pipeshub-ai: An open-source context layer for AI agents and an enterprise search platform.
What problem it solves
Company knowledge is distributed across business systems such as Slack, Google Drive, Jira, GitHub, and Microsoft 365. AI applications need a governed way to search this information, respect each user's access controls, and provide answers that can be traced to their sources.
Key features
Permission-aware enterprise search — Searches connected company systems while applying source-level access controls for each requester. Results and answers are filtered according to the user's permissions.
Source: README
Cited, explainable answers — Provides grounded answers with block-level citations to the original documents, making the supporting evidence available for review.
Source: README
Multi-strategy retrieval — Combines semantic and keyword search, exact pattern matching, knowledge-graph navigation, and full-document reading. The agent loop can call tools and continue until it has sufficient evidence.
Source: README
Broad connector ecosystem — Connects Slack, Google Drive, GitHub, Microsoft 365, Notion, and more than 50 other systems, with real-time and scheduled indexing.
Source: README
Extensible development interfaces — Exposes the same connected and permission-filtered context through MCP, SDKs, APIs, custom connectors, and built-in agent workflows. It can be deployed locally or self-hosted with a chosen LLM provider.
Source: README, install.sh
Quick start
Copied verbatim from the project's README.
curl -fsSL https://get.pipeshub.com/install | bashgit clone https://github.com/pipeshub-ai/pipeshub-ai.git
cd pipeshub-ai
# Same installer, run from the repo root
./install.shWho it may suit
Inference: may suit teams and developers building internal search, AI agents, workflows, or applications that need governed access to distributed company knowledge.
Topics to discuss
How should permission-aware context be exposed to external AI agents without weakening source access controls?
Which new enterprise connectors or indexing workflows would be most useful for your organization?
How can citation, graph navigation, and focused retrieval be evaluated in real-world enterprise use cases?
Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.
Read the original README https://github.com/pipeshub-ai/pipeshub-ai#readme
ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.
Comments
…