Skill 与 AgentSKILLS & AGENTS· MCP-SERVER
pipeshub-ai/pipeshub-ai
把公司散落在 Slack、网盘、Jira 的资料,变成 AI 能搜索和引用的工作区。PipesHub is an open-source context layer that gives AI agents a permission-aware, searchable view of Slack, Drive, Jira, GitHub and Microsoft 365.
根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
集中检索散落在各处的公司资料
查看带内部资料出处的搜索结果
只显示你有权查看的公司信息
启动本地知识搜索页面
查找聊天、文档、工单里的历史内容
Search Slack, Drive, Jira, GitHub and Microsoft 365.
Grep company knowledge and jump to exact records.
Find answers with citations you can check.
Search while keeping existing permissions on files and messages.
Run it yourself with Docker Compose.
上手GET STARTED
curl -fsSL https://get.pipeshub.com/install | bash选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
存在风险Risk found
静态扫描STATIC SCAN
01执行远程脚本Runs a remote scriptreadme
> curl -fsSL https://get.pipeshub.com/install | bash
静态扫描发现高风险项:README 中的一键安装命令会直接从远程下载脚本并交给 bash 执行(curl -fsSL https://get.pipeshub.com/install | bash),存在供应链风险。建议先下载脚本逐行审阅后再运行,或改用 git clone 后手动执行安装。The scan flagged the install command as high risk because it downloads a remote script and runs it with bash. You can review the script first by saving it to a file and reading it before executing.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+8.7%+8.7%
3.8k → 4.1k stars · 50 个快照3.8k → 4.1k stars · 50 snapshots
状态STATUS
持续活跃Active
质量 B+Quality B+
近 7 天有 351 次提交,开发节奏非常活跃。Open source under Apache-2.0, so teams can run it themselves.
热度分MOMENTUM
自 2026-10-09 起追踪 9 天。热度分从 36.7 到 64.2,净变化 +27.5。目前处于追踪以来的最高水平。上榜 1 天,记录里排到过第 9 名。Tracked 9 days since 2026-10-09. Momentum went from 36.7 to 64.2, a net change of +27.5. It is currently at its highest tracked level. On the published ranking 1 day, and published rank in this record reached 9.
折线从左到右按追踪日期排列,表示热度分。The line reads left to right by tracked date and shows momentum.
数据说明:走势来自 Signal Garden 每日追踪的热度分;只有标注「上榜」的日期出现在公开每日榜单上。Data note: the trend uses Signal Garden’s daily tracked momentum scores; only dates marked “Ranked” appeared on the public daily list.
同类RELATED
下面这些项目与它有相同的语言、分类或仓库主题。热度分是各自最近一次上榜时的分数。These projects share a language, category, or repository topic. Momentum is the score from each project's latest ranking appearance.
相同主题 ai-agents、context-engineering · 热度分 55.7 · 2026-10-13shared topic ai-agents, context-engineering · momentum 55.7 · 2026-10-13
相同主题 ai-agents、claude-code · 热度分 59.8 · 2026-10-26shared topic ai-agents, claude-code · momentum 59.8 · 2026-10-26
相同主题 ai-agents、claude-code · 热度分 70.2 · 2026-11-16shared topic ai-agents, claude-code · momentum 70.2 · 2026-11-16
相同主题 ai-agents、context-engineering · 热度分 56.9 · 2026-10-06shared topic ai-agents, context-engineering · momentum 56.9 · 2026-10-06
相同主题 claude-code、mcp · 热度分 62.1 · 2026-11-03shared topic claude-code, mcp · momentum 62.1 · 2026-11-03
相同主题 self-hosted · 热度分 64.4 · 2026-10-19shared topic self-hosted · momentum 64.4 · 2026-10-19
读者WHO IT'S FOR
用 Python 做 knowledge-graph、ollama、rag 的团队会用它处理这件事:An open-source context layer for AI agents and an enterprise search platform。用途要落在 knowledge-graph 而不是站内同类 WrenAI 更偏向的 bigquery 时优先选它,仓库许可为 Apache-2.0,热度走势为上升。Teams using Python on knowledge-graph, ollama, rag use it for this problem: An open-source context layer for AI agents and an enterprise search platform. Prefer it over the in-site peer WrenAI when the use stays on knowledge-graph rather than bigquery, the repository license is Apache-2.0, and the momentum shape is rising.
{
"agents": [
{
"agent": "claude-code",
"evidence": "tree: .claude/"
},
{
"agent": "gemini-cli",
"evidence": "tree: .gemini/"
}
],
"apiKey": "ent: `PIPESHUB_MCP_URL=... PIPESHUB_MCP_TOKEN=... omnigent run examples/pipeshub/`. 3",
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 0,
"dev-tools": 0,
"indie-web": 0,
"skill-agent": 12,
"productivity": 7
},
"primary": "skill-agent",
"secondary": "mcp-server"
},
"localRuntime": "oyment Guide PipesHub can be run locally or deployed on any server using Docker",
"skillMdTotal": 11,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 6,
"agent": 3,
"media": 0,
"design": 0,
"browser": 0,
"devtool": 0,
"security": 0,
"marketing": 0,
"productivity": 4
},
"classification": [
{
"signal": "11 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "skills/ directory with 3 markdown files",
"weight": 0.75
},
{
"signal": "MCP topic + README",
"weight": 0.6
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
".claude/skills/add-connector/SKILL.md",
".claude/skills/pr-review/SKILL.md",
".claude/skills/release-changelog/SKILL.md",
"backend/python/app/agents/agent_loop/skills/builtin_packs/data-analysis/SKILL.md",
"backend/python/app/agents/agent_loop/skills/builtin_packs/data-visualization/SKILL.md",
"backend/python/app/agents/agent_loop/skills/builtin_packs/docx/SKILL.md",
"backend/python/app/agents/agent_loop/skills/builtin_packs/file-conversion/SKILL.md",
"backend/python/app/agents/agent_loop/skills/builtin_packs/office-utils/SKILL.md",
"backend/python/app/agents/agent_loop/skills/builtin_packs/pdf/SKILL.md",
"backend/python/app/agents/agent_loop/skills/builtin_packs/pptx/SKILL.md",
"backend/python/app/agents/agent_loop/skills/builtin_packs/xlsx/SKILL.md"
],
"skillMdFetched": 11
}