OSS TanbouOn this page
Overview
PipesHub indexes more than 50 business systems including Slack, Google Drive, GitHub, Microsoft 365, and Notion, then provides permission-aware search and cited answers. The same context layer can be exposed to custom agents through MCP and SDKs.
Features and best fit
Based on official documentation; not hands-on tested · Content checked:
Key features
Index enterprise knowledge through 50+ connectors
Real-time and scheduled indexing bring content from multiple business systems into a common search and AI context layer.
Sources: [2]
Resolve source-level permissions when each query runs
Users and agents retrieve only information they are authorized to see in the source system, with access controls resolved at query time rather than approximated only during indexing.
Sources: [2]
Combine citations, knowledge-graph retrieval, MCP, and SDK access
Block-level citations, graph-backed retrieval, MCP, and Python/TypeScript/Go SDKs let the same knowledge layer serve search UIs and custom agents.
Sources: [2]
Best fit
Fits organizations self-hosting permission-aware RAG across business SaaS
It is relevant when Slack, Drive, and other systems should feed enterprise search, Q&A, and coding agents without discarding existing user permissions.
Sources: [2]
Before adoption
Operate connector credentials and source permissions as security-critical state
Permission-aware retrieval still depends on correct connector scopes and source-side user or group mappings. Credential rotation and permission synchronization remain operational responsibilities.
Sources: [2]
Use HTTPS for remote deployments
The README warns that plain HTTP cloud deployments can cause browser requests to be blocked and recommends TLS termination through Cloudflare, Nginx, Traefik, or an equivalent layer.
Sources: [2]
Review the installer and choose slim/full infrastructure deliberately
The interactive installer generates secrets and selects graph database, message broker, KV store, and image tags. The README also documents downloading and inspecting the script before execution.
Sources: [2]
Official sources
- [1]pipeshub-ai/pipeshub-ai repository(2026-10-01)
- [2]PipesHub README(2026-10-01)
- [3]PipesHub v0.9.1 release(2026-10-01)
- [4]PipesHub Apache-2.0 license(2026-10-01)
Supplemental curator note
PipesHub indexes systems such as Slack, Google Drive, GitHub, Microsoft 365, and Notion, resolves source-system permissions at query time, and exposes the resulting context to search, MCP clients, SDKs, and custom agents.
Try it in 3 steps
- 1
Download the installer
Download the installer to a file instead of piping it directly to the shell so it can be reviewed before execution.
curl -fsSL https://get.pipeshub.com/install -o pipeshub-install.sh - 2
Review the installer
Inspect Docker prerequisites, secret generation, slim/full deployment choices, and graph database, broker, and KV-store configuration.
less pipeshub-install.sh - 3
Set up v0.9.1
Pin the stable release image tag and run the interactive installer. When it finishes, open http://localhost:3000 and configure the first connector.
bash pipeshub-install.sh --version 0.9.1
Growth
Growth trends · Last 30 days
3,804 Stars
Trend data is still being collected.
Development activity
Last 90 days · weekly
- Commits (last 30 days)
- 1,678
- Open PRs
- 154
Development activity is still being collected.
Built with
Categories and tags
GitHub data
GitHub dataView detailed GitHub data
GitHub Topics
- glean
- knowledge-graph
- ollama
- python
- rag
- ai
- enterprise-search
- graphrag
- mcp
- self-hosted
- workplace-ai
- agentic-rag
- Stars
- 3,804
- Forks
- 594
- Watchers
- 18
- Open issues
- 75
- Contributors
- 68
- Owner type
- Organization
- Primary language
- Python
- License
- Apache-2.0
- Repository last updated
- Oct 2, 2026
Related information
Write a related articleShare a guide or use case for this OSS in Markdown. Articles are published after administrator approval.
Explore next
- OpenSERP1,438 Stars
4 shared tag(s) · 1 shared category(s)
combine multiple search services and content extraction behind one API
Go - Dify157,686 Stars
7 shared tag(s) · 2 shared category(s)
design and publish AI workflows, retrieval, and agents on one platform
TypeScript - Khoj37,550 Stars
6 shared tag(s) · 2 shared category(s) · Same language
Combine documents, the web, local/cloud LLMs, agents, and automations in a self-hosted personal AI
Python - Keep12,373 Stars
6 shared tag(s) · 1 shared category(s) · Same language
centralize monitoring alerts and connect correlation, enrichment, and response workflows
Python - Langflow155,453 Stars
5 shared tag(s) · 1 shared category(s) · Same language
make AI workflows visible, then publish them as APIs and MCP tools
Python - n8n206,453 Stars
5 shared tag(s) · 1 shared category(s)
Connect visual workflows, code, AI agents, and human approvals in one automation runtime
TypeScript
Report incorrect information
Tell us if any listing information is incorrect or outdated.