by pipeshub-ai
The open-source context layer for AI agents and enterprise AI search. Permission-aware search and cited answers across 30+ sources, including Slack, Drive, Jira, GitHub and Microsoft 365, for people and agents through MCP, SDKs and built-in agents. Self-hosted or Cloud.
# Add to your Claude Code skills
git clone https://github.com/pipeshub-ai/pipeshub-aiGuides for using ai agents skills like pipeshub-ai.
Last scanned: 10/2/2026
{
"issues": [
{
"file": "README.md",
"line": 54,
"type": "remote-install",
"message": "Install command (remote install script piped to a shell — review the source before running): \"curl -fsSL https://get.pipeshub.com/install | bash\"",
"severity": "low"
}
],
"status": "PASSED",
"scannedAt": "2026-10-02T10:19:58.662Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how pipeshub-ai compares with popular alternatives.
pipeshub-ai is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by pipeshub-ai. The open-source context layer for AI agents and enterprise AI search. Permission-aware search and cited answers across 30+ sources, including Slack, Drive, Jira, GitHub and Microsoft 365, for people and agents through MCP, SDKs and built-in agents. Self-hosted or Cloud. It has 4,124 GitHub stars.
Yes. pipeshub-ai passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/pipeshub-ai/pipeshub-ai" and add it to your Claude Code skills directory (see the Installation section above).
pipeshub-ai is primarily written in Python. It is open-source under pipeshub-ai on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh pipeshub-ai against similar tools.
No comments yet. Be the first to share your thoughts!
From $49 · 30 days · terms & refunds
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Automated security scan — not a certification.
Translations: Français · Deutsch · 简体中文 · 日本語 · Русский · עברית · 한국어 · Español · Português · Türkçe · Tiếng Việt · Italiano · Čeština
PipesHub is an open-source platform for connecting AI applications to the knowledge stored across your company's business systems.
Connect Slack, Google Drive, GitHub, Microsoft 365, Notion and 50+ other systems. Search across them and get answers with citations, filtered by what each person is allowed to see — or give that same context to your own agents, workflows and MCP clients.
[!TIP] Deploy with a single command:
curl -fsSL https://get.pipeshub.com/install | bash
PipesHub builds a unified context layer across documents, conversations, structured data, wikis, tickets and code. Connectors sync each source along with its permissions. The indexing pipeline parses, chunks and embeds the content, and links records, people and entities in a knowledge graph.
Questions are answered by an agent loop, not a single retrieve-then-generate pass. The agent plans, calls tools, reads the results and keeps going until it has the evidence:
Every tool call is filtered by the asking user's permissions, and every answer cites the blocks it came from.
How PipesHub performs, and how each test was run.
| Benchmark | What it measures | Result | Details |
|---|---|---|---|
| EnterpriseRAG-Bench (independent, run by Onyx) | 500 questions over 500,000+ company documents | #1 of 39 systems (93.24). OpenAI File Search 61.03, Amazon Q 48.96, Azure AI Search 48.42, Vertex AI Search 41.87 | Leaderboard |
| Google FRAMES (824 questions) | Answers that need facts from several documents | 92.7%, against 78.9% for the best of 18 standard RAG pipelines | Write-up |
| Company index vs. per-app MCP connectors | The same Claude agent on 100 work questions, searching each app through its own connector or through PipesHub | Facts found: Haiku 55% → 80%, Sonnet 65% → 89%, Opus 85% → 92%; 27–45% faster and 27–32% cheaper per answer | Write-up |
| Code graph accuracy (vs. Graphify, codebase-memory-mcp, CodeGraphContext) | How accurately each tool maps relationships in code across 9 repositories | Highest accuracy (F1 score) on 8 of 9 repositories | Write-up |
Leaderboard standing as of 3 November 2026 (leaderboard data at that date). The FRAMES, connector and code-graph tests were run by the PipesHub team. The connector test used questions about our own internal work; we will publish a version on public data.
Don't just use PipesHub — build on it.
Give Claude Code, Cursor, or Codex secure access to your company's knowledge → About ten minutes once PipesHub is running with data indexed. Mint a Personal Access Token (no admin needed), connect your assistant (one command for Claude Code, one config file for Cursor or Codex), and ask "why was the retry logic in the billing worker changed?" — it answers from the incident postmortem, the pull request, the chat thread, and the design doc, each cited, and only if you're allowed to see them.
Want the same retrieval inside your own code, or behind a search box for your team? The SDK starter and search example cover both. Built something? Show us.
Answers you can trust
Connected to your systems