#1919th of 41 in RAG, knowledge and search
PipesHub
Permission-aware search and cited answers across Slack, Drive, GitHub and 50+ systems
- Stars
- 3.8k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
2,680 on 26 Mar 20263,846 on 22 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
PipesHub indexes content from 50+ business systems such as Slack, Google Drive, GitHub, Microsoft 365 and Notion. It answers questions with block-level citations, filtered by each user's source-system permissions. The same context is exposed to your own agents through an MCP server, Python, TypeScript and Go SDKs, and a no-code agent builder.
Who it is for: Teams self-hosting company-wide search and agent context over SaaS data
Strengths
- Answers carry block-level citations to the original documents
- Access checks follow source-system permissions per user, resolved at query time
- 50+ connectors with real-time and scheduled indexing
- MCP server plus Python, TypeScript and Go SDKs; any LLM provider or Ollama
Weaknesses
- Stack needs Neo4j or ArangoDB, Qdrant, MongoDB and Redis, plus Kafka at larger scale
- Audio and video can be stored but are not indexed yet
- Hosted PipesHub Cloud is only a waitlist
- README does not list supported LLM providers, only 'any provider'
What it needs
- GPU optional
- Docker + Compose
- Needs Docker Compose v2, Neo4j or ArangoDB, Qdrant, MongoDB, Redis, Kafka (larger deployments)
- Models: any LLM provider, Ollama, local embedding server, multimodal LLM for scanned PDF OCR
- port 3000
Quick answers
Is PipesHub open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Can you run PipesHub with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does PipesHub need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in RAG, knowledge and search
See all 41| Rank | Project | Score |
|---|---|---|
| 1 | RAGFlowRAG engine with deep document parsing, template chunking and agentic retrieval | 90 out of 100 |
| 2 | deeptutorSelf-hosted AI tutor with knowledge bases, guided learning, books and quizzes | 89 out of 100 |
| 3 | LightRAGGraph-based RAG framework with a REST API server and web UI | 89 out of 100 |
| #4 | MaxKBEnterprise knowledge-base agent platform with RAG, workflows and MCP tools | 86 out of 100 |
| #5 | Open NotebookSelf-hosted NotebookLM alternative with podcasts and 20+ model providers | 83 out of 100 |