PipesHub AI is an open-source context layer for enterprise AI, offering explainable search, no-code agents, and extensible connectors with self-hostable deployment. It supports Docker Compose deployments and BYO-Model LLMs, with a modular backend stack and multiple SDKs.
Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).
What it is
PipesHub is an open-source Context Layer for Enterprise AI. It enables connect enterprise knowledge across an organization, preserve access permissions, generate trustworthy citations, and build AI agents, enterprise search, RAG applications, MCP servers, and agentic workflows on a single governed context layer.
How it works
The project provides a backend architecture that includes GraphDB (Neo4j / ArangoDB), VectorDB (Qdrant / OpenSearch / Redis), Document Store (MongoDB), and various supporting services (Kafka / Redis Streams, Redis, etcd). It uses a FastAPI web framework, LangChain for LLM interfaces, and supports multiple document parsing and conversion tools (pdfplumber, selectolax, markdown-it, openpyxl, csv; LibreOffice, CairoSVG). It also exposes MCP capabilities and SDKs for Python, TypeScript, and Go to integrate with external clients.
Getting started
Quickstart (Recommended)
Requires Docker with Compose v2.
# 1. Clone the repository
git clone https://github.com/pipeshub-ai/pipeshub-ai.git
cd pipeshub-ai/deployment/docker-compose
# 2. Run the interactive installer
./install.sh
The installer will:
- Check Docker, RAM, and disk prerequisites
- Ask whether you want a slim or full deployment
- Let you optionally customise the graph DB, message broker, and KV store
- Generate randomised secrets and write a
.envfile - Pull images and start the stack
- Wait for PipesHub to pass its health check and print the URL
Open http://localhost:3000 once the installer completes.
Installer options
| Flag | Description |
|------|-------------|
| -y / --yes | Accept all defaults; skip interactive prompts (CI-friendly) |
| --version TAG | Pin a specific image tag, e.g. --version 0.7.0 |
| --reconfigure | Re-run the wizard and overwrite an existing .env |
| --print-env-only | Write .env and print the compose command without starting containers |
Advanced Deployment options are documented in the repo.
Recent releases
The latest releases include v0.6.0-beta (2026-08-01) with fixes for deep agent stale tasks and invite mail logging, followed by v0.5.0 (2026-07-01) and earlier patches. Each release lists specific change items per version.
Traction
The repository has 3156 stars and 479 forks, with 106 open issues, indicating community activity and ongoing maintenance.
License
Apache-2.0
Getting started (commands to reproduce)
- git clone https://github.com/pipeshub-ai/pipeshub-ai.git
- cd pipeshub-ai/deployment/docker-compose
- ./install.sh
Repos and SDKs
- Python SDK: https://github.com/pipeshub-ai/pipeshub-sdk-python
- TypeScript SDK: https://github.com/pipeshub-ai/pipeshub-sdk-typescript
- Go SDK: https://github.com/pipeshub-ai/pipeshub-sdk-go