公开记录中等
软件健康报告模式 0.27.0 · 指标 1.13.0 · 2026-07-23 00:34 UTC
evo-hq / evo
turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.
evo-hq/evo 的健康指数为 100 分中的 61 分，处于「中等」区间。 其得分最高的类别是Vitality（80/100），最低的是Security（33/100）。 最近一次更新在 5 天前。 近期的大部分工作由 1 位贡献者完成。
61
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；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 49（有风险）的上限。AI 就绪度不计入总体分。
61
优秀85-100堪称典范；基本满足所有检验标准
良好70-84健康；仅有轻微不足
中等50-69可接受，但存在明显不足；建议进行审查
存在风险30-49存在重大薄弱环节；采用时应保持审慎
危急1-29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。
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 | @evo-hq/evo-agent | 0.8.0 | 8,539 | 65 | 5 天前 | evoclaude-codeoptimizationexperimentsbenchmarks |
| PyPI | evo-hq-agent | 0.8.0 | - | 65 | 5 天前 | — |
| PyPI | evo-hq-cli | 0.8.0 | 2,008 | 64 | 5 天前 | — |
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？
80
开发活跃度
74良好
评分方式
| 36/36 | 推送新近度 — 最近一次推送于 5 天前 |
| 9.7/36 | 提交节奏 — 52 周中有 14 周有提交 |
| 18/18 | 提交量 — 最近一年 458 次提交 |
| 10/10 | OpenSSF Scorecard：Maintained — 30 commit(s) and 24 issue activity found in the last 90 days -- score normalized to 10 |
所用输入
| commits_last_year | 458 |
| human_commit_share | 1 |
| days_since_last_push | 5 |
| active_weeks_last_year | 14 |
发布纪律
90优秀
评分方式
| 27/27 | 有发布版本 — 已发布 59 个发布版本 |
| 36/36 | 发布时效 — 最近一次发布版本于 5 天前 |
| 27/27 | 发布节奏 — 约每 3.2 天发布一次 |
| 0/10 | OpenSSF Scorecard：Signed-Releases — Project has not signed or included provenance with any releases. |
所用输入
| releases_count | 59 |
| latest_release_tag | v0.8.0 |
| releases_from_tags | 否 |
| days_since_latest_release | 5 |
| mean_days_between_releases | 3.2 |
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？
62
流行度与采用
69中等
评分方式
| 50.8/60 | 星标 — 1,348 个星标 |
| 16.7/25 | 复刻 — 101 个复刻 |
| 1.7/15 | 关注者 — 3 位关注者 |
所用输入
| forks | 101 |
| stars | 1,348 |
| watchers | 3 |
| growth_state | unverified |
| growth_factor_pct | 100 |
| growth_unverified_reason | no_history |
社区健康
50中等
评分方式
| 22.5/22.5 | README |
| 22.5/22.5 | 许可证 — 可识别的许可证（Apache-2.0） |
| 0/18 | CONTRIBUTING 指南 |
| 0/13.5 | 行为准则 |
| 0/7.2 | 议题模板 |
| 0/6.3 | PR 模板 |
所用输入
| has_readme | 是 |
| has_license | 是 |
| has_contributing | 否 |
| has_issue_template | 否 |
| has_code_of_conduct | 否 |
| has_pull_request_template | 否 |
生态采用（下载量）
67中等
评分方式
| 53.6/80 | 月度下载量 — npm, pypi 合计每月 10,547 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 | @evo-hq/evo-agent, evo-hq-agent, evo-hq-cli |
| dependents | — |
| ecosystems | npm, pypi |
| total_downloads | — |
| monthly_downloads | 10,547 |
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？
52
维护者韧性（巴士系数）
15危急
评分方式
| 9/54 | 巴士系数 — 1 位贡献者贡献了半数提交 |
| 0.2/22.5 | 提交分布 — 头号贡献者编写了 99% 的提交 |
| 5.4/13.5 | 贡献者广度 — 4 位贡献者 |
| 0/10 | OpenSSF Scorecard：Contributors — project has 0 contributing companies or organizations -- score normalized to 0 |
所用输入
| bus_factor | 1 |
| contributors_sampled | 4 |
| top_contributor_share | 0.989 |
议题与 PR 响应能力
65中等
评分方式
| 32.7/46.8 | 议题解决 — 70% 的议题已关闭 |
| 31.9/38.3 | PR 接受 — 已裁定的 PR 中 40/48 已合并 |
| 0/15 | OpenSSF Scorecard：Code-Review — Found 0/10 approved changesets -- score normalized to 0 |
所用输入
| merged_prs | 40 |
| open_issues | 9 |
| closed_issues | 21 |
| issue_closed_ratio | 0.7 |
| closed_unmerged_prs | 8 |
所有权与托管责任
46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 |
| 9/25 | 所有者影响力 — evo-hq 有 17 位关注者 |
| 6.7/25 | 既往记录 — 6 个公开仓库，账户约 0 年 |
所用输入
| followers | 17 |
| owner_type | Organization |
| is_verified | — |
| owner_login | evo-hq |
| public_repos | 6 |
| account_age_days | 106 |
软件包维护
100优秀
评分方式
| 25/25 | 已发布且可解析 — npm, pypi 上有 3 个软件包 |
| 35/35 | 发布时效 — 最近一次发布于 5 天前 |
| 20/20 | 版本历史 — 65 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 | @evo-hq/evo-agent, evo-hq-agent, evo-hq-cli |
| ecosystems | npm, pypi |
| any_deprecated | 否 |
| min_days_since_publish | 5 |
工程质量
基础的工程与文档实践是否到位？
71
工程实践
68中等
评分方式
| 24/24 | CI 工作流 — 2 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 — 6 out of 6 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
75良好
评分方式
| 30/30 | README |
| 0/25 | 文档目录 |
| 15/15 | 文档 / 主页站点 — https://evo-hq.com |
| 10/10 | 仓库描述 |
| 10/10 | 主题标签 — 8 个主题标签 |
| 10/10 | Wiki |
所用输入
| topics | agent-skills, autonomous-agents, autoresearch, claude-code, code-optimization, codex, evolutionary-algorithms, llm-agents |
| has_wiki | 是 |
| homepage | https://evo-hq.com |
| has_readme | 是 |
| has_docs_dir | 否 |
| 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？
33
安全态势
33存在风险
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 — 6 out of 6 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 0/10 approved changesets -- score normalized to 0 |
| 0/2.5 | Contributors — project has 0 contributing companies or organizations -- score normalized to 0 |
| 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 24 issue activity found in the last 90 days -- score normalized to 10 |
| 5/5 | Packaging — packaging workflow detected |
| 0/5 | Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0 |
| 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 — Project has not signed or included provenance with any releases. |
| 0/7.5 | Token-Permissions — detected GitHub workflow tokens with excessive permissions |
| 0/7.5 | Vulnerabilities — 32 existing vulnerabilities detected |
所用输入
| source | openssf_scorecard |
| checks_evaluated | 18 |
| scorecard_version | v5.5.0 |
| checks_inconclusive | 0 |
| scorecard_aggregate | 3.3 |
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？这是一枚独立的实验性徽章——权重为 0.0，因此单独呈现，不影响总体健康评分。
46
AI 代理上下文与指引
40存在风险
评分方式
| 0/45 | 代理指令 — 没有 CLAUDE.md / AGENTS.md / 编辑器规则 |
| 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 89 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 | 0.89 |
| agent_instruction_files | — |
| agent_instruction_max_bytes | — |
验证循环（构建 / 测试 / 类型检查）
47存在风险
评分方式
| 12.6/18 | 一条命令的引导启动 — plugins/evo/bin/evo-hook-drain-rs/Cargo.toml（工具链约定，无任务运行器） |
| 22/22 | 自动化测试 |
| 0/11 | Lint / 格式化配置 |
| 0/11 | 静态类型检查 |
| 10/10 | 可复现环境 — lockfile |
| 2/10 | 已体现的代理实践 — 最近 100 次提交中有 1 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 |
| 0/10 | OpenSSF Scorecard：Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0 |
所用输入
| has_nix | 否 |
| has_tests | 是 |
| lockfiles | Cargo.lock, uv.lock |
| has_dockerfile | 否 |
| typed_language | 否 |
| bootstrap_files | — |
| has_devcontainer | 否 |
| has_linter_config | 否 |
| typecheck_configs | — |
| agent_commit_share | 0.01 |
| toolchain_manifests | plugins/evo/bin/evo-hook-drain-rs/Cargo.toml |
| dependency_bot_commit_share | 0 |
面向模型的代码可读性
53中等
评分方式
| 0/45 | 可类型检查的代码 — Python，未配置类型检查 |
| 53.2/55 | 可控的文件大小 — 采样的 187 个源文件中有 6 个超过 60KB |
所用输入
| primary_language | Python |
| largest_source_bytes | 296,301 |
| source_files_sampled | 187 |
| oversized_source_files | 6 |
关键数据
1,348GitHub 星标
4贡献者
458最近 12 个月提交数
5距最近推送天数
59发布版本数
1巴士系数（bus factor）
9开放议题
—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
- deps.dev does not index npm:@evo-hq/evo-agent@0.8.0; advisories assessed against the repository dependency graph instead
更多细节
Star 与 Fork 历史 0 ★ / 101 ⇿
0Star
101Fork
59发布
每颗 star 和每个 fork 的添加时间，来自 GitHub 并按天汇总。累计增长位于其构成来源——每日新增——的正上方，二者可相互对照：稳定的自然增长与短暂的突增形态截然不同。当这一差别可被衡量时，它会作为增长真实性予以报告。
主版本 0次版本 6修订 13
OpenSSF Scorecard 3.3 / 10
3.3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 | 6 out of 6 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 0/10 approved changesets -- score normalized to 0 |
| 0 | Contributors | project has 0 contributing companies or organizations -- score normalized to 0 |
| 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 24 issue activity found in the last 90 days -- score normalized to 10 |
| 10 | Packaging | packaging workflow detected |
| 0 | Pinned-Dependencies | dependency not pinned by hash detected -- score normalized to 0 |
| 0 | SAST | SAST tool is not run on all commits -- score normalized to 0 |
| 0 | Security-Policy | security policy file not detected |
| 0 | Signed-Releases | Project has not signed or included provenance with any releases. |
| 0 | Token-Permissions | detected GitHub workflow tokens with excessive permissions |
| 0 | Vulnerabilities | 32 existing vulnerabilities detected |
直接依赖 4
| 注册表 | 软件包 | 版本约束 | 清单文件 |
|---|---|---|---|
| PyPI | flask | >=3.0.0 | plugins/evo/pyproject.toml |
| PyPI | portalocker | >=2.8.0 | plugins/evo/pyproject.toml |
| PyPI | pyyaml | >=6.0.0 | plugins/evo/pyproject.toml |
| PyPI | requests | >=2.31.0 | plugins/evo/pyproject.toml |
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
原始 JSON 报告 机器可读
{
"data": {
"repo": {
"topics": [
"agent-skills",
"autonomous-agents",
"autoresearch",
"claude-code",
"code-optimization",
"codex",
"evolutionary-algorithms",
"llm-agents"
],
"is_fork": false,
"size_kb": 17111,
"has_wiki": true,
"homepage": "https://evo-hq.com",
"languages": {
"CSS": 82833,
"HTML": 9844,
"Rust": 32410,
"Shell": 20708,
"Python": 2296064,
"JavaScript": 465566,
"TypeScript": 79486
},
"pushed_at": "2026-07-17T16:52:59Z",
"created_at": "2026-04-05T16:04:50Z",
"owner_type": "Organization",
"updated_at": "2026-07-22T00:29:40Z",
"description": "turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.",
"is_archived": false,
"is_disabled": false,
"license_spdx": "Apache-2.0",
"default_branch": "main",
"license_spdx_raw": "Apache-2.0",
"primary_language": "Python",
"significant_languages": [
"Python",
"JavaScript"
]
},
"owner": {
"blog": "https://evo-hq.com/",
"name": "EVO",
"type": "Organization",
"login": "evo-hq",
"company": null,
"location": null,
"followers": 17,
"avatar_url": "https://avatars.githubusercontent.com/u/274232282?v=4",
"created_at": "2026-04-07T11:14:12Z",
"is_verified": null,
"public_repos": 6,
"account_age_days": 106
},
"license": {
"state": "standard",
"spdx_id": "Apache-2.0",
"raw_spdx": "Apache-2.0",
"file_present": true,
"scorecard_found": true,
"profile_has_license": true
},
"activity": {
"releases": [
{
"tag": "v0.8.0",
"kind": "minor",
"published_at": "2026-07-17T16:57:14Z"
},
{
"tag": "v0.7.1-alpha.1",
"kind": "prerelease",
"published_at": "2026-07-17T15:03:57Z"
},
{
"tag": "v0.7.0",
"kind": "minor",
"published_at": "2026-07-01T15:04:22Z"
},
{
"tag": "v0.7.0-alpha.3",
"kind": "prerelease",
"published_at": "2026-07-01T13:21:55Z"
},
{
"tag": "v0.7.0-alpha.2",
"kind": "prerelease",
"published_at": "2026-07-01T10:34:08Z"
},
{
"tag": "v0.7.0-alpha.1",
"kind": "prerelease",
"published_at": "2026-07-01T09:26:47Z"
},
{
"tag": "v0.6.4-alpha.1",
"kind": "prerelease",
"published_at": "2026-06-30T05:59:30Z"
},
{
"tag": "v0.6.2",
"kind": "patch",
"published_at": "2026-06-19T12:36:04Z"
},
{
"tag": "v0.6.1",
"kind": "patch",
"published_at": "2026-06-18T20:02:06Z"
},
{
"tag": "v0.6.1-alpha.2",
"kind": "prerelease",
"published_at": "2026-06-18T19:12:03Z"
},
{
"tag": "v0.6.1-alpha.1",
"kind": "prerelease",
"published_at": "2026-06-18T19:02:05Z"
},
{
"tag": "v0.6.0",
"kind": "minor",
"published_at": "2026-06-18T18:29:11Z"
},
{
"tag": "v0.6.0-alpha.1",
"kind": "prerelease",
"published_at": "2026-06-17T08:41:03Z"
},
{
"tag": "v0.5.3",
"kind": "patch",
"published_at": "2026-06-14T15:32:40Z"
},
{
"tag": "v0.5.2",
"kind": "patch",
"published_at": "2026-06-11T10:38:43Z"
},
{
"tag": "v0.5.1",
"kind": "patch",
"published_at": "2026-06-11T03:55:24Z"
},
{
"tag": "v0.5.0",
"kind": "minor",
"published_at": "2026-06-06T09:40:22Z"
},
{
"tag": "v0.5.0-alpha.13",
"kind": "prerelease",
"published_at": "2026-06-05T22:10:09Z"
},
{
"tag": "v0.5.0-alpha.12",
"kind": "prerelease",
"published_at": "2026-06-05T14:09:43Z"
},
{
"tag": "v0.5.0-alpha.11",
"kind": "prerelease",
"published_at": "2026-06-04T22:44:47Z"
},
{
"tag": "v0.5.0-alpha.10",
"kind": "prerelease",
"published_at": "2026-06-04T21:42:41Z"
},
{
"tag": "v0.5.0-alpha.9",
"kind": "prerelease",
"published_at": "2026-06-04T21:08:59Z"
},
{
"tag": "v0.5.0-alpha.8",
"kind": "prerelease",
"published_at": "2026-06-04T19:50:44Z"
},
{
"tag": "v0.4.5",
"kind": "patch",
"published_at": "2026-06-04T08:26:57Z"
},
{
"tag": "v0.5.0-alpha.7",
"kind": "prerelease",
"published_at": "2026-06-02T13:24:34Z"
},
{
"tag": "v0.5.0-alpha.6",
"kind": "prerelease",
"published_at": "2026-06-02T12:13:45Z"
},
{
"tag": "v0.5.0-alpha.5",
"kind": "prerelease",
"published_at": "2026-06-01T23:10:12Z"
},
{
"tag": "v0.5.0-alpha.4",
"kind": "prerelease",
"published_at": "2026-06-01T21:25:09Z"
},
{
"tag": "v0.5.0-alpha.3",
"kind": "prerelease",
"published_at": "2026-06-01T21:06:05Z"
},
{
"tag": "v0.4.4",
"kind": "patch",
"published_at": "2026-05-30T08:29:34Z"
},
{
"tag": "v0.4.4-alpha.6",
"kind": "prerelease",
"published_at": "2026-05-30T07:44:38Z"
},
{
"tag": "v0.4.4-alpha.5",
"kind": "prerelease",
"published_at": "2026-05-29T15:22:18Z"
},
{
"tag": "v0.4.4-alpha.3",
"kind": "prerelease",
"published_at": "2026-05-28T17:53:29Z"
},
{
"tag": "v0.4.4-alpha.2",
"kind": "prerelease",
"published_at": "2026-05-28T16:31:51Z"
},
{
"tag": "v0.4.4-alpha.1",
"kind": "prerelease",
"published_at": "2026-05-28T15:36:49Z"
},
{
"tag": "v0.4.3",
"kind": "patch",
"published_at": "2026-05-21T10:18:27Z"
},
{
"tag": "v0.4.3-alpha.1",
"kind": "prerelease",
"published_at": "2026-05-21T09:48:29Z"
},
{
"tag": "v0.4.2",
"kind": "patch",
"published_at": "2026-05-19T14:35:57Z"
},
{
"tag": "v0.4.2-alpha.1",
"kind": "prerelease",
"published_at": "2026-05-19T12:28:03Z"
},
{
"tag": "v0.4.1",
"kind": "patch",
"published_at": "2026-05-18T19:01:22Z"
},
{
"tag": "v0.4.1-alpha.5",
"kind": "prerelease",
"published_at": "2026-05-18T17:58:30Z"
},
{
"tag": "v0.4.1-alpha.4",
"kind": "prerelease",
"published_at": "2026-05-18T17:38:22Z"
},
{
"tag": "v0.4.1-alpha.2",
"kind": "prerelease",
"published_at": "2026-05-18T13:00:11Z"
},
{
"tag": "v0.4.1-alpha.1",
"kind": "prerelease",
"published_at": "2026-05-17T23:44:29Z"
},
{
"tag": "v0.4.0",
"kind": "minor",
"published_at": "2026-05-13T14:29:32Z"
},
{
"tag": "v0.4.0-alpha.11",
"kind": "prerelease",
"published_at": "2026-05-12T01:05:37Z"
},
{
"tag": "v0.4.0-alpha.10",
"kind": "prerelease",
"published_at": "2026-05-12T00:31:03Z"
},
{
"tag": "v0.4.0-alpha.9",
"kind": "prerelease",
"published_at": "2026-05-07T23:31:06Z"
},
{
"tag": "v0.4.0-alpha.8",
"kind": "prerelease",
"published_at": "2026-05-07T22:58:11Z"
},
{
"tag": "v0.4.0-alpha.7",
"kind": "prerelease",
"published_at": "2026-05-07T22:58:03Z"
},
{
"tag": "v0.4.0-alpha.6",
"kind": "prerelease",
"published_at": "2026-05-07T22:58:02Z"
},
{
"tag": "v0.4.0-alpha.5",
"kind": "prerelease",
"published_at": "2026-05-07T22:58:00Z"
},
{
"tag": "v0.4.0-alpha.3",
"kind": "prerelease",
"published_at": "2026-04-29T20:59:33Z"
},
{
"tag": "v0.3.3",
"kind": "patch",
"published_at": "2026-04-28T19:52:47Z"
},
{
"tag": "v0.4.0-alpha.2",
"kind": "prerelease",
"published_at": "2026-04-28T14:07:50Z"
},
{
"tag": "v0.4.0-alpha.1",
"kind": "prerelease",
"published_at": "2026-04-28T11:26:11Z"
},
{
"tag": "v0.3.2",
"kind": "patch",
"published_at": "2026-04-27T03:47:01Z"
},
{
"tag": "v0.3.1",
"kind": "patch",
"published_at": "2026-04-26T16:32:17Z"
},
{
"tag": "v0.3.0",
"kind": "minor",
"published_at": "2026-04-26T09:02:11Z"
}
],
"recent_commits": [
{
"oid": "ab5fbd6c8210ed900157c8907a431bafc74c4215",
"body": "Adds Kimi Code as a supported evo host: install adapter (managed-dir copy plus installed.json registration), plugin manifest, skills and slash-command wiring, and the self-contained drain path for hooks and mid-run directives. Verified end-to-end against kimi-code 0.26.0 — install, SessionStart hook\n[…]\ntion, and directive delivery/ack.\n\nAlso wires the Kimi manifest into the release version tooling and bumps the release to v0.8.0.\n\nSupersedes #85.\n\nCo-authored-by: pierre aubert <pierre@spinorama.org>",
"is_bot": false,
"headline": "Add Kimi Code host support; release v0.8.0 (#86)",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-07-17T16:52:31Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "f5e7e9b9be33f387a598c137309dce99753363fe",
"body": "Add gitdir backend, claude-science host, and sandbox dashboard gate; release 0.7.0",
"is_bot": false,
"headline": "Merge gitdir backend, claude-science host, and dashboard gate (#82)",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-07-01T14:59:19Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "db2adcd4a804cb70f43d39b01f3a56f3cd4fc3f3",
"body": "Path.write_text() translates \\n to \\r\\n on Windows. git's alternates parser\nreads the path literally and keeps the trailing \\r, so it looked for\n'objects\\r' and the shared object store went unlinked (parent commit unfound).\nWrite bytes with a bare LF. Assert no CR in the alternates file.",
"is_bot": false,
"headline": "gitdir: write alternates with a bare LF so it works on Windows",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-07-01T14:43:30Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4105c4d6b49c60f6fd2fc057f4c661cb07cd4e35",
"body": "…reachable\n\nThe Windows CI 'parent commit not found' failure is opaque. Include the\nwritten alternates path, whether the base object store dir resolves, and\ngit's stderr in the error so the root cause is visible.",
"is_bot": false,
"headline": "gitdir: surface alternates path + git stderr when parent commit is un…",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-07-01T14:35:52Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "efe7c9f5670c67345e6bcb5ee5063d2096645d5a",
"body": "- gitdir alternates: write the base object-store path with forward slashes.\n git's alternates parser doesn't resolve Windows backslash paths, so the\n shared object store went unlinked and the parent commit read as missing.\n- find_workspace_root: skip a .evo that is the global evo home ($EVO_HOME /\n ~/.evo). It shares the name but isn't a workspace; on Windows temp dirs live\n under ~, so an ambient ~/.evo was wrongly resolved as the workspace root.",
"is_bot": false,
"headline": "Fix gitdir backend and workspace lookup on Windows",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-07-01T14:24:17Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "832c8041d15db4f69a3d611584784076344f85a0",
"body": null,
"is_bot": false,
"headline": "Release v0.7.0",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-07-01T13:45:33Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "5aa1abb440a8ac5914f144f30ae82c657ee597cb",
"body": null,
"is_bot": false,
"headline": "Release v0.7.0-alpha.3",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-07-01T13:17:17Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e1ff1707f6ce88b2fa613ac6c202142659b83b53",
"body": "init started the dashboard supervisor unconditionally. Relocated gitdir /\nclaude-science workspaces run under a sandbox that forbids TCP socket binds,\nso the supervisor only crash-loops there. Gate the start on the relocate\npath and print a note pointing at `evo status` / `evo tree` instead.",
"is_bot": false,
"headline": "Skip evo's dashboard in relocated (sandbox) workspaces",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-07-01T13:14:50Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1dc5cbe3cf45d73e448a64a7340614caa0349caf",
"body": null,
"is_bot": false,
"headline": "Release v0.7.0-alpha.2",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-07-01T10:15:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3529ffcc0345857dc0ba7f3b3743b52be1eda222",
"body": "Sandboxes (e.g. the Claude Science kernel) block the home directory, so\n~/.evo can't be created and any user-default read/write fails with EPERM.\nglobal_evo_dir() now falls back to <workspace>/.evo/home when ~/.evo isn't\nwritable, so evo works without a manually-set EVO_HOME and delegated child\nkernels resolve a writable home on their own without inheriting env.",
"is_bot": false,
"headline": "Fall back EVO_HOME to a workspace-local home when ~/.evo is unwritable",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-07-01T10:15:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b2bef4b169041770941bf54c6144e727e733c5c4",
"body": null,
"is_bot": false,
"headline": "Release v0.7.0-alpha.1",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-07-01T09:21:55Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1be22cf9acf2f145bfd44fc2f49cb9069739be2c",
"body": "Extends the gitdir backend so evo runs end-to-end where `.git` creation is\nforbidden, not just per-experiment isolation.\n\n- `evo init --backend gitdir` (and any `--host claude-science` workspace)\n relocates the BASE repo off `.git`: it creates `.evo/basegit` via a\n relocated GIT_DIR, commits a bas\n[…]\napplies for relocated workspaces, no-op otherwise), and the\nclaude-science adapter (install/doctor/uninstall). Verified end-to-end via the\nreal CLI: init + new in a non-git dir with zero .git created.",
"is_bot": false,
"headline": "Add gitdir base-repo relocation, claude-science host, and git-env hook",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-07-01T09:21:55Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "566d55de4c19e0c000a643c0c2f8444445a36d2a",
"body": "Some execution sandboxes deny creating any path named .git (files and\ndirectories alike), so the worktree backend's `git worktree add` and even\n`git init` fail with EPERM. The gitdir backend isolates each experiment with a\nrelocated GIT_DIR under <run>/gitdirs/<exp> and a working tree that contains \n[…]\ne and at the parent commit, objects share via alternates rather than\ncopy, the executor commit path makes a real commit, two experiments stay\nisolated, and discard/sweep_orphans reclaim the workspace.",
"is_bot": false,
"headline": "Add gitdir execution backend for sandboxes that forbid .git",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-07-01T08:45:35Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "884031cf87210a12af82ed31d44c2f70969d11aa",
"body": "Alpha patch carrying the PostToolUse hook hang fix (bounded spawnSync\n+ stdin tty-guard so the node launcher fails open instead of spinning\nindefinitely). spawnSync timeout set to 2s.\n\nBumps all version pins via scripts/bump-version.py and syncs npm/.",
"is_bot": false,
"headline": "Release v0.6.4-alpha.1",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-30T05:42:32Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c1e6c2c643e4399b50b492efc4569f0600ba2d26",
"body": "The 0.6.2 migration wrapped every hook command in a `node -e` launcher\nthat calls `spawnSync(helper, {input})` with no timeout. The helper\n(`evo-hook-drain`) hands off to the Python `evo-drain`, which inherits\nthe helper's stdout/stderr (`Stdio::inherit()`). node's `spawnSync` does\nnot return until \n[…]\n the\ninherited stdio and asserts the hook still returns and fails open.\n\nCo-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>\nClaude-Session: https://claude.ai/code/session_01VpudqCLoPU7Y29rAKLw3Eg",
"is_bot": false,
"headline": "Fix PostToolUse hooks hanging/\"running continuously\"",
"author_name": "Claude",
"author_login": "claude",
"committed_at": "2026-06-30T03:41:43Z",
"body_truncated": true,
"is_coding_agent": true
},
{
"oid": "1b9807c57e1da6e3b9ff57e17828c0c88d64cd14",
"body": null,
"is_bot": false,
"headline": "Bump version to 0.6.3",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-19T22:03:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "108cab2b49b31bb1b47684f92f16d9cef66a7bc9",
"body": null,
"is_bot": false,
"headline": "Repair Codex evo config on update (#77)",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-19T22:03:02Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "efd3ed96a91049b940b3a2b970eb7150d1e10f4a",
"body": "Fix Codex hook launch behavior so restored marketplace hooks no longer depend on Claude-only environment variables and fail open in unrelated Codex sessions.",
"is_bot": false,
"headline": "Fix Codex hook launcher for 0.6.2",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-19T12:30:36Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "33d87a4b8d1ad1b96dea2455084f4f0c1f266f7e",
"body": "Ship the Codex hook repair, upgrade handling, and 0.6.1 release bump.",
"is_bot": false,
"headline": "Fix Codex hook paths for 0.6.1",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-18T19:56:58Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f55cf052c52d9d2ec2e2f94f6bd56c6c1feaedf8",
"body": "Merge release/0.6 into main.",
"is_bot": false,
"headline": "Release 0.6.0",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-18T18:16:36Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "78acc3d350f1db1462e34c7a2feecd02f43e7610",
"body": null,
"is_bot": false,
"headline": "fix: align dashboard result accounting",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-18T16:59:50Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "fdfd2b88fd12633473b0a04d660ffd643bf5cace",
"body": null,
"is_bot": false,
"headline": "release: bump evo to 0.6.0",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-18T16:07:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3fc56f90bc3953f86c7badc91cbb8a032dbd9e3a",
"body": null,
"is_bot": false,
"headline": "evo: harden optimize and report flow",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-18T16:06:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e3aab6094204ec1ecdfd55de98116ab026e6b2eb",
"body": null,
"is_bot": false,
"headline": "Add telemetry relationship context",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-17T19:57:57Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "69ad4c8715398299dd14c9f869f4b57778a48f91",
"body": null,
"is_bot": false,
"headline": "Add anonymous telemetry for evo CLI",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-17T08:34:57Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d9fbe64a764408f4addff3005d436fe288b347c5",
"body": null,
"is_bot": false,
"headline": "Add explicit prune validity semantics",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-16T20:59:14Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3a9f488f5303314e901e82536ffc0deb5edd74c1",
"body": "…ange\n\nNew ship skill distills the best-scoring experiment into a minimal clean\ndiff (PR when the repo has a remote, else a merge) and attaches an advisory\nmergeability report covering technique + the FrontierCode quality axes.\nPoint at it from the optimize stop-summary and the discover lifecycle map.",
"is_bot": false,
"headline": "skills: add evo:ship to land the winning experiment as a mergeable ch…",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-16T17:57:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "55e096975268e478815775c576958f9301643eff",
"body": null,
"is_bot": false,
"headline": "docs: add hosted platform CTA",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-16T17:50:19Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "105d2f59420eef47b1d178729441b942efdece95",
"body": null,
"is_bot": false,
"headline": "test: pin prose-default as the optimize driver policy",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-14T15:26:11Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c142b36abd42ccf6699e952080c08408c15d07c4",
"body": null,
"is_bot": false,
"headline": "chore(release): v0.5.3",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-14T15:15:10Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "77148f10400dd1874ed4de316794cdbc45310311",
"body": "Gate failures were recorded on nodes (gate_result, gate_failures) but never\nsurfaced. A node the accuracy gate rejected now shows an amber status dot and a\n\"gate ✗\" badge in the node flow, and an \"Accuracy gate FAILED (...)\" line in the\ndetail drawer, separate from an ordinary regression discard.\n\nT\n[…]\npand opens a collapsed strip, then\nmaximizes it to fill the center column with the timeline hidden. The header-click\ncaret is removed. The size (collapsed, normal, maximized) persists to localStorage.",
"is_bot": false,
"headline": "dashboard: surface gate failures, rework scatter collapse/expand",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-14T15:13:17Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "5302f4be8907159bfc4044dd884e8152814adaf2",
"body": "The optimize skill drove the loop with the dynamic workflow by default on\nClaude Code and treated prose as the fallback. Reverse that. The prose loop is\nthe default driver on every host; the workflow runs only when\ndefault-orchestrator is explicitly 'workflow' and the Workflow tool is present\nthis s\n[…]\neports an unset default_orchestrator\nas 'prose', and drain.py suppresses the prose stop-nudge only when\ndefault_orchestrator == 'workflow'. This is a change to the SKILL text that\nresolves the driver.",
"is_bot": false,
"headline": "optimize: default to the prose loop, make the workflow opt-in",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-14T11:57:57Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "410023257a2c5f8b50be4f6badc5e22bd73d20fd",
"body": "CITATION.cff was left at 0.4.4 by the 0.5.2 release because the bump\nscript did not touch it. Syncs it to 0.5.2, adds a _bump_citation_cff\nstep (version + date-released) to bump-version.py, and registers the\nfile in check_versions.py so drift fails the consistency check.",
"is_bot": false,
"headline": "chore(release): cover CITATION.cff in version bump tooling",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-12T15:48:10Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d7cf3c3b9d50de10d2cfd506740e4fc5f6889cad",
"body": "fix(deps): upgrade urllib3 to 2.7.0 (CVE-2026-44431)",
"is_bot": false,
"headline": "Merge pull request #73 from evo-hq/fix/urllib3-2.7.0",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-12T05:37:44Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3448abb26b107e6d8e5df4f16fd472c74edd7e39",
"body": "Regenerates plugins/evo/uv.lock with uv lock --upgrade-package urllib3.\nAlso syncs the lockfile's stale evo-hq-cli self-version (0.5.1 -> 0.5.2)\nleft behind by the 0.5.2 release bump.",
"is_bot": false,
"headline": "fix(deps): upgrade urllib3 to 2.7.0 (CVE-2026-44431)",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-12T05:34:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "eccfedfead2921ce6112c8fb81faabce8fb89f1e",
"body": "ci: disable the post-release live smoke job",
"is_bot": false,
"headline": "Merge pull request #70 from evo-hq/ci/disable-release-smoke",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-11T10:33:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "cc9f402a5a1bca8b2e874bb1c02e2e47a37d033e",
"body": "release-smoke keeps the publish run alive for up to 30 minutes per\nrelease (v0.5.1's run was cancelled mid-smoke at ~35 min). The job is\nreactive, not gating, so disabling it does not affect publishing.\nCondition preserved in a comment for re-enabling.",
"is_bot": false,
"headline": "ci: disable the post-release live smoke job",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-11T10:33:32Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "df2105385a7741f05ee954ba110e545e0feea5e1",
"body": "release: 0.5.2",
"is_bot": false,
"headline": "Merge pull request #69 from evo-hq/release/0.5.2",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-11T10:30:57Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "55e554873137d137a309b1cab94ccf91974ac008",
"body": null,
"is_bot": false,
"headline": "release: bump to 0.5.2",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-11T10:28:26Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4c29afdfe072c41bd50a2a4d6c7c8daee19155fc",
"body": "… prompt targets, session-model routing\n\n- set-prompt appends now accumulate as standing directives; replace swaps\n the base prompt and keeps accumulated appends. harnessSummary exposes the\n full override texts so fresh meta ticks see standing directives instead\n of a bare target:mode list.\n- pre\n[…]\nent/revise agents inherit\n the session model instead of a pinned opus, so sessions on newer models\n (Fable) are not downgraded. Easy briefs stay on sonnet; the state reader\n stays pinned to sonnet.",
"is_bot": false,
"headline": "feat(optimize): meta journal, accumulating prompt overrides, verifier…",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-11T10:27:58Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "934cb798604e3ec31779a978144d845ceb60b9ea",
"body": "release: 0.5.1",
"is_bot": false,
"headline": "Merge pull request #68 from evo-hq/release/0.5.1",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-11T03:50:36Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7cb0021e7915a9fe8f1c4dfa4934b882aeecab42",
"body": "CI runners have no codex CLI and stage evo-hook-drain.exe on Windows;\nthe new install/doctor tests assumed both.\n\n- TestInstallRunsDoctor satisfies codex.install's which(\"codex\") gate\n with a PATH stub (never invoked for --from-path installs)\n- TestDoctorHookBinary stages the platform binary name; doctor resolves\n evo-hook-drain.exe on Windows since a68f30e\n- TestWrapperPreservation skips on Windows (sh wrapper is posix-only)",
"is_bot": false,
"headline": "test: make install/doctor tests host-independent and Windows-correct",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-11T03:43:17Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a68f30ea4576297cb389d44f168f3de34891064c",
"body": "…hooks by default\n\nCodex re-clones its marketplace snapshot from git at session start and\nre-stages the plugin cache from it, removing anything evo staged into\nthose directories. Mirroring the binary into the snapshot (previous\ncommit) therefore only survives until the next refresh.\n\n- The fetched e\n[…]\ntouches a hook silently reverted codex\ninstalls to untrusted. evo doctor codex verifies trust state: passes\nwhen all hashes match, warns on a deliberate untrusted install, fails\nwhen hashes are stale.",
"is_bot": false,
"headline": "fix(install): stable hook binary home + tracked wrapper; trust codex …",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-11T03:30:55Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "d1a5b85264c218f441c1b6d70f741d6a30b4b3b4",
"body": "`evo install <host>` and `evo update <host>` now finish by running the\nhost's doctor and return its result. An install that doctor can't\nverify previously reported success and failed at hook-fire time;\nverification required knowing to run `evo doctor <host>` manually.",
"is_bot": false,
"headline": "feat(install): run the host doctor after every install/update",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-11T03:05:30Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "471e6805099703b0e82d1d6856f37c6b4f8e43c2",
"body": null,
"is_bot": false,
"headline": "release: bump to 0.5.1",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-11T02:59:26Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "febc48a3855e509c64dcff2e616148c9e8d2c229",
"body": "Hosts re-stage the plugin cache by copying the marketplace snapshot:\ncodex does it on its own when the snapshot changes, claude-code on\n`claude plugin update`. The snapshot is a git tree without the release\nbinary, so a re-stage dropped bin/evo-hook-drain from the cache and\nevery hook fired exit 127\n[…]\nout failing:\n `evo update` skips hosts whose doctor fails, and update is what\n re-mirrors the binary\n- regression tests simulate the host re-stage in sandboxed\n CODEX_HOME / CLAUDE_CONFIG_DIR roots",
"is_bot": false,
"headline": "fix(install): mirror evo-hook-drain into the marketplace snapshot",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-11T02:59:20Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "0090ce91832070ae641d0ae516254eba13c3691a",
"body": "Release v0.5.0",
"is_bot": false,
"headline": "Merge pull request #67 from evo-hq/release/0.5",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-06T09:35:40Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "62e56c440605587e1ef2ef873ec08accb2246423",
"body": "- finetuning SKILL.md was stuck at 0.4.4-alpha.3; set to 0.5.0.\n- bump-version.py SKILLS tuple tracked verifier/ideator (agents, silently\n skipped) and omitted finetuning, so the script never bumped it; point it\n at the real skills incl. finetuning.\n- dashboard stripAnsi: replace the invisible lit\n[…]\nb escape and broaden the ESC-dropped fallback to any CSI\n letter with a digit guard — strips [2K]-style leftovers while leaving\n [INFO]/[ERROR]/[WARN] markers intact.\n\nAddresses Devin review on #67.",
"is_bot": false,
"headline": "fix: finetuning skill version + bump SKILLS tuple; harden stripAnsi",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-06T09:33:09Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "00c3b0c916501acd59e7701f8c61de2f0845843c",
"body": "_descendant_pids was Unix-only (`ps -eo pid=,ppid=`); add a Windows path\nvia `Get-CimInstance Win32_Process` (PowerShell) emitting the same\n'pid ppid' lines, so `evo abort` finds the subprocess tree on Windows too.\n\nMake the two asset-abstraction tests OS-agnostic instead of Unix-assuming:\n- normalize path separators before the artifact-resolve suffix check\n- spawn a python child (not the `sleep` binary) in the descendant-pids test,\n and capture descendants before killing the parent.",
"is_bot": false,
"headline": "fix(cli): make _descendant_pids cross-platform + OS-agnostic tests",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-06T09:23:05Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e0e9bccd301d51cd417708b3f6bddc1b631c70a5",
"body": null,
"is_bot": false,
"headline": "release: bump to 0.5.0",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-06T09:03:25Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "54659f346031abe7b032db1d6a11606142edd6f9",
"body": null,
"is_bot": false,
"headline": "release: bump to 0.5.0-alpha.13",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-05T22:05:30Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6d5c909205a6a8e9ddec108c2219c94536c51df6",
"body": "…low is the default driver on Claude Code\n\nRename the concurrent analyst to \"meta\" and give it free-will harnessEdits\n(set-knob / toggle-phase / set-prompt / inject-step). The optimize loop now reads\na mutable harness object each round -- width, budget, stall, ideate cadence,\nphase toggles, per-step\n[…]\nhe skill reconciles the config so the nudge\nstill drives.\n\nTests: test_analyst_stop.py -> test_meta_stop.py (meta/harness + driver-default\npolicy); test_stop_nudge.py gains workflow-suppression cases.",
"is_bot": false,
"headline": "feat(optimize): meta controller restructures the workflow live; workf…",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-05T21:18:09Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "895e6fa5972805e1141833c66316119aecf8744c",
"body": "…--from-path installs\n\nA --from-path install runs the plugin straight from the source tree -- claude\nresolves ${CLAUDE_PLUGIN_ROOT} to <from_path>/plugins/evo, not the version\ncache. install()/update() staged evo-hook-drain into _latest_cache_dir(), so\nthe from-path bin/ never received it and every hook fired exit 127, breaking\nevo direct delivery. Route staging through _hook_drain_staging_dir(), which\ntargets the source plugin dir when from_path is set and the cache otherwise.",
"is_bot": false,
"headline": "fix(host_install/claude-code): stage hook-drain into source tree for …",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-05T14:36:17Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1cbf965ef03cceeac0a9e5b07b41edc48158d80d",
"body": null,
"is_bot": false,
"headline": "chore: bump 0.5.0-alpha.11 → 0.5.0-alpha.12, sync npm/",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-05T14:04:42Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e80126169df01ecb52db701f4a3e8d097b2fc466",
"body": "tests/unit/test_asset_abstractions.py — guards the CLI behavior the manual dry\nrun exercised so it survives in CI:\n- _resolve_preserved_artifact: single, multi-source dedup (the bug we hit),\n ambiguity (+ label disambiguation), missing manifest\n- _runtime_env_for_attempt: EVO_SEED_ARTIFACT + EVO_PA\n[…]\nts recorded as reusable\n- evo discard --failure-class: recorded on the node\n- task-skills config: comma-list normalization + clear\n- _descendant_pids: abort tree-kill core finds the child process tree",
"is_bot": false,
"headline": "test(assets): unit cover the new evo abstractions",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-05T13:57:20Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "1c4f4929a1aba9b961a60a0b5b60b99c90e1d088",
"body": "The STOP-signal examples were finetuning-flavored (device_map offload,\nchat-template corruption). Generalize to category-agnostic signatures\n(unparseable scorer output, silent throughput collapse, corrupt input/format)\nso the analyst reasons the same for any task category; the category skill\nsupplies the specifics.",
"is_bot": false,
"headline": "docs(optimize/workflow): make analyst STOP examples category-agnostic",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-05T13:51:49Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4786eec95bdbf1e20bcc60e5ed189905181f0b68",
"body": "…coded HF/hardware specifics\n\nWas a HuggingFace+80GB-specific blurb (device_map={'':0}, the exact meta-device\nerror, '4-8B on 80GB'). Rewrite principle-first: configure for training not\ninference — don't enable inference auto-placement/sharding/offload (or other\ninference-mode defaults) in a training run; they break the backward pass or\nsilently offload (slow, no error); shard only when it truly doesn't fit, via the\nframework's training-parallelism path. HF case demoted to a labeled example.",
"is_bot": false,
"headline": "docs(finetuning): make device-placement a generic principle, not hard…",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-05T13:50:56Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "fc63ca6debe9e98886598995cabf589bebd2af81",
"body": "…p-resume after STOP (#7)\n\n#7 is the EXISTING scan/aggregate's job, not a new mechanism — they already emit\naxis-warnings and the brief pivots to the orthogonal axis. Wire them to use the\nnew failure_class signal:\n- scanBrief + aggregatePrompt: a cluster of failure_class=hypothesis across\n structur\n[…]\nrt status:none and do NOT retry — so the round completes cleanly and\nthe next brief carries the recorded fix (via analystSignals -> knownLearnings).\n\ntests/unit/test_analyst_stop.py extended for both.",
"is_bot": false,
"headline": "feat(optimize/workflow): cluster-on-failure_class in scan + clean loo…",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-05T12:23:14Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "a7e426a0c2e8f80c2f6fff4e2f00e9909955ce32",
"body": "Wires the in-flight circuit-breaker on the analyst<->enforcer split:\n\n- ANALYST_FINDINGS gains a `stops` array; every stop carries the full\n diagnosis: {expId, failureClass (build|eval|hypothesis), reason, fixHint}.\n A STOP is a diagnosed, recoverable stop — not a crash.\n- analystPrompt instructs \n[…]\nrief corrects rather than just abandons.\n\nDetect (analyst) and act (enforcer) stay separate; the enforcer double-checks\nbefore pulling the trigger. tests/unit/test_analyst_stop.py guards the contract.",
"is_bot": false,
"headline": "feat(optimize/workflow): analyst STOP signal + gated enforcer (#6)",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-05T12:09:52Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "f43beed8b93db6c518cba5d4172285afc8b3ed8a",
"body": "…ucted\n\nCompletes the capsule piece of #5:\n- Document the lane decomposition in runBrief: build+eval are a single agent;\n the only split (implement | run) is at the read-only evo:verifier seam, with\n the worktree as referenced shared state and the capsule loading category\n skills on both — \"decom\n[…]\nde-driven behavior check that RUNS the real\n capsuleLines() and asserts it emits the load instruction (+ known learnings)\n when state.taskSkills is set, and a project.md-inference fallback when not.",
"is_bot": false,
"headline": "test(optimize): task-skill loading parity + workflow-loads-when-instr…",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-05T11:52:39Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "33f2eaaa73ced85b3552572353d5117de361e2ee",
"body": "…agents load them\n\nCloses the \"resolve once, load everywhere\" half of the capsule design.\n\n- New `task-skills` config field (comma-separated evo skill names): set/get,\n shown in `config show`, normalized to a list, free-form (no enum) so new\n category skills need no CLI change.\n- discover (Step 7a\n[…]\nument the field.\n\nSo both planes now load the category's method skill deterministically instead\nof reverting to base-model defaults (the device_map / stale-API / eval-before-\nbuild class of mistakes).",
"is_bot": false,
"headline": "feat(config): task-skills field — discover resolves category skills, …",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-05T11:41:44Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "ee650c1056ea37538c8da3344e31ee34c7e77d12",
"body": null,
"is_bot": false,
"headline": "chore: refresh uv.lock",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-05T07:43:14Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "453fbb94fc520a61c8cf7e88cb74fccfa03e9b48",
"body": "…aker\n\nCategory-agnostic asset/reuse/stop machinery (mechanism in core, knowledge\ndeclared by skills — never finetuning-specific, no hardcoded final_model):\n\nCLI (cli.py):\n- `evo discard --failure-class {build,eval,hypothesis}` — records why a node\n failed on the node + outcome, to route reuse vs b\n[…]\n(classified + checkpoint preserved) -> new\n--from-artifact -> EVO_SEED_ARTIFACT reached the recipe; and abort mid-run took\ndown the driver + benchmark subprocess tree with the partial checkpoint kept.",
"is_bot": false,
"headline": "feat(assets): failure classifier, artifact reuse, mid-run circuit-bre…",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-05T07:42:45Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "b159561b6e7a0de0afa161bafdf3261c16d892ec",
"body": "…ly known learnings\n\nThe workflow decomposed each experiment into stateless implement/run agents\nthat loaded only the subagent skill, so the agent writing the recipe had none\nof the task-category priors a prose single-subagent gets (it never loaded\nevo:finetuning — grep was 0). Result: it rediscover\n[…]\n\"finetuning\".\n\nAlso generalize the run-lane ordering guard: the produced artifact is whatever\nthe recipe declares (checkpoint dir / adapter / merged model / index / ...),\nnot a hardcoded final_model/.",
"is_bot": false,
"headline": "feat(optimize/workflow): context capsule — load category skills + app…",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-05T04:53:47Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "1fbcd3da92d20764b1d40c815c5ee28679c04030",
"body": "Cherry-picked from anirudh5harma's #64 onto the 0.5.0 line. Copies\ndeclared benchmark/trace artifacts out of a worktree-backed experiment\nbefore discard, writes a discard artifact manifest, and references the\npreserved artifacts from the discarded result — so eval-side failures\ndon't destroy still-u\n[…]\n5.0 branch: kept the existing\n_capture_discard_time_diff call alongside the new preservation step;\nboth run before delete_discarded_experiment wipes the worktree.\n\n(cherry picked from commit b111ec5e)",
"is_bot": false,
"headline": "fix(discard): preserve declared artifacts (#64)",
"author_name": "anirudh5harma",
"author_login": "anirudh5harma",
"committed_at": "2026-06-05T04:48:39Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "06eae04bb77ee194ef43a8c30d5714aa2508b3da",
"body": null,
"is_bot": false,
"headline": "chore: bump 0.5.0-alpha.10 → 0.5.0-alpha.11, sync npm/",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-04T22:39:57Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e2861d806c920cde1526a909df53144c0bb85ae4",
"body": "…ore evo run\n\nThe workflow splits a subagent into separate implement and run agents.\nimplementPrompt loads the subagent skill in full; runPrompt was a fresh\nagent told only \"Run `evo run` to evaluate and commit\" — no skill load,\nno `--check`, no train-then-eval ordering. For a finetune the run agent\n[…]\nmes `evo run --check` for\nnon-committing wiring validation, and requires the artifact (e.g.\nfinal_model/) to exist before the real run, warm-starting from\nEVO_PARENT_POLICY when the experiment trains.",
"is_bot": false,
"headline": "fix(optimize/workflow): run-lane must finish the build/train step bef…",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-04T22:39:47Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "aac0f72a1dfea015773820443b26d90981ce077c",
"body": null,
"is_bot": false,
"headline": "chore: bump 0.5.0-alpha.9 → 0.5.0-alpha.10, sync npm/",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-04T21:38:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a24ca6b675dde109614a53dd1faa2dd76339f340",
"body": null,
"is_bot": false,
"headline": "chore: bump 0.5.0-alpha.8 → 0.5.0-alpha.9, sync npm/",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-04T21:04:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "24f220e9bf802395b64ed0e2449ff7554b5d34d4",
"body": "Runs a self-paced Opus observer alongside the optimize round loop via\nPromise.all. It checks host and cross-history signals during rounds\n(zombie GPU, buried stderr, stuck experiment, saturated axis, dead\ndirection) and folds work-quality hints into the next round's brief;\nruntime and host issues su\n[…]\nect Promise.all and abort the run.\n- Self-disables after 3 consecutive failed ticks, so a tick that fails\n before its pacing wait can't hot-spin agents.\n\nOrient state-read moves from haiku to sonnet.",
"is_bot": false,
"headline": "feat(optimize): concurrent analyst thread for the workflow driver",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-04T21:03:55Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "ca14911389e45ba178f1fec65875d9627dd05ce9",
"body": null,
"is_bot": false,
"headline": "chore: bump 0.5.0-alpha.7 → 0.5.0-alpha.8, sync npm/",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-04T19:38:42Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "026692c2d170b14167d2f61f0afe3e02053c3563",
"body": null,
"is_bot": false,
"headline": "feat(optimize): configurable scan batch size + compact scan-batch labels",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-04T19:38:32Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c8882b6a57eac3abc2ba97cc51ab97d6ecf36542",
"body": "…loop\n\nOpt-in, Claude-Code-only workflow driver alongside the prose loop, selected by\ndefault-orchestrator (prose|workflow; default prose). When host=claude-code and\nthe flag resolves to workflow, optimize/SKILL.md launches\nskills/optimize/workflows/evo-optimize.js via the Workflow tool instead of\nd\n[…]\ng); schemas stay flat\nbecause the StructuredOutput validator rejects allOf/if/then.\n\ncli.py: default-orchestrator config field (set/get/show + argparse choices).\n.gitignore: ignore .claude/worktrees/.",
"is_bot": false,
"headline": "feat(optimize): Claude Code dynamic-workflow driver for the optimize …",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-04T18:08:48Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "3890380d70e0a5c0da1bd87eac9f5111f024f467",
"body": null,
"is_bot": false,
"headline": "Merge branch 'feat/model-update' into feat/optimize-workflow",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-04T09:12:28Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d5439773f724adcc7e0c8a31f5e80e6eec581cc1",
"body": "# Conflicts:\n#\tplugins/evo/.claude-plugin/plugin.json\n#\tplugins/evo/.codex-plugin/plugin.json\n#\tplugins/evo/npm/package.json\n#\tplugins/evo/npm/skills/discover/SKILL.md\n#\tplugins/evo/npm/skills/infra-setup/SKILL.md\n#\tplugins/evo/npm/skills/optimize/SKILL.md\n#\tplugins/evo/npm/skills/report/SKILL.md\n#\t\n[…]\n#\tplugins/evo/skills/report/SKILL.md\n#\tplugins/evo/skills/subagent/SKILL.md\n#\tplugins/evo/src/evo/__init__.py\n#\tsdk/node/package.json\n#\tsdk/python/pyproject.toml\n#\tsdk/python/src/evo_agent/__init__.py",
"is_bot": false,
"headline": "Merge remote-tracking branch 'origin/main' into feat/model-update",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-04T09:11:57Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "b4f06a35e092627d3dc4bbddcfd86ff59ad064d5",
"body": "Existing codex installs hitting hook exit 127 are skipped by evo update\n(the broken install reports unhealthy), so document the explicit\nuv tool install --force + evo install codex --force recovery.",
"is_bot": false,
"headline": "docs(readme): codex exit-127 recovery in Upgrading (#62)",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-04T08:51:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4a45773f728f8e56b6be0e17253a1ed963c69196",
"body": "….5 (#61)\n\n* fix(host_install/claude-code): honor CLAUDE_CONFIG_DIR for cache paths\n\nPath.home() / \".claude\" hardcoded in 7 spots silently misses the plugin\ncache when Claude Code is configured via CLAUDE_CONFIG_DIR (cloud\ncontainers with a persistent volume, sandbox setups, custom configs).\nThe dow\n[…]\ncographically\n(0.9.0 > 0.10.0) and matched commented-out [plugins.\"evo@...\"] lines.\nSort numerically and skip comment lines. Add doctor integration tests\ncovering both. (Devin review findings on #61.)",
"is_bot": false,
"headline": "fix(codex): stage hook binary under owner marketplace name + bump 0.4…",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-04T08:23:19Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "007ddb7b3d54694cee08aff9bbf622b6e14e2c49",
"body": "Drawer Summary tab gains a Diagnoses section (global annotations from\nbenchmark-reviewer/verifier/agents); Tasks tab shows the per-task\nannotation inline under each failing task, plus target + full model\noutput on expand. Logs tab replaces the file dropdown with inline file\ntabs, strips ANSI escape codes, and unifies the card styling. Tab strip\nfixed from 3-col to 4-col grid (Logs no longer wraps) with brighter\nactive-tab contrast for low-contrast monitors.",
"is_bot": false,
"headline": "feat(dashboard): render annotations + clean up tabs and logs",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-03T17:02:57Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "00ef492b0a4a129035862e1d9bf5c50dc30ec101",
"body": "- finetuning: add `## Long training: checkpoint, mid-eval, early-stop\n in-script` -- for trainings > 30 min, build a TrainerCallback that\n periodically saves a checkpoint, runs a mini-eval on a 5-10 item\n held-out subset, and stops on stalled/regressing trajectory. Commits\n the best mid-eval che\n[…]\nd evo:finetuning trigger line with\n scope hint (technique choice, training recipe, observability, retry\n discipline) so the subagent knows it has the right skill without\n re-reading the whole body.",
"is_bot": false,
"headline": "skills(finetuning,subagent): training-scale discipline",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-02T19:18:31Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "77265f2289c3eb443ea0ee62ab21547c34f57009",
"body": "- benchmark-reviewer: add `mode=review-experiment` for post-commit\n per-task failure analysis. Reads per-task traces + eval-runner log,\n classifies failures into a 9-category taxonomy (truncated,\n wrong-format, wrong-answer, hallucination, refusal, language-drift,\n prompt-misread, eval-error, un\n[…]\nort_to one-liners, custom-loop init+log pattern, EVO_EXPERIMENT_ID\n as run name. Closes the observability-blind window during long\n training runs (separate from in-flight evo state, tracked in #59).",
"is_bot": false,
"headline": "skills: post-commit per-task review + training observability",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-02T18:52:23Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "0ddab59b5cf45910e473336807b7d92e86c27e79",
"body": "Existing test_hook_drain.py uses a fake evo-drain shim that prints {} --\nverifies the Rust binary handoff trigger, not what drain.py actually\ndoes with queued events. Real drain code path had zero coverage.\n\n6 new tests in tests/unit/test_directive_delivery_e2e.py exercising\nthe full pipeline: cmd_d\n[…]\nefore\nthe next drain invocation -- until after observation ended.\n\nThese tests serve as regression coverage for the queue+delivery\ncontract going forward; they would catch a real break in either half.",
"is_bot": false,
"headline": "test: end-to-end coverage for directive delivery pipeline (#58)",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-02T15:05:32Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "17bb3f48c42d804da9e8c0aef30ee92f5a534fa0",
"body": "…tion\n\nPrevious description -- \"Run the evo optimization loop with parallel\nsubagents until interrupted\" -- read like ceremony if width is 1. Agent\nin a recent run reasoned itself out of invoking the skill: \"instead\nof going through the full evo:optimize ceremony (which adds subagent\noverhead), I'll\n[…]\n slash-command\nlisting before deciding whether to invoke. Loading it via Skill is\ngated behind that decision; once the agent decides bypass is fine,\nthe body's \"don't bypass\" warnings are unreachable.",
"is_bot": false,
"headline": "skills/optimize: reframe description as structured autoresearch itera…",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-02T14:53:29Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "59787eaac3f0789eb3cd3b0e0e63a914a0149623",
"body": "…ences principle\n\nReplace the verbose \"Skills before references, always\" lecture in\ndiscover with one principle line near the top of the Evo surface\nsection: \"Always have a sense of the skill before jumping into its\nreferences.\" Keep the tree itself unchanged (skills + references at\ntheir normal hie\n[…]\nhe tree placed it alongside skills with no ordering\nhint.\n\nglue.md: short pointer at the top noting the technique pick lives in\nthe parent skill body, not in this file. One sentence; doesn't\nmoralize.",
"is_bot": false,
"headline": "skills: reframe Evo surface as general guidance + skills-before-refer…",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-02T13:57:55Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "5a6bbe8b71001003a1a69547acd6d28d325e2fc8",
"body": "Carries:\n- skills: Evo surface trees in discover/optimize/subagent + categorized\n references tree (rl/sft/serving) in finetuning\n- skills: drop ideator/verifier stub redirects; make evo:subagent\n orchestrator-readable\n- hook-drain (#49 follow-up): word-boundary `evo` detection in\n PostToolUse + e\n[…]\nnt wipes the worktree+branch; dashboard\n drawer renders discard_reason for discarded experiments\n- testing: 38 new unit tests (18 Rust + 20 Python); helpers refactored\n out of cli.py for testability",
"is_bot": false,
"headline": "chore: bump 0.5.0-alpha.6 → 0.5.0-alpha.7, sync npm/",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-02T13:19:40Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "9598a64fc6ee32466e5f7e5a45ddac43787f657b",
"body": "#49 (Rust hook-drain) -- 18 new unit tests in main.rs:\n - contains_evo_word: 8 tests covering direct, chained, shell-snapshot\n wrappers, tab separators, start-of-string, AND adversarial cases\n (servo init, levo build, evolution.py, evolved.sh, sevo --help,\n cargo install evo-hq-cli, python\n[…]\n pass (1 known-flaky test\n `test_gate_check_runs_gates_without_changing_node_status` passes\n in isolation; intermittent failure in bulk sweep is pre-existing\n and not caused by these changes)",
"is_bot": false,
"headline": "test: cover #49/#56/#57 + extract helpers for testability",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-02T13:10:19Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "5b82f2b7c548491b685bdb2cb505c3e7be713631",
"body": "…6), discard-time diff + dashboard discard_reason (#57)\n\n#49 -- hook-drain: engage on evo invocations seen via PostToolUse\n Previously: SessionStart engaged the orchestrator, but only when\n .evo/ already existed. For claude --print batch mode that created\n the workspace mid-session via `evo init`\n[…]\non in the dashboard summary and (ii) the actual code changes\n via diff.patch the dashboard's Diff tab renders.\n\nCloses #49 (engagement-half; registration-half already landed).\nCloses #56.\nCloses #57.",
"is_bot": false,
"headline": "fix: hook-drain engagement upgrade (#49), --check tasks assertion (#5…",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-02T12:46:34Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "6f54c9b64df9548b1e561553a83a17a4853f29de",
"body": "Carries:\n- skills: drop ideator/verifier stub redirects; make evo:subagent\n orchestrator-readable\n- skills: add Evo surface tree to discover/optimize/subagent +\n finetuning references (categorized by rl/sft/serving)\n- sizing-the-round.md: moved from optimize/ to discover/references/\n (decision happens at the discover->optimize handoff)",
"is_bot": false,
"headline": "chore: bump 0.5.0-alpha.5 → 0.5.0-alpha.6, sync npm/",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-02T12:08:56Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "199a28af55157b29b4b98142ed5bfe9df57be3cb",
"body": "…ng references\n\nThe agent has had no map of evo's invocable surface, only individual\nskill descriptions. Result, observed in a recent run: agent stuck in SFT\nfor 5 experiments without ever invoking evo:finetuning, never read\nsizing-the-round.md, hand-wrote a stripped-down log_task/write_result\nthat \n[…]\n->optimize handoff,\nwhich is during discover; reading it after /evo:optimize is invoked is\ntoo late -- subagents=N is already chosen). Updated the path reference\nin optimize/SKILL.md body accordingly.",
"is_bot": false,
"headline": "skills: add Evo surface tree to discover/optimize/subagent + finetuni…",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-02T12:01:42Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "8a8a7785faa81916f37fbf6f5fa6aa5930192412",
"body": "…ator-readable\n\nideator and verifier migrated from skills to subagents in d69f35d /\n0127244 (plugins/evo/agents/{ideator,verifier}.md). The skill paths\nwere kept as 6-line stub redirects so any caller resolving\nSkill(\"evo:ideator\") got a clear pointer rather than a not-found\nerror.\n\nIn practice the \n[…]\n\nat \"Host conventions\" -- the rest of the body is subagent-as-reader.\nThe brief-writing logic in /optimize gets a place to learn the\nsubagent's input/output contract without having to grep the source.",
"is_bot": false,
"headline": "skills: drop ideator/verifier stub redirects + make subagent orchestr…",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-02T11:27:55Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "a6e70c4f152bd881d8b26410982ea66a998d9560",
"body": "Carries:\n- docs(skill/finetuning): cache expensive intermediates under .evo/cache/\n- docs(skill/subagent): domain-agnostic counterpart pointing at finetuning",
"is_bot": false,
"headline": "chore: bump 0.5.0-alpha.4 → 0.5.0-alpha.5, sync npm/",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-01T23:05:32Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6333a4d104db345997a9c52c5f9fb857fa61487e",
"body": "Domain-agnostic counterpart to the finetuning skill's caching section.\nSubagent skill applies to every experiment-running agent regardless of\ndomain, so this is where the general \"check before recomputing\" prior\nbelongs.\n\nLists the artifact shape (slow to produce, stable across siblings/\ndescendants\n[…]\ne path (.evo/cache/, gitignored, untouched by\nnew/run/reset). Calls out the worktree-local anti-pattern. Defers the\nconcrete read-or-compute pattern to the finetuning skill rather than\nduplicating it.",
"is_bot": false,
"headline": "docs(skill/subagent): reuse expensive intermediates via .evo/cache/",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-01T23:02:39Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "3d490d7090691bd89357d23bd170080ccff64a71",
"body": "New section after parent-warm-start covering reusable artifacts -- LoRA\nadapters, curated/tokenized datasets, embeddings, retrieval indexes,\nprecomputed eval generations.\n\nConvention is .evo/cache/, sibling to run_<NNNN>/. Already gitignored\nvia the workspace's .evo/ exclude. Survives evo new / evo \n[…]\nes the artifact, read-or-compute. Calls out the worktree-local\nanti-pattern (artifact disappears on gc) and acknowledges the HF Hub\ncache to avoid duplication.\n\nDefers the named-asset registry to #55.",
"is_bot": false,
"headline": "docs(skill/finetuning): cache expensive intermediates under .evo/cache/",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-01T22:49:23Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "6fb7699a3a525ec5ea2800d095ddf8ac2e145b4b",
"body": null,
"is_bot": false,
"headline": "chore: bump 0.5.0-alpha.3 → 0.5.0-alpha.4, sync npm/",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-01T21:20:28Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d6f733b8e6a2b0723b13ff699ffbdaf0e677c246",
"body": "…workspace check\n\nFixes #53.\n\n`cmd_wait` called `repo_root()` and the `.evo/` existence check at the\ntop of the function, before any `--for` parsing. That bailed any\ninvocation outside an evo workspace, even when the user only requested\nexternal-state watches (`--for process=<pid>`, `--for log-growt\n[…]\nout 1s` (legacy default) in the same tmpdir still\n errors with `ERROR: not in an evo workspace (required for --for\n experiments|ideators)`.\n- All 19 unit tests in `tests/unit/test_evo_wait.py` pass.",
"is_bot": false,
"headline": "fix(evo wait): non-workspace targets (process/log-growth/gpu-*) skip …",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-01T21:20:28Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "cb3b3d74374cc8d3b4fe6505b14c8db853177996",
"body": null,
"is_bot": false,
"headline": "chore: bump 0.5.0-alpha.2 → 0.5.0-alpha.3, sync npm/",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-01T21:01:03Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9a20b2cb1409b010de18c1a13aa9a5610b4b4e6b",
"body": "The evo wait extension (#52) broke 8 unit tests in three clusters,\nwhich kept the v0.5.0-alpha.1 and v0.5.0-alpha.2 publish workflows\nfailing at preflight. Fix all three:\n\n1. test_timeout_capped_at_3600 expected the old 1-hour cap. The cap\n was raised to 24h alongside the extension so long externa\n[…]\nanged from \"no new ideator proposal\" to \"no\nideators activity\"; loosened assertIn to \"ideators\" which matches\nboth old and new wording.\n\nAll 18 tests pass locally (pytest tests/unit/test_evo_wait.py).",
"is_bot": false,
"headline": "fix(tests): unit tests for evo wait keep up with the extension (d979bab)",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-01T21:01:03Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "ffa6ca35b68a8a750eaea204c55588883365c695",
"body": "…e to use it\n\n`evo wait` got extended with process/log-growth/gpu-active/gpu-idle\ntargets, --timeout duration strings, --stall-threshold, --poll-interval,\nand --json in d979bab (#52), but the docs lagged:\n\n- cli-quick-reference.md still showed the pre-#52 surface\n (`[--for experiments|ideators] [--\n[…]\ntics\n- the bounded poll-loop fallback drops from primary content to a\n one-paragraph fallback for environments where `evo wait` isn't\n available\n\nNo version bump; this is pure docs. Tests untouched.",
"is_bot": false,
"headline": "docs(evo wait): add references/evo-wait.md; update discover + optimiz…",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-01T20:45:13Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "26ffbebfe30f4c988f24715e16ec2b7f2ac5a6f8",
"body": "Standard bump-version.py run. Updates the 12 versioned files\n(pyproject.toml, evo/__init__.py, plugin.json, .codex-plugin/plugin.json,\nnpm/package.json, sdk/python/pyproject.toml, sdk/python/evo_agent/\n__init__.py, sdk/node/package.json) plus the evo_version frontmatter\nin every SKILL.md and the `ev\n[…]\nrichness note + eval-only\nbenchmark, finetuning literature-research + warm-start, etc.) and\nthe new agents/ subagents (benchmark-reviewer, verifier, ideator)\nreflected in the npm-bundled skill bodies.",
"is_bot": false,
"headline": "chore: bump 0.5.0-alpha.1 → 0.5.0-alpha.2, sync npm/",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-01T20:35:51Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "d369d62a850aee3ad66411764af0ebf99e8baeac",
"body": "… voice\n\nd352c27 added step 6a with three domain-specific checks: training\ntechniques named in check 1 (SFT, GRPO, RFT), TRL/distributed/\ninterpreter failures in check 2, training-loss-vs-benchmark and\nchat-template alignment in check 3. Plus a hard \"MUST target the\northogonal axis\" closing rule. Th\n[…]\n point without commandment.\n\nevo is a general-purpose autoresearcher. The pattern check should\nread clean to an orchestrator optimizing a search algorithm or a\nbuild pipeline, not just an ML pipeline.",
"is_bot": false,
"headline": "fix(skill/optimize): make step 6a checks domain-agnostic, soften rule…",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-01T20:33:42Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "82690f4e31cc656d3833b4681ecf13ab8f5add3b",
"body": "The existing \"per-task emission is load-bearing\" + runner-library\nwrapper anti-pattern guidance covers SHAPE (one entry per item, with\nextras). It didn't cover what those extras and the experiment-level\nannotation should actually contain. A trace recording {score: 0} with\nno context is unrecoverable\n[…]\nd\n ideator briefs, so they're facts, not plans or feelings.\n\nTwo paragraphs, no MUSTs beyond the inherited ones. Slots between\nthe existing runner-library paragraph and step 10d (benchmark-reviewer).",
"is_bot": false,
"headline": "feat(skill/discover): note that traces are for the future reader",
"author_name": "Alok Kumar Bishoyi",
"author_login": "alokwhitewolf",
"committed_at": "2026-06-01T20:26:56Z",
"body_truncated": true,
"is_coding_agent": false
}
],
"releases_count": 59,
"commits_last_year": 458,
"latest_release_at": "2026-07-17T16:57:14Z",
"latest_release_tag": "v0.8.0",
"releases_from_tags": false,
"days_since_last_push": 5,
"active_weeks_last_year": 14,
"days_since_latest_release": 5,
"mean_days_between_releases": 3.2
},
"community": {
"has_readme": true,
"has_license": true,
"has_description": true,
"has_contributing": false,
"health_percentage": 37,
"has_issue_template": false,
"has_code_of_conduct": false,
"has_pull_request_template": false
},
"ecosystem": {
"packages": [
{
"name": "@evo-hq/evo-agent",
"exists": true,
"license": "Apache-2.0",
"keywords": [
"evo",
"claude-code",
"optimization",
"experiments",
"benchmarks"
],
"ecosystem": "npm",
"matches_repo": true,
"registry_url": "https://www.npmjs.com/package/@evo-hq/evo-agent",
"is_deprecated": false,
"latest_version": "0.8.0",
"repository_url": "https://github.com/evo-hq/evo",
"versions_count": 65,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": 1,
"monthly_downloads": 8539,
"first_published_at": "2026-04-12T08:14:34.399000Z",
"latest_published_at": "2026-07-17T16:56:21.417000Z",
"latest_version_yanked": null,
"days_since_latest_publish": 5
},
{
"name": "evo-hq-agent",
"exists": true,
"license": "Apache-2.0",
"keywords": [],
"ecosystem": "pypi",
"matches_repo": true,
"registry_url": "https://pypi.org/project/evo-hq-agent/",
"is_deprecated": false,
"latest_version": "0.8.0",
"repository_url": "https://github.com/evo-hq/evo",
"versions_count": 65,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": null,
"monthly_downloads": null,
"first_published_at": "2026-04-12T08:27:25.750538Z",
"latest_published_at": "2026-07-17T16:56:27.953900Z",
"latest_version_yanked": null,
"days_since_latest_publish": 5
},
{
"name": "evo-hq-cli",
"exists": true,
"license": "Apache-2.0",
"keywords": [],
"ecosystem": "pypi",
"matches_repo": true,
"registry_url": "https://pypi.org/project/evo-hq-cli/",
"is_deprecated": false,
"latest_version": "0.8.0",
"repository_url": "https://github.com/evo-hq/evo",
"versions_count": 64,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": null,
"monthly_downloads": 2008,
"first_published_at": "2026-04-13T18:53:49.083298Z",
"latest_published_at": "2026-07-17T16:56:30.123533Z",
"latest_version_yanked": null,
"days_since_latest_publish": 5
}
]
},
"popularity": {
"forks": 101,
"stars": 1348,
"watchers": 3,
"fork_history": {
"days": [
{
"date": "2026-04-12",
"count": 10
},
{
"date": "2026-04-13",
"count": 11
},
{
"date": "2026-04-14",
"count": 3
},
{
"date": "2026-04-15",
"count": 4
},
{
"date": "2026-04-16",
"count": 5
},
{
"date": "2026-04-18",
"count": 2
},
{
"date": "2026-04-20",
"count": 1
},
{
"date": "2026-04-21",
"count": 4
},
{
"date": "2026-04-22",
"count": 1
},
{
"date": "2026-04-24",
"count": 1
},
{
"date": "2026-04-25",
"count": 2
},
{
"date": "2026-04-26",
"count": 1
},
{
"date": "2026-04-27",
"count": 1
},
{
"date": "2026-04-28",
"count": 3
},
{
"date": "2026-05-01",
"count": 1
},
{
"date": "2026-05-02",
"count": 1
},
{
"date": "2026-05-04",
"count": 1
},
{
"date": "2026-05-05",
"count": 1
},
{
"date": "2026-05-08",
"count": 1
},
{
"date": "2026-05-09",
"count": 1
},
{
"date": "2026-05-10",
"count": 1
},
{
"date": "2026-05-13",
"count": 1
},
{
"date": "2026-05-26",
"count": 1
},
{
"date": "2026-05-27",
"count": 4
},
{
"date": "2026-05-28",
"count": 1
},
{
"date": "2026-05-29",
"count": 1
},
{
"date": "2026-05-31",
"count": 1
},
{
"date": "2026-06-03",
"count": 3
},
{
"date": "2026-06-04",
"count": 3
},
{
"date": "2026-06-05",
"count": 1
},
{
"date": "2026-06-06",
"count": 2
},
{
"date": "2026-06-07",
"count": 1
},
{
"date": "2026-06-08",
"count": 3
},
{
"date": "2026-06-10",
"count": 1
},
{
"date": "2026-06-13",
"count": 1
},
{
"date": "2026-06-16",
"count": 1
},
{
"date": "2026-06-17",
"count": 2
},
{
"date": "2026-06-18",
"count": 1
},
{
"date": "2026-06-19",
"count": 2
},
{
"date": "2026-06-20",
"count": 2
},
{
"date": "2026-06-21",
"count": 1
},
{
"date": "2026-06-22",
"count": 1
},
{
"date": "2026-06-23",
"count": 1
},
{
"date": "2026-06-24",
"count": 1
},
{
"date": "2026-06-25",
"count": 1
},
{
"date": "2026-07-03",
"count": 1
},
{
"date": "2026-07-06",
"count": 1
},
{
"date": "2026-07-11",
"count": 2
},
{
"date": "2026-07-14",
"count": 1
},
{
"date": "2026-07-17",
"count": 1
},
{
"date": "2026-07-19",
"count": 1
},
{
"date": "2026-07-21",
"count": 1
}
],
"complete": true,
"collected": 101,
"total_forks": 101
},
"star_history": null,
"open_issues_and_prs": 17
},
"ai_readiness": {
"has_nix": false,
"example_dirs": [],
"has_llms_txt": false,
"has_dockerfile": false,
"has_mcp_signal": false,
"bootstrap_files": [],
"api_schema_files": [],
"has_devcontainer": false,
"typecheck_configs": [],
"toolchain_manifests": [
"plugins/evo/bin/evo-hook-drain-rs/Cargo.toml"
],
"largest_source_bytes": 296301,
"source_files_sampled": 187,
"oversized_source_files": 6,
"agent_instruction_files": [],
"agent_instruction_max_bytes": null
},
"dependencies": {
"manifests": [],
"advisories": {
"error": null,
"scope": null,
"source": null,
"findings": [],
"collected": false,
"malicious": [],
"truncated": false,
"by_severity": {},
"advisory_count": 0,
"affected_count": 0,
"assessed_count": 0,
"malicious_count": 0,
"assessed_package": null,
"unassessed_count": 0,
"direct_affected_count": 0
},
"ecosystems": [],
"dependencies": [
{
"name": "flask",
"manifest": "plugins/evo/pyproject.toml",
"ecosystem": "pypi",
"version_constraint": ">=3.0.0"
},
{
"name": "portalocker",
"manifest": "plugins/evo/pyproject.toml",
"ecosystem": "pypi",
"version_constraint": ">=2.8.0"
},
{
"name": "pyyaml",
"manifest": "plugins/evo/pyproject.toml",
"ecosystem": "pypi",
"version_constraint": ">=6.0.0"
},
{
"name": "requests",
"manifest": "plugins/evo/pyproject.toml",
"ecosystem": "pypi",
"version_constraint": ">=2.31.0"
}
],
"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": 8,
"merged_prs": 40,
"open_issues": 9,
"closed_ratio": 0.7,
"closed_issues": 21,
"closed_unmerged_prs": 8
},
"bus_factor": 1,
"bot_contributors": 0,
"top_contributors": [
{
"type": "User",
"login": "alokwhitewolf",
"commits": 453,
"avatar_url": "https://avatars.githubusercontent.com/u/24509942?v=4"
},
{
"type": "User",
"login": "abpatramsft",
"commits": 3,
"avatar_url": "https://avatars.githubusercontent.com/u/248452882?v=4"
},
{
"type": "User",
"login": "claude",
"commits": 1,
"avatar_url": "https://avatars.githubusercontent.com/u/81847?v=4"
},
{
"type": "User",
"login": "anirudh5harma",
"commits": 1,
"avatar_url": "https://avatars.githubusercontent.com/u/78658727?v=4"
}
],
"contributors_sampled": 4,
"top_contributor_share": 0.989
},
"quality_signals": {
"has_ci": true,
"has_tests": true,
"ci_workflows": [
"ci.yml",
"publish.yml"
],
"has_docs_dir": false,
"linter_configs": [],
"has_editorconfig": false,
"has_linter_config": false,
"has_precommit_config": false
},
"security_signals": {
"lockfiles": [
"Cargo.lock",
"uv.lock"
],
"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": "6 out of 6 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 0/10 approved changesets -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#code-review"
},
{
"name": "Contributors",
"score": 0,
"reason": "project has 0 contributing companies or organizations -- score normalized to 0",
"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 24 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": 10,
"reason": "packaging workflow detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#packaging"
},
{
"name": "Pinned-Dependencies",
"score": 0,
"reason": "dependency not pinned by hash detected -- score normalized to 0",
"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": 0,
"reason": "Project has not signed or included provenance with any releases.",
"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": "32 existing vulnerabilities detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#vulnerabilities"
}
],
"commit": "ab5fbd6c8210ed900157c8907a431bafc74c4215",
"ran_at": "2026-07-23T00:34:02Z",
"aggregate_score": 3.3,
"scorecard_version": "v5.5.0"
},
"has_codeql_workflow": false,
"has_security_policy": false,
"has_dependabot_config": false
},
"contribution_flow": {
"collected": true,
"ci_last_run_at": "2026-07-17T16:57:17Z",
"oldest_open_prs": [
{
"number": 63,
"created_at": "2026-06-04T12:24:28Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 64,
"created_at": "2026-06-04T12:42:21Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 66,
"created_at": "2026-06-05T12:48:09Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 78,
"created_at": "2026-06-23T21:28:44Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 80,
"created_at": "2026-06-27T03:59:04Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 83,
"created_at": "2026-07-03T04:56:03Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 87,
"created_at": "2026-07-22T16:19:37Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 88,
"created_at": "2026-07-22T17:19:11Z",
"last_comment_at": null,
"last_comment_author": null
}
],
"last_merged_pr_at": "2026-07-17T16:52:31Z",
"ci_last_conclusion": "SUCCESS",
"oldest_open_issues": [
{
"number": 3,
"created_at": "2026-04-13T03:28:05Z",
"last_comment_at": "2026-06-05T23:04:43Z",
"last_comment_author": "PredictiveManish"
},
{
"number": 4,
"created_at": "2026-04-13T05:58:18Z",
"last_comment_at": "2026-06-08T08:13:11Z",
"last_comment_author": "anirudh5harma"
},
{
"number": 6,
"created_at": "2026-04-13T08:29:50Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 24,
"created_at": "2026-04-26T16:19:17Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 27,
"created_at": "2026-04-28T04:47:21Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 55,
"created_at": "2026-06-01T20:45:52Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 58,
"created_at": "2026-06-02T14:26:47Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 59,
"created_at": "2026-06-02T18:08:59Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 84,
"created_at": "2026-07-03T12:10:40Z",
"last_comment_at": null,
"last_comment_author": null
}
]
}
},
"config": {
"disabled_metrics": [],
"disabled_categories": [],
"disabled_components": {}
},
"source": {
"url": "https://github.com/evo-hq/evo",
"host": "github.com",
"name": "evo",
"owner": "evo-hq"
},
"metrics": {
"overall": {
"key": "overall",
"band": "moderate",
"name": "Overall health",
"note": null,
"notes": [],
"value": 61,
"inputs": {
"security": 33,
"vitality": 80,
"community": 62,
"governance": 52,
"engineering": 71
},
"components": []
},
"categories": [
{
"key": "vitality",
"band": "good",
"name": "Vitality",
"value": 80,
"weight": 0.22,
"metrics": [
{
"key": "development_activity",
"band": "good",
"name": "Development activity",
"note": null,
"notes": [],
"value": 74,
"inputs": {
"commits_last_year": 458,
"human_commit_share": 1,
"days_since_last_push": 5,
"active_weeks_last_year": 14
},
"components": [
{
"key": "push_recency",
"name": "Push recency",
"detail": "last push 5 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "push_recency",
"params": {
"days": 5
}
}
],
"max_points": 36
},
{
"key": "commit_cadence",
"name": "Commit cadence",
"detail": "14/52 weeks with commits",
"points": 9.7,
"status": "partial",
"details": [
{
"code": "commit_cadence_weeks",
"params": {
"weeks": 14
}
}
],
"max_points": 36
},
{
"key": "commit_volume",
"name": "Commit volume",
"detail": "458 commits in the last year",
"points": 18,
"status": "met",
"details": [
{
"code": "commits_last_year",
"params": {
"count": 458
}
}
],
"max_points": 18
},
{
"key": "openssf_scorecard_maintained",
"name": "OpenSSF Scorecard: Maintained",
"detail": "30 commit(s) and 24 issue activity found in the last 90 days -- score normalized to 10",
"points": 10,
"status": "met",
"details": [],
"max_points": 10
}
]
},
{
"key": "release_discipline",
"band": "excellent",
"name": "Release discipline",
"note": null,
"notes": [],
"value": 90,
"inputs": {
"releases_count": 59,
"latest_release_tag": "v0.8.0",
"releases_from_tags": false,
"days_since_latest_release": 5,
"mean_days_between_releases": 3.2
},
"components": [
{
"key": "ships_releases",
"name": "Ships releases",
"detail": "59 releases published",
"points": 27,
"status": "met",
"details": [
{
"code": "releases_published",
"params": {
"count": 59
}
}
],
"max_points": 27
},
{
"key": "release_recency",
"name": "Release recency",
"detail": "latest release 5 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "release_recency",
"params": {
"days": 5
}
}
],
"max_points": 36
},
{
"key": "release_cadence",
"name": "Release cadence",
"detail": "a release every ~3.2 days",
"points": 27,
"status": "met",
"details": [
{
"code": "release_cadence",
"params": {
"gap": 3.2
}
}
],
"max_points": 27
},
{
"key": "openssf_scorecard_signed_releases",
"name": "OpenSSF Scorecard: Signed-Releases",
"detail": "Project has not signed or included provenance with any releases.",
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
}
]
},
{
"key": "abandonment",
"band": "excellent",
"name": "Abandonment",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"cap": null,
"state": "unverified",
"guards": [],
"signals": [],
"red_flag": false,
"multiplier_pct": 100,
"declared_reason": null,
"unverified_reason": "repository_too_young",
"unanswered_open_prs": null,
"unanswered_open_issues": null,
"days_since_last_merged_pr": null,
"days_since_last_human_commit": null,
"days_since_last_human_commit_is_floor": false
},
"components": [
{
"key": "project_is_still_maintained",
"name": "Project is still maintained",
"detail": "maintenance record not established from the collected data",
"points": 100,
"status": "met",
"details": [
{
"code": "abandonment_unverified",
"params": {}
}
],
"max_points": 100
}
]
}
],
"description": "Is the project alive — is code being written and are releases shipping?"
},
{
"key": "community",
"band": "moderate",
"name": "Community & Adoption",
"value": 62,
"weight": 0.18,
"metrics": [
{
"key": "popularity",
"band": "moderate",
"name": "Popularity & adoption",
"note": null,
"notes": [],
"value": 69,
"inputs": {
"forks": 101,
"stars": 1348,
"watchers": 3,
"growth_state": "unverified",
"growth_factor_pct": 100,
"growth_unverified_reason": "no_history"
},
"components": [
{
"key": "stars",
"name": "Stars",
"detail": "1,348 stars",
"points": 50.8,
"status": "partial",
"details": [
{
"code": "stars",
"params": {
"count": 1348
}
}
],
"max_points": 60
},
{
"key": "forks",
"name": "Forks",
"detail": "101 forks",
"points": 16.7,
"status": "partial",
"details": [
{
"code": "forks",
"params": {
"count": 101
}
}
],
"max_points": 25
},
{
"key": "watchers",
"name": "Watchers",
"detail": "3 watchers",
"points": 1.7,
"status": "partial",
"details": [
{
"code": "watchers",
"params": {
"count": 3
}
}
],
"max_points": 15
}
]
},
{
"key": "community_health",
"band": "moderate",
"name": "Community health",
"note": null,
"notes": [],
"value": 50,
"inputs": {
"has_readme": true,
"has_license": true,
"has_contributing": false,
"has_issue_template": false,
"has_code_of_conduct": false,
"has_pull_request_template": false
},
"components": [
{
"key": "readme",
"name": "README",
"detail": null,
"points": 22.5,
"status": "met",
"details": [],
"max_points": 22.5
},
{
"key": "license",
"name": "License",
"detail": "recognized license (Apache-2.0)",
"points": 22.5,
"status": "met",
"details": [
{
"code": "license_standard",
"params": {}
},
{
"code": "license_spdx",
"params": {
"spdx": "Apache-2.0"
}
}
],
"max_points": 22.5
},
{
"key": "contributing_guide",
"name": "CONTRIBUTING guide",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 18
},
{
"key": "code_of_conduct",
"name": "Code of conduct",
"detail": null,
"points": 0,
"status": "missed",
"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": 0,
"status": "missed",
"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": 67,
"inputs": {
"packages": [
"@evo-hq/evo-agent",
"evo-hq-agent",
"evo-hq-cli"
],
"dependents": null,
"ecosystems": "npm, pypi",
"total_downloads": null,
"monthly_downloads": 10547
},
"components": [
{
"key": "monthly_downloads",
"name": "Monthly downloads",
"detail": "10,547 downloads/month across npm, pypi",
"points": 53.6,
"status": "partial",
"details": [
{
"code": "downloads_monthly",
"params": {
"count": 10547,
"ecosystems": "npm, pypi"
}
}
],
"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": "moderate",
"name": "Sustainability & Governance",
"value": 52,
"weight": 0.24,
"metrics": [
{
"key": "maintainer_resilience",
"band": "critical",
"name": "Maintainer resilience (bus factor)",
"note": null,
"notes": [],
"value": 15,
"inputs": {
"bus_factor": 1,
"contributors_sampled": 4,
"top_contributor_share": 0.989
},
"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 99% of commits",
"points": 0.2,
"status": "partial",
"details": [
{
"code": "top_contributor_share",
"params": {
"share": 99
}
}
],
"max_points": 22.5
},
{
"key": "contributor_breadth",
"name": "Contributor breadth",
"detail": "4 contributors",
"points": 5.4,
"status": "partial",
"details": [
{
"code": "contributors_sampled",
"params": {
"count": 4
}
}
],
"max_points": 13.5
},
{
"key": "openssf_scorecard_contributors",
"name": "OpenSSF Scorecard: Contributors",
"detail": "project has 0 contributing companies or organizations -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
}
]
},
{
"key": "responsiveness",
"band": "moderate",
"name": "Issue & PR responsiveness",
"note": null,
"notes": [],
"value": 65,
"inputs": {
"merged_prs": 40,
"open_issues": 9,
"closed_issues": 21,
"issue_closed_ratio": 0.7,
"closed_unmerged_prs": 8
},
"components": [
{
"key": "issue_resolution",
"name": "Issue resolution",
"detail": "70% of issues closed",
"points": 32.7,
"status": "partial",
"details": [
{
"code": "issues_closed_share",
"params": {
"share": 70
}
}
],
"max_points": 46.75
},
{
"key": "pr_acceptance",
"name": "PR acceptance",
"detail": "40/48 decided PRs merged",
"points": 31.9,
"status": "partial",
"details": [
{
"code": "decided_prs_merged",
"params": {
"merged": 40,
"decided": 48
}
}
],
"max_points": 38.25
},
{
"key": "openssf_scorecard_code_review",
"name": "OpenSSF Scorecard: Code-Review",
"detail": "Found 0/10 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": 46,
"inputs": {
"followers": 17,
"owner_type": "Organization",
"is_verified": null,
"owner_login": "evo-hq",
"public_repos": 6,
"account_age_days": 106
},
"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": "17 followers of evo-hq",
"points": 9,
"status": "partial",
"details": [
{
"code": "owner_followers",
"params": {
"count": 17,
"login": "evo-hq"
}
}
],
"max_points": 25
},
{
"key": "track_record",
"name": "Track record",
"detail": "6 public repos, account ~0 yr old",
"points": 6.7,
"status": "partial",
"details": [
{
"code": "public_repos",
"params": {
"count": 6
}
},
{
"code": "account_age_years",
"params": {
"years": 0
}
}
],
"max_points": 25
}
]
},
{
"key": "package_maintenance",
"band": "excellent",
"name": "Package maintenance",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"packages": [
"@evo-hq/evo-agent",
"evo-hq-agent",
"evo-hq-cli"
],
"ecosystems": "npm, pypi",
"any_deprecated": false,
"min_days_since_publish": 5
},
"components": [
{
"key": "published_resolvable",
"name": "Published & resolvable",
"detail": "3 package(s) on npm, pypi",
"points": 25,
"status": "met",
"details": [
{
"code": "packages_published",
"params": {
"count": 3,
"ecosystems": "npm, pypi"
}
}
],
"max_points": 25
},
{
"key": "publish_recency",
"name": "Publish recency",
"detail": "latest publish 5 days ago",
"points": 35,
"status": "met",
"details": [
{
"code": "publish_recency",
"params": {
"days": 5
}
}
],
"max_points": 35
},
{
"key": "version_history",
"name": "Version history",
"detail": "65 published versions",
"points": 20,
"status": "met",
"details": [
{
"code": "published_versions",
"params": {
"count": 65
}
}
],
"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": 71,
"weight": 0.2,
"metrics": [
{
"key": "engineering_practices",
"band": "moderate",
"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": "2 workflow(s)",
"points": 24,
"status": "met",
"details": [
{
"code": "ci_workflows",
"params": {
"count": 2
}
}
],
"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": "6 out of 6 merged PRs checked by a CI test -- score normalized to 10",
"points": 20,
"status": "met",
"details": [],
"max_points": 20
}
]
},
{
"key": "documentation",
"band": "good",
"name": "Documentation",
"note": null,
"notes": [],
"value": 75,
"inputs": {
"topics": [
"agent-skills",
"autonomous-agents",
"autoresearch",
"claude-code",
"code-optimization",
"codex",
"evolutionary-algorithms",
"llm-agents"
],
"has_wiki": true,
"homepage": "https://evo-hq.com",
"has_readme": true,
"has_docs_dir": false,
"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": 0,
"status": "missed",
"details": [],
"max_points": 25
},
{
"key": "documentation_homepage_site",
"name": "Documentation / homepage site",
"detail": "https://evo-hq.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": "8 topics",
"points": 10,
"status": "met",
"details": [
{
"code": "topics_count",
"params": {
"count": 8
}
}
],
"max_points": 10
},
{
"key": "wiki",
"name": "Wiki",
"detail": null,
"points": 10,
"status": "met",
"details": [],
"max_points": 10
}
]
}
],
"description": "Are baseline engineering and documentation practices in place?"
},
{
"key": "security",
"band": "at_risk",
"name": "Security",
"value": 33,
"weight": 0.16,
"metrics": [
{
"key": "security_posture",
"band": "at_risk",
"name": "Security posture",
"note": null,
"notes": [],
"value": 33,
"inputs": {
"source": "openssf_scorecard",
"checks_evaluated": 18,
"scorecard_version": "v5.5.0",
"checks_inconclusive": 0,
"scorecard_aggregate": 3.3
},
"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": "6 out of 6 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 0/10 approved changesets -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "contributors",
"name": "Contributors",
"detail": "project has 0 contributing companies or organizations -- score normalized to 0",
"points": 0,
"status": "missed",
"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 24 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 detected",
"points": 5,
"status": "met",
"details": [],
"max_points": 5
},
{
"key": "pinned_dependencies",
"name": "Pinned-Dependencies",
"detail": "dependency not pinned by hash detected -- score normalized to 0",
"points": 0,
"status": "missed",
"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": "Project has not signed or included provenance with any releases.",
"points": 0,
"status": "missed",
"details": [],
"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": "32 existing vulnerabilities detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
}
]
},
{
"key": "high_risk_jurisdiction_exposure",
"band": "excellent",
"name": "High-Risk Jurisdiction Exposure",
"note": "Only high-confidence self-published location evidence affects this multiplier. Ambiguous matches are review-only; country evidence is not proof of nationality, citizenship, legal registration, malicious intent, or sanctions status.",
"notes": [
{
"code": "jurisdiction_evidence_limits",
"params": {}
}
],
"value": 100,
"inputs": {
"meaning": "self-published location evidence; not nationality or citizenship",
"red_flag": false,
"exposures": [],
"policy_countries": [
"Russia",
"Iran",
"North Korea"
],
"review_only_matches": 0,
"assessed_self_published_locations": 1
},
"components": [
{
"key": "policy_exposure_multiplier",
"name": "Policy exposure multiplier",
"detail": "no confirmed policy-scope location match",
"points": 100,
"status": "met",
"details": [
{
"code": "jurisdiction_no_match",
"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": "at_risk",
"name": "AI Readiness",
"value": 46,
"weight": 0,
"metrics": [
{
"key": "ai_agent_context",
"band": "at_risk",
"name": "Agent context & guidance",
"note": null,
"notes": [],
"value": 40,
"inputs": {
"has_llms_txt": false,
"legible_history_share": 0.89,
"agent_instruction_files": [],
"agent_instruction_max_bytes": null
},
"components": [
{
"key": "agent_instructions",
"name": "Agent instructions",
"detail": "no CLAUDE.md / AGENTS.md / editor rules",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_agent_instructions",
"params": {}
}
],
"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": "89 of 100 human commits state their intent (structured subject or explanatory body)",
"points": 40,
"status": "met",
"details": [
{
"code": "legible_history",
"params": {
"legible": 89,
"sampled": 100
}
}
],
"max_points": 40
}
]
},
{
"key": "ai_verify_loop",
"band": "at_risk",
"name": "Verify loop (build / test / typecheck)",
"note": null,
"notes": [],
"value": 47,
"inputs": {
"has_nix": false,
"has_tests": true,
"lockfiles": [
"Cargo.lock",
"uv.lock"
],
"has_dockerfile": false,
"typed_language": false,
"bootstrap_files": [],
"has_devcontainer": false,
"has_linter_config": false,
"typecheck_configs": [],
"agent_commit_share": 0.01,
"toolchain_manifests": [
"plugins/evo/bin/evo-hook-drain-rs/Cargo.toml"
],
"dependency_bot_commit_share": 0
},
"components": [
{
"key": "one_command_bootstrap",
"name": "One-command bootstrap",
"detail": "plugins/evo/bin/evo-hook-drain-rs/Cargo.toml (toolchain convention, no task runner)",
"points": 12.6,
"status": "partial",
"details": [
{
"code": "toolchain_convention",
"params": {
"files": "plugins/evo/bin/evo-hook-drain-rs/Cargo.toml"
}
}
],
"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": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 11
},
{
"key": "reproducible_environment",
"name": "Reproducible environment",
"detail": "lockfile",
"points": 10,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "lockfile"
}
}
],
"max_points": 10
},
{
"key": "demonstrated_agent_practice",
"name": "Demonstrated agent practice",
"detail": "1 of the last 100 commits agent-authored or agent-credited",
"points": 2,
"status": "partial",
"details": [
{
"code": "agent_authored_commits",
"params": {
"count": 1,
"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 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
}
]
},
{
"key": "ai_code_legibility",
"band": "moderate",
"name": "Code legibility for models",
"note": null,
"notes": [],
"value": 53,
"inputs": {
"primary_language": "Python",
"largest_source_bytes": 296301,
"source_files_sampled": 187,
"oversized_source_files": 6
},
"components": [
{
"key": "type_checkable_code",
"name": "Type-checkable code",
"detail": "Python without a type-check config",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_typecheck_config_language",
"params": {
"language": "Python"
}
}
],
"max_points": 45
},
{
"key": "manageable_file_sizes",
"name": "Manageable file sizes",
"detail": "6/187 source files over 60KB",
"points": 53.2,
"status": "partial",
"details": [
{
"code": "oversized_source_files",
"params": {
"kb": 60,
"sampled": 187,
"oversized": 6
}
}
],
"max_points": 55
}
]
}
],
"description": "How well is the repo equipped to be developed and maintained with AI coding agents? An independent, experimental badge — weight 0.0, so it is surfaced on its own and does not affect the overall health score."
}
],
"metrics_version": "1.13.0"
},
"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",
"deps.dev does not index npm:@evo-hq/evo-agent@0.8.0; advisories assessed against the repository dependency graph instead"
],
"report_type": "repository",
"generated_at": "2026-07-23T00:34:19.379300Z",
"schema_version": "0.27.0",
"badge_url": "https://raw.githubusercontent.com/inspect-software/badges/main/v1/e/evo-hq/evo.svg",
"full_name": "evo-hq/evo",
"license_state": "standard",
"license_spdx": "Apache-2.0"
}