公开记录
软件健康报告模式 0.31.0 · 指标 2.10.0 · 2026-08-04 23:17 UTC

ruvnet / ruflo

🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

TypeScript · JavaScriptMIT★ 67,036 星标⑂ 8,005 复刻始于 2025年6月在 GitHub 上查看 ↗
类型库命令行工具网络服务MCP 服务器网页界面如何判定
#claude-code#swarm#agentic-ai#agentic-framework#agentic-workflow#autonomous-agents#codex#mcp-server#multi-agent#ai-assistant#multi-agent-systems#swarm-intelligence#agents#ai-coding#ai-skills#skills#npm#typescript#ai-agents#harness

ruvnet/ruflo 的健康指数为 100 分中的 90 分，处于「优秀」区间。 其得分最高的类别是Vitality（98/100），最低的是Sustainability & Governance（57/100）。 最近一次更新在今天。 近期的大部分工作由 1 位贡献者完成。

90
总分 / 100
优秀

软件健康指数

指标归入加权类别，统一采用 1–100 量表。总体分先取类别加权平均，再依据公开记录的分布进行校准，使各等级具有百分位含义；当公开证据触发高风险司法辖区政策时，评级会按政策调整，并设置 34（存在风险）的上限。

90
卓越93-100公开记录中的最高层级（约前 5%）；基本满足所有检验标准
优秀80-92各方面均表现强劲；仅有少量不足
良好65-79健康；不足之处有限且可控
中等50-64可接受，但存在明显不足；建议进行审查
薄弱35-49多个领域存在实质性薄弱环节
存在风险20-34存在重大薄弱环节；采用时应保持审慎
危急1-19问题严重（项目被弃置、仅有单一维护者、缺乏基本工程规范）
活力社区与采用可持续性与治理工程质量安全AI 就绪度

评分画像

每条轴代表一个类别。形状比平均值更重要——健康的对象会填满整个图形，而“一峰一谷”式画像意味着某一维度的优势正掩盖另一维度的风险。

加权总体分 76 经校准后在公布的指数量表上为 90（记录校准 2026-08-02）。

所有权

rUv个人账户
10,809 关注者199 个公开仓库始于 2012年11月Not a Bot

该仓库由个人账户拥有。相较于组织支持的项目，单一所有者项目的延续性风险更高。

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
npmclaude-flow指向其他仓库——不计分3.34.081,6107964 天前ruvflowclaudeclaude-codeanthropicaiai-agentsmulti-agentagent-orchestrationswarm-intelligenceswarmmcpmodel-context-protocolllmlarge-language-modelgptchatgptautomationworkfloworchestrationclideveloper-toolsdevtoolscoding-assistantcode-generationenterprisevector-databaseembeddingsmachine-learningneural-networkhive-minddistributed-systemsconsensusself-learning
npmruflo指向其他仓库——不计分3.34.0310,7693604 天前rufloclaude-flowclaudeclaude-codeanthropicaiai-agentsmulti-agentagent-orchestrationswarm-intelligenceswarmmcpmodel-context-protocolclideveloper-toolsenterpriseself-learning
npmruflo-graph-intelligence0.1.0-alpha.175177 天前ruflograph-intelligencepageranksublinearcomplexity-awarepersonalized-pagerankagent-substratemcpclaude-flow

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？

98卓越 · 占总体的 21%

开发活跃度

96卓越
评分方式
36/36推送新近度 — 最近一次推送于 0 天前
32.5/36提交节奏 — 52 周中有 47 周有提交
18/18提交量 — 最近一年 6,535 次提交
10/10OpenSSF Scorecard：Maintained — 30 commit(s) and 9 issue activity found in the last 90 days -- score normalized to 10
所用输入
commits_last_year6,535
human_commit_share1
days_since_last_push0
active_weeks_last_year47

发布纪律

100卓越
评分方式
27/27有发布版本 — 已发布 100 个发布版本
36/36发布时效 — 最近一次发布版本于 4 天前
27/27发布节奏 — 约每 0.2 天发布一次
0/10OpenSSF Scorecard：Signed-Releases — 无数据
所用输入
releases_count100
latest_release_tagv3.34.0
releases_from_tags否
days_since_latest_release4
mean_days_between_releases0.2
已排除计分（无数据或不适用）：OpenSSF Scorecard：Signed-Releases。 其余权重已重新归一化。

社区与采用

项目是否拥有用户、下载量与关注度，并具备欢迎贡献者参与的配置？

72良好 · 占总体的 17%

流行度与采用

100卓越
评分方式
60/60星标 — 67,036 个星标
25/25复刻 — 8,005 个复刻
14.6/15关注者 — 430 位关注者
所用输入
forks8,005
stars67,036
watchers430
growth_stateunverified
growth_factor_pct100
growth_unverified_reasonno_history

社区健康

70良好
评分方式
22.5/22.5README
22.5/22.5许可证 — 可识别的许可证（MIT）
18/18CONTRIBUTING 指南
0/13.5行为准则
0/7.2议题模板
0/6.3PR 模板
所用输入
has_readme是
has_license是
readme_badges11
has_contributing是
has_issue_template否
has_code_of_conduct否
readme_badge_servicesshields.io
has_pull_request_template否

生态采用（下载量）

31存在风险
评分方式
25.1/80月度下载量 — npm 合计每月 75 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
packagesruflo-graph-intelligence
dependents—
ecosystemsnpm
total_downloads—
monthly_downloads75
unverified_packages_excluded—
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？

57中等 · 占总体的 23%

维护者韧性（巴士系数）

33存在风险
评分方式
9/54巴士系数 — 1 位贡献者贡献了半数提交
0.3/22.5提交分布 — 头号贡献者编写了 98% 的提交
13.5/13.5贡献者广度 — 31 位贡献者
10/10OpenSSF Scorecard：Contributors — project has 3 contributing companies or organizations -- score normalized to 10
所用输入
bus_factor1
contributors_sampled31
top_contributor_share0.985

议题与 PR 响应能力

45薄弱
评分方式
27.6/42议题解决 — 66% 的议题已关闭
16/30PR 接受 — 已裁定的 PR 中 526/986 已合并
0/13Newcomer PR acceptance — 30 天内首次贡献者的 PR 已合并 0/2
1.5/15OpenSSF Scorecard：Code-Review — Found 4/30 approved changesets -- score normalized to 1
所用输入
merged_prs526
open_issues537
closed_issues1,030
prs_merged_7d7
prs_decided_7d58
prs_merged_30d7
prs_decided_30d58
issue_closed_ratio0.657
closed_unmerged_prs460
first_time_authors_30d2
first_time_prs_merged_30d0
first_time_prs_decided_30d2

所有权与托管责任

75良好
评分方式
10/30所有权背书 — 个人（用户）账户
0/20已验证域名 — 不适用于个人账户
25/25所有者影响力 — ruvnet 有 10,809 位关注者
25/25既往记录 — 199 个公开仓库，账户约 13 年
所用输入
followers10,809
owner_typeUser
is_verified—
owner_loginruvnet
public_repos199
account_age_days4,995
已排除计分（无数据或不适用）：已验证域名。 其余权重已重新归一化。

软件包维护

84优秀
评分方式
25/25已发布且可解析 — npm 上有 1 个软件包
35/35发布时效 — 最近一次发布于 77 天前
4/20版本历史 — 1 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
packagesruflo-graph-intelligence
ecosystemsnpm
any_deprecated否
min_days_since_publish77

工程质量

基础的工程与文档实践是否到位？

90优秀 · 占总体的 19%

工程实践

84优秀
评分方式
24/24CI 工作流 — 28 个工作流
24/24存在测试
16/16Linter 配置 — .eslintrc.cjs, .eslintrc.json, eslint.config.js
0/9.6Pre-commit 钩子
0/6.4.editorconfig
20/20OpenSSF Scorecard：CI-Tests — 26 out of 26 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是
has_precommit_config否

文档

100卓越
评分方式
30/30README
25/25文档目录
15/15文档 / 主页站点 — https://Cognitum.One
10/10仓库描述
10/10主题标签 — 20 个主题标签
10/10Wiki
所用输入
topicsclaude-code, swarm, agentic-ai, agentic-framework, agentic-workflow, autonomous-agents, codex, mcp-server, multi-agent, ai-assistant, multi-agent-systems, swarm-intelligence, agents, ai-coding, ai-skills, skills, npm, typescript, ai-agents, harness
has_wiki是
homepagehttps://Cognitum.One
docs_sitehttps://Cognitum.One
has_readme是
has_docs_dir是
has_description是

安全

可见的安全与供应链实践是否稳固，且不存在未解决的高风险司法辖区暴露？

58中等 · 占总体的 16%

安全态势

56中等
评分方式
6/7.5Binary-Artifacts — binaries present in source code
0/7.5Branch-Protection — branch protection not enabled on development/release branches
2.5/2.5CI-Tests — 26 out of 26 merged PRs checked by a CI test -- score normalized to 10
0/2.5CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected
0.8/7.5Code-Review — Found 4/30 approved changesets -- score normalized to 1
2.5/2.5Contributors — project has 3 contributing companies or organizations -- score normalized to 10
10/10Dangerous-Workflow — no dangerous workflow patterns detected
7.5/7.5Dependency-Update-Tool — update tool detected
0/5Fuzzing — project is not fuzzed
2.5/2.5许可证 — license file detected
7.5/7.5Maintained — 30 commit(s) and 9 issue activity found in the last 90 days -- score normalized to 10
5/5Packaging — packaging workflow detected
0.5/5Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 1
5/5SAST — SAST tool is run on all commits
5/5Security-Policy — security policy file detected
0/7.5Signed-Releases — 无数据
0/7.5Token-Permissions — detected GitHub workflow tokens with excessive permissions
0/7.5Vulnerabilities — 258 existing vulnerabilities detected
所用输入
sourceopenssf_scorecard
checks_evaluated17
scorecard_versionv5.5.0
checks_inconclusive1
scorecard_aggregate5.6
已排除计分（无数据或不适用）：Signed-Releases。 其余权重已重新归一化。

依赖安全公告

65良好
评分方式
35/35直接依赖不含已知公告 — 没有直接依赖携带已知公告
2.3/25间接依赖不含已知公告 — 9 个受影响：protobufjs 6.11.6 (critical 9.8), @opentelemetry/propagator-jaeger 2.7.1 (high 7.5), adm-zip 0.5.18 (high 7.5)，另有 6 个
27.9/40没有长期未处理的公告 — 2 个携带公告的软件包超过 90 天未处理；最早一条发布于 202 天前
所用输入
sourceosv
advisories30
affected_packages9
assessed_packages677
unassessed_packages0
affected_by_severitycritical 1, high 5, moderate 3
direct_affected_packages0
比对的是 npm:ruflo@3.34.0 的运行时依赖闭包——安装已发布的软件包时真正被拉取进来的内容——共 677 个软件包。 未对可达性进行分析。

AI 就绪度

该仓库在多大程度上具备与 AI 编码代理协同开发与维护的条件？权重刻意设小（4%）：代理工具链是一项真实的维护信号，但完全不具备的仓库仍可达到 100/100。

81优秀 · 占总体的 4%

AI 代理上下文与指引

85优秀
评分方式
45/45代理指令 — .claude/agents/goal/agent.md, .claude/agents/reasoning/agent.md, .claude/commands/monitoring/agents.md, AGENTS.md, CLAUDE.md, ruflo/src/ruvocal/CLAUDE.md, v3/@claude-flow/cli/.claude/agents/goal/agent.md, v3/@claude-flow/cli/.claude/commands/monitoring/agents.md, v3/@claude-flow/cli/CLAUDE.md, v3/@claude-flow/codex/AGENTS.md, v3/@claude-flow/mcp/.claude/agents/goal/agent.md, v3/@claude-flow/mcp/.claude/commands/monitoring/agents.md, v3/@claude-flow/mcp/CLAUDE.md, v3/CLAUDE.md
0/15机器可读文档（llms.txt）
40/40可读的提交历史 — 100 次人类提交中有 99 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
llms_txt_url—
legible_history_share0.99
agent_instruction_files.claude/agents/goal/agent.md, .claude/agents/reasoning/agent.md, .claude/commands/monitoring/agents.md, AGENTS.md, CLAUDE.md, ruflo/src/ruvocal/CLAUDE.md, v3/@claude-flow/cli/.claude/agents/goal/agent.md, v3/@claude-flow/cli/.claude/commands/monitoring/agents.md, v3/@claude-flow/cli/CLAUDE.md, v3/@claude-flow/codex/AGENTS.md, v3/@claude-flow/mcp/.claude/agents/goal/agent.md, v3/@claude-flow/mcp/.claude/commands/monitoring/agents.md, v3/@claude-flow/mcp/CLAUDE.md, v3/CLAUDE.md
agent_instruction_max_bytes66,757

验证循环（构建 / 测试 / 类型检查）

80优秀
评分方式
18/18一条命令的引导启动 — tests/docker-regression/Makefile
22/22自动化测试
11/11Lint / 格式化配置 — .eslintrc.cjs, .eslintrc.json, eslint.config.js
11/11静态类型检查 — plugins/ruflo-arena/tsconfig.json, plugins/ruflo-graph-intelligence/tsconfig.json, ruflo/src/ruvocal/tsconfig.json, tsconfig.json, v3/@claude-flow/aidefence/tsconfig.json, v3/@claude-flow/browser/tsconfig.json, v3/@claude-flow/claims/tsconfig.json, v3/@claude-flow/cli-core/tsconfig.json, v3/@claude-flow/cli/tsconfig.json, v3/@claude-flow/codex/tsconfig.json, v3/@claude-flow/deployment/tsconfig.json, v3/@claude-flow/embeddings/tsconfig.json, v3/@claude-flow/guidance/tsconfig.json, v3/@claude-flow/hooks/tsconfig.json, v3/@claude-flow/integration/tsconfig.json, v3/@claude-flow/mcp/tsconfig.json, v3/@claude-flow/memory/tsconfig.json, v3/@claude-flow/neural/tsconfig.json, v3/@claude-flow/performance/tsconfig.json, v3/@claude-flow/plugin-agent-federation/tsconfig.json, v3/@claude-flow/plugin-iot-cognitum/tsconfig.json, v3/@claude-flow/plugins/tsconfig.json, v3/@claude-flow/providers/tsconfig.json, v3/@claude-flow/security/tsconfig.json, v3/@claude-flow/shared/tsconfig.json, v3/@claude-flow/swarm/tsconfig.json, v3/@claude-flow/testing/tsconfig.json, v3/goal_ui/tsconfig.json, v3/plugins/agentic-qe/tsconfig.json, v3/plugins/code-intelligence/tsconfig.json, v3/plugins/cognitive-kernel/tsconfig.json, v3/plugins/financial-risk/tsconfig.json, v3/plugins/gastown-bridge/tsconfig.json, v3/plugins/healthcare-clinical/tsconfig.json, v3/plugins/hyperbolic-reasoning/tsconfig.json, v3/plugins/legal-contracts/tsconfig.json, v3/plugins/neural-coordination/tsconfig.json, v3/plugins/perf-optimizer/tsconfig.json, v3/plugins/prime-radiant/tsconfig.json, v3/plugins/quantum-optimizer/tsconfig.json, v3/plugins/ruvector-upstream/tsconfig.json, v3/plugins/teammate-plugin/tsconfig.json, v3/plugins/test-intelligence/tsconfig.json, v3/tsconfig.json
10/10可复现环境 — devcontainer, Dockerfile, 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
5/8自动化维护 — 已配置依赖自动化，但在抽样提交中未观察到
1/10OpenSSF Scorecard：Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 1
所用输入
has_nix否
has_tests是
lockfilesCargo.lock, package-lock.json, pnpm-lock.yaml
has_dockerfile是
typed_language是
bootstrap_filestests/docker-regression/Makefile
has_devcontainer是
has_linter_config是
typecheck_configsplugins/ruflo-arena/tsconfig.json, plugins/ruflo-graph-intelligence/tsconfig.json, ruflo/src/ruvocal/tsconfig.json, tsconfig.json, v3/@claude-flow/aidefence/tsconfig.json, v3/@claude-flow/browser/tsconfig.json, v3/@claude-flow/claims/tsconfig.json, v3/@claude-flow/cli-core/tsconfig.json, v3/@claude-flow/cli/tsconfig.json, v3/@claude-flow/codex/tsconfig.json, v3/@claude-flow/deployment/tsconfig.json, v3/@claude-flow/embeddings/tsconfig.json, v3/@claude-flow/guidance/tsconfig.json, v3/@claude-flow/hooks/tsconfig.json, v3/@claude-flow/integration/tsconfig.json, v3/@claude-flow/mcp/tsconfig.json, v3/@claude-flow/memory/tsconfig.json, v3/@claude-flow/neural/tsconfig.json, v3/@claude-flow/performance/tsconfig.json, v3/@claude-flow/plugin-agent-federation/tsconfig.json, v3/@claude-flow/plugin-iot-cognitum/tsconfig.json, v3/@claude-flow/plugins/tsconfig.json, v3/@claude-flow/providers/tsconfig.json, v3/@claude-flow/security/tsconfig.json, v3/@claude-flow/shared/tsconfig.json, v3/@claude-flow/swarm/tsconfig.json, v3/@claude-flow/testing/tsconfig.json, v3/goal_ui/tsconfig.json, v3/plugins/agentic-qe/tsconfig.json, v3/plugins/code-intelligence/tsconfig.json, v3/plugins/cognitive-kernel/tsconfig.json, v3/plugins/financial-risk/tsconfig.json, v3/plugins/gastown-bridge/tsconfig.json, v3/plugins/healthcare-clinical/tsconfig.json, v3/plugins/hyperbolic-reasoning/tsconfig.json, v3/plugins/legal-contracts/tsconfig.json, v3/plugins/neural-coordination/tsconfig.json, v3/plugins/perf-optimizer/tsconfig.json, v3/plugins/prime-radiant/tsconfig.json, v3/plugins/quantum-optimizer/tsconfig.json, v3/plugins/ruvector-upstream/tsconfig.json, v3/plugins/teammate-plugin/tsconfig.json, v3/plugins/test-intelligence/tsconfig.json, v3/tsconfig.json
agent_commit_share0.01
toolchain_manifestsCargo.toml, v3/@claude-flow/guidance/wasm-kernel/Cargo.toml, v3/crates/ruflo-agntcy/Cargo.toml, v3/crates/ruflo-federation-peer/Cargo.toml, v3/plugins/gastown-bridge/Cargo.toml, v3/plugins/gastown-bridge/wasm/Cargo.toml, v3/plugins/gastown-bridge/wasm/gastown-formula-wasm/Cargo.toml, v3/plugins/gastown-bridge/wasm/ruvector-gnn-wasm/Cargo.toml, v3/plugins/gastown-bridge/wasm/shared/Cargo.toml
dependency_bot_commit_share0

面向模型的代码可读性

99卓越
评分方式
45/45可类型检查的代码 — TypeScript（静态类型）
54.3/55可控的文件大小 — 采样的 2,556 个源文件中有 31 个超过 60KB
所用输入
primary_languageTypeScript
largest_source_bytes238,864
source_files_sampled2,556
oversized_source_files31

机器可读接口

60中等
评分方式
0/40API 模式（OpenAPI/GraphQL/proto）
20/20MCP 服务器
40/40可运行示例 — examples
所用输入
example_dirsexamples
has_mcp_signal是
api_schema_files—
interfaces_expected_ofnetwork-service

关键数据

67,036GitHub 星标
31贡献者
6,535最近 12 个月提交数
0距最近推送天数
100发布版本数
1巴士系数（bus factor）
537开放议题
crates.io, npm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
  • npm package 'claude-flow' points at a different repository (https://github.com/ruvnet/claude-flow); excluded from ecosystem scoring
  • npm package 'ruflo' points at a different repository (https://github.com/ruvnet/claude-flow); excluded from ecosystem scoring
  • Could not fetch npm package 'ruflo-arena' from its registry
  • GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository

更多细节

Star 与 Fork 历史 0 ★ / 8,005 ⇿
0Star
8,005Fork
72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。

仅显示最近的历史——该仓库超出采集窗口，因此未采集最早的历史记录。

7,0007,2007,4007,6007,8008,0008,2008,005382026-062026-072026-08
主版本 0次版本 18修订 53
OpenSSF Scorecard 5.6 / 10
5.6综合

来自开源项目 OpenSSF Scorecard 的独立、工具无关的安全评估。每项检查奖励的是安全实践本身，而非特定供应商的工具。Scorecard 无法判定的检查项标记为 不适用，并从安全评分中剔除（绝不按零分计）。Scorecard v5.5.0 · 2026-08-04 23:16 UTC

8Binary-Artifactsbinaries present in source code
0Branch-Protectionbranch protection not enabled on development/release branches
10CI-Tests26 out of 26 merged PRs checked by a CI test -- score normalized to 10
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
1Code-ReviewFound 4/30 approved changesets -- score normalized to 1
10Contributorsproject has 3 contributing companies or organizations -- score normalized to 10
10Dangerous-Workflowno dangerous workflow patterns detected
10Dependency-Update-Toolupdate tool detected
0Fuzzingproject is not fuzzed
10Licenselicense file detected
10Maintained30 commit(s) and 9 issue activity found in the last 90 days -- score normalized to 10
10Packagingpackaging workflow detected
1Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 1
10SASTSAST tool is run on all commits
10Security-Policysecurity policy file detected
不适用Signed-Releasesno releases found
0Token-Permissionsdetected GitHub workflow tokens with excessive permissions
0Vulnerabilities258 existing vulnerabilities detected
直接依赖 76
注册表软件包版本约束清单文件
npm@claude-flow/cli-core3.7.0-alpha.5package.json
npm@claude-flow/codex3.0.3package.json
npm@claude-flow/mcp3.0.0-alpha.9package.json
npm@claude-flow/neural3.0.0-alpha.9package.json
npm@claude-flow/plugin-agent-federation1.0.0-alpha.18package.json
npm@claude-flow/security3.0.0-alpha.14package.json
npm@claude-flow/shared3.0.0-alpha.8package.json
npm@iarna/toml^2.2.5package.json
npm@noble/ed255192.3.0package.json
npm@ruvector/rabitq-wasm0.1.0package.json
npmbcryptjs^3.0.3package.json
npmchalk^5.3.0package.json
npmcommander^12.0.0package.json
npmfs-extra^11.2.0package.json
npminquirer^9.2.0package.json
npmsemver7.7.3package.json
npmtoml^3.0.0package.json
npmws>=8.21.0package.json
npmyaml^2.8.0package.json
npmzod3.25.76package.json
npm@claude-flow/cli^3.33.0ruflo/package.json
npmsemantic-release25.0.2v3/package.json
npmzod^3.22.4plugins/ruflo-arena/package.json
npmsublinear-time-solver^1.7.0plugins/ruflo-graph-intelligence/package.json
npmzod^3.22.4plugins/ruflo-graph-intelligence/package.json
npm@hookform/resolvers^3.10.0v3/goal_ui/package.json
npm@radix-ui/react-accordion^1.2.11v3/goal_ui/package.json
npm@radix-ui/react-alert-dialog^1.1.14v3/goal_ui/package.json
npm@radix-ui/react-aspect-ratio^1.1.7v3/goal_ui/package.json
npm@radix-ui/react-avatar^1.1.10v3/goal_ui/package.json
npm@radix-ui/react-checkbox^1.3.2v3/goal_ui/package.json
npm@radix-ui/react-collapsible^1.1.11v3/goal_ui/package.json
npm@radix-ui/react-context-menu^2.2.15v3/goal_ui/package.json
npm@radix-ui/react-dialog^1.1.14v3/goal_ui/package.json
npm@radix-ui/react-dropdown-menu^2.1.15v3/goal_ui/package.json
npm@radix-ui/react-hover-card^1.1.14v3/goal_ui/package.json
npm@radix-ui/react-label^2.1.7v3/goal_ui/package.json
npm@radix-ui/react-menubar^1.1.15v3/goal_ui/package.json
npm@radix-ui/react-navigation-menu^1.2.13v3/goal_ui/package.json
npm@radix-ui/react-popover^1.1.14v3/goal_ui/package.json
npm@radix-ui/react-progress^1.1.7v3/goal_ui/package.json
npm@radix-ui/react-radio-group^1.3.7v3/goal_ui/package.json
npm@radix-ui/react-scroll-area^1.2.9v3/goal_ui/package.json
npm@radix-ui/react-select^2.2.5v3/goal_ui/package.json
npm@radix-ui/react-separator^1.1.7v3/goal_ui/package.json
npm@radix-ui/react-slider^1.3.5v3/goal_ui/package.json
npm@radix-ui/react-slot^1.2.3v3/goal_ui/package.json
npm@radix-ui/react-switch^1.2.5v3/goal_ui/package.json
npm@radix-ui/react-tabs^1.1.12v3/goal_ui/package.json
npm@radix-ui/react-toast^1.2.14v3/goal_ui/package.json
npm@radix-ui/react-toggle^1.1.9v3/goal_ui/package.json
npm@radix-ui/react-toggle-group^1.1.10v3/goal_ui/package.json
npm@radix-ui/react-tooltip^1.2.7v3/goal_ui/package.json
npm@supabase/supabase-js^2.74.0v3/goal_ui/package.json
npm@tanstack/react-query^5.83.0v3/goal_ui/package.json
npmclass-variance-authority^0.7.1v3/goal_ui/package.json
npmclsx^2.1.1v3/goal_ui/package.json
npmcmdk^1.1.1v3/goal_ui/package.json
npmdate-fns^3.6.0v3/goal_ui/package.json
npmembla-carousel-react^8.6.0v3/goal_ui/package.json
npminput-otp^1.4.2v3/goal_ui/package.json
npmlucide-react^0.462.0v3/goal_ui/package.json
npmnext-themes^0.3.0v3/goal_ui/package.json
npmreact^18.3.1v3/goal_ui/package.json
npmreact-day-picker^8.10.1v3/goal_ui/package.json
npmreact-dom^18.3.1v3/goal_ui/package.json
npmreact-hook-form^7.61.1v3/goal_ui/package.json
npmreact-resizable-panels^2.1.9v3/goal_ui/package.json
npmreact-router-dom^6.30.1v3/goal_ui/package.json
npmreactflow^11.11.4v3/goal_ui/package.json
npmrecharts^2.15.4v3/goal_ui/package.json
npmsonner^1.7.4v3/goal_ui/package.json
npmtailwind-merge^2.6.0v3/goal_ui/package.json
npmtailwindcss-animate^1.0.7v3/goal_ui/package.json
npmvaul^0.9.9v3/goal_ui/package.json
npmzod^3.25.76v3/goal_ui/package.json
全部依赖 未采集

本报告未能采集到解析后的依赖集合：GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository

依赖安全公告 9

安装 npm:ruflo@3.34.0 会引入 677 个包（直接与传递）：其中 9 个存在已知公告，0 个为直接依赖。

软件包版本关系严重程度公告数修复版本
protobufjs6.11.6间接严重118.6.0
@opentelemetry/propagator-jaeger2.7.1间接高12.9.0
adm-zip0.5.18间接高10.6.0
sharp0.32.6间接高10.35.0
sharp0.34.5间接高10.35.0
undici5.29.0间接高128.9.0
@opentelemetry/core1.30.1间接中12.8.0
@opentelemetry/core2.7.1间接中12.8.0
hono4.12.33间接中14.12.34

公告表示依赖图中记录的版本落入某条公告的受影响范围。可达性未经分析，且依赖图包含开发与测试的版本固定——某项发现可能只涉及工具链而非交付的软件。

原始 JSON 报告 机器可读

反馈

发现这份报告有不准确之处，或有想法要分享？错误的测量、未识别的工具、建议、疑问——都欢迎提出。每条消息都会被阅读并得到回复。

登录过程中消息不会丢失。

相关记录

与 ruvnet/ruflo 共享目录标签或生态系统的已检测仓库。 并排阅读 →

97strands-agents/harness-sdkBuild an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.卓越98awslabs/cli-agent-orchestratorMulti-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions卓越98bytedance/deer-flowAn open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.卓越98ModelEngine-Group/nexentNexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skills, memory, and orchestration with built-in constraints, feedback loops, and control planes.卓越100deepset-ai/haystackOpen-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.卓越98ComposioHQ/composioComposio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.卓越

评分是信号，而非担保。 评分反映的是 GitHub 上公开可见的实践——不是代码审计，也不是安全保证。

缺失数据将被剔除并重新归一化权重，绝不按零分计。方法论已版本化并公开：指标 v2.10.0、模式 v0.31.0—— 完整方法论 · 指标知识库.

单项结果在整体记录中的位置： 汇总统计 — npm.