
{
"code": "no_direct_advisories",
"params": {}
}
],
"max_points": 35
},
{
"key": "indirect_dependencies_free_of_known_advisories",
"name": "Indirect dependencies free of known advisories",
"detail": "1 affected: hono 4.12.33 (moderate 5.3)",
"points": 14.4,
"status": "partial",
"details": [
{
"code": "advisories_affected",
"params": {
"count": 1,
"packages": "hono 4.12.33 (moderate 5.3)"
}
}
],
"max_points": 25
},
{
"key": "no_advisories_left_outstanding",
"name": "No advisories left outstanding",
"detail": "no advisory has been public longer than 90 days",
"points": 40,
"status": "met",
"details": [
{
"code": "advisories_none_stale",
"params": {
"days": 90
}
}
],
"max_points": 40
}
]
},
{
"key": "malicious_dependencies",
"band": "exceptional",
"name": "Malicious dependencies",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"source": "osv",
"meaning": "reported as a malicious package by the OpenSSF corpus; the remedy is removal or moving off the compromised name, never an upgrade of the same artifact. Versions the registry has since pulled are listed but not scored",
"packages": [],
"red_flag": false,
"assessed_packages": 114,
"malicious_packages": 0,
"direct_malicious_packages": 0,
"withdrawn_malicious_packages": 0,
"installable_malicious_packages": 0
},
"components": [
{
"key": "no_dependency_reported_as_a_malicious_package",
"name": "No dependency reported as a malicious package",
"detail": "no dependency is reported as a malicious package",
"points": 100,
"status": "met",
"details": [
{
"code": "no_malicious_dependencies",
"params": {}
}
],
"max_points": 100
}
]
}
],
"description": "Are visible security and supply-chain practices strong, with no malicious dependency and no unresolved high-risk jurisdiction exposure?"
},
{
"key": "ai_readiness",
"band": "good",
"name": "AI Readiness",
"value": 74,
"weight": 0.04,
"metrics": [
{
"key": "ai_agent_context",
"band": "excellent",
"name": "Agent context & guidance",
"note": null,
"notes": [],
"value": 85,
"inputs": {
"has_llms_txt": false,
"legible_history_share": 1,
"agent_instruction_files": [
"AGENTS.md",
"CLAUDE.md"
],
"agent_instruction_max_bytes": 4797
},
"components": [
{
"key": "agent_instructions",
"name": "Agent instructions",
"detail": "AGENTS.md, CLAUDE.md",
"points": 45,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "AGENTS.md, CLAUDE.md"
}
}
],
"max_points": 45
},
{
"key": "machine_readable_docs_llms_txt",
"name": "Machine-readable docs (llms.txt)",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 15
},
{
"key": "legible_commit_history",
"name": "Legible commit history",
"detail": "100 of 100 human commits state their intent (structured subject or explanatory body)",
"points": 40,
"status": "met",
"details": [
{
"code": "legible_history",
"params": {
"legible": 100,
"sampled": 100
}
}
],
"max_points": 40
}
]
},
{
"key": "ai_verify_loop",
"band": "good",
"name": "Verify loop (build / test / typecheck)",
"note": null,
"notes": [],
"value": 76,
"inputs": {
"has_nix": false,
"has_tests": true,
"lockfiles": [
"package-lock.json"
],
"has_dockerfile": true,
"typed_language": true,
"bootstrap_files": [
"benchmark/Makefile"
],
"has_devcontainer": false,
"has_linter_config": false,
"typecheck_configs": [
"mcp/tsconfig.json",
"platform/web/tsconfig.json"
],
"agent_commit_share": 0.69,
"toolchain_manifests": [],
"dependency_bot_commit_share": 0
},
"components": [
{
"key": "one_command_bootstrap",
"name": "One-command bootstrap",
"detail": "benchmark/Makefile",
"points": 18,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "benchmark/Makefile"
}
}
],
"max_points": 18
},
{
"key": "automated_tests",
"name": "Automated tests",
"detail": null,
"points": 22,
"status": "met",
"details": [],
"max_points": 22
},
{
"key": "lint_format_config",
"name": "Lint / format config",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 11
},
{
"key": "static_type_checking",
"name": "Static type checking",
"detail": "mcp/tsconfig.json, platform/web/tsconfig.json",
"points": 11,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "mcp/tsconfig.json, platform/web/tsconfig.json"
}
}
],
"max_points": 11
},
{
"key": "reproducible_environment",
"name": "Reproducible environment",
"detail": "Dockerfile, lockfile",
"points": 10,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "Dockerfile, lockfile"
}
}
],
"max_points": 10
},
{
"key": "demonstrated_agent_practice",
"name": "Demonstrated agent practice",
"detail": "69 of the last 100 commits agent-authored or agent-credited",
"points": 10,
"status": "met",
"details": [
{
"code": "agent_authored_commits",
"params": {
"count": 69,
"sampled": 100
}
}
],
"max_points": 10
},
{
"key": "automated_maintenance",
"name": "Automated maintenance",
"detail": "no automated dependency updates observed",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_dependency_automation",
"params": {}
}
],
"max_points": 8
},
{
"key": "openssf_scorecard_pinned_dependencies",
"name": "OpenSSF Scorecard: Pinned-Dependencies",
"detail": "dependency not pinned by hash detected -- score normalized to 5",
"points": 5,
"status": "partial",
"details": [],
"max_points": 10
}
]
},
{
"key": "ai_code_legibility",
"band": "exceptional",
"name": "Code legibility for models",
"note": null,
"notes": [],
"value": 99,
"inputs": {
"primary_language": "TypeScript",
"largest_source_bytes": 1034526,
"source_files_sampled": 386,
"oversized_source_files": 8
},
"components": [
{
"key": "type_checkable_code",
"name": "Type-checkable code",
"detail": "TypeScript (statically typed)",
"points": 45,
"status": "met",
"details": [
{
"code": "statically_typed_language",
"params": {
"language": "TypeScript"
}
}
],
"max_points": 45
},
{
"key": "manageable_file_sizes",
"name": "Manageable file sizes",
"detail": "8/386 source files over 60KB",
"points": 53.9,
"status": "partial",
"details": [
{
"code": "oversized_source_files",
"params": {
"kb": 60,
"sampled": 386,
"oversized": 8
}
}
],
"max_points": 55
}
]
},
{
"key": "ai_interfaces",
"band": "at_risk",
"name": "Machine-readable interfaces",
"note": null,
"notes": [],
"value": 20,
"inputs": {
"example_dirs": [],
"has_mcp_signal": true,
"api_schema_files": []
},
"components": [
{
"key": "api_schema_openapi_graphql_proto",
"name": "API schema (OpenAPI/GraphQL/proto)",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 40
},
{
"key": "mcp_server",
"name": "MCP server",
"detail": null,
"points": 20,
"status": "met",
"details": [],
"max_points": 20
},
{
"key": "runnable_examples",
"name": "Runnable examples",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 40
}
]
}
],
"description": "How well is the repo equipped to be developed and maintained with AI coding agents? Carries a deliberately small weight: agent tooling is a real maintenance signal, but its absence must never gate the top of the scale (calibration saturates at raw 91, so 100/100 remains reachable with AI Readiness at zero)."
}
],
"classification": {
"top": [
"library",
"application"
],
"labels": [
"library",
"mcp-server",
"cli"
],
"scores": {
"cli": 6,
"library": 10.8,
"mcp-server": 9,
"network-service": 3
},
"primary": "library",
"evidence": [
{
"tier": "declared",
"label": "cli",
"source": "npm.bin",
"weight": 6
},
{
"tier": "distribution",
"label": "library",
"source": "registry:npm",
"weight": 6
},
{
"tier": "declared",
"label": "library",
"source": "npm.entry",
"weight": 4.8
},
{
"tier": "dependencies",
"label": "mcp-server",
"source": "dep:@modelcontextprotocol/sdk",
"weight": 4
},
{
"tier": "structure",
"label": "mcp-server",
"source": "mcp_signal",
"weight": 3
},
{
"tier": "structure",
"label": "network-service",
"source": "tree.compose",
"weight": 3
},
{
"tier": "tags",
"label": "mcp-server",
"source": "tag:mcp-server",
"weight": 2
}
],
"artifacts": [
{
"path": "mcp/package.json",
"labels": [
"cli",
"library"
],
"ecosystem": "npm"
}
],
"confidence": "high",
"host_extension": false,
"runs_as_process": true,
"consumed_by_code": true
},
"metrics_version": "2.5.0"
},
"warnings": [
"Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token",
"GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository"
],
"report_type": "repository",
"generated_at": "2026-08-05T09:14:04.042867Z",
"schema_version": "0.31.0",
"badge_url": "https://raw.githubusercontent.com/inspect-software/badges/main/v1/k/kage-core/Kage.svg",
"full_name": "kage-core/Kage",
"license_state": "standard",
"license_spdx": "GPL-3.0"
}