airweave-ai/airweave
Airweave
Airweave is a tool that lets agents semantically search any app. Itβs MCP compatible and seamlessly connects any app, database, or API, to transform their contents into agent-ready knowledge.
Overview
Airweave simplifies the process of making information retrievable for your agent. Whether you have structured or unstructured data, Airweave helps you break it into processable entities, store the data and make it retrievable through REST and MCP endpoints.
Table of Contents
π Quick Start
Make sure docker and docker-compose are installed, thenβ¦
|
|
Thatβs it! Access the dashboard at http://localhost:8080
π Supported Integrations
π» Usage
Frontend
- Access the UI at
http://localhost:8080
- Connect sources, configure syncs, and query data
API
- Swagger docs:
http://localhost:8001/docs
- Create connections, trigger syncs, and search data
π¦ SDKs
Python
|
|
|
|
TypeScript/JavaScript
|
|
|
|
π Key Features
- Data synchronization from 25+ sources with minimal config
- Entity extraction and transformation pipeline
- Multi-tenant architecture with OAuth2
- Incremental updates using content hashing
- Semantic search for agent queries
- Versioning for data changes
- White-labeling support for SaaS builders
π§ Technology Stack
- Frontend: React/TypeScript with ShadCN
- Backend: FastAPI (Python)
- Databases: PostgreSQL (metadata), Qdrant (vectors)
- Deployment: Docker Compose (dev), Kubernetes (prod)
π£οΈ Roadmap
- Additional source integrations
- Redis worker queues for large-scale syncs
- Webhooks for event-driven syncs
- Kubernetes support via Helm charts
π₯ Contributing
We welcome contributions! Please check CONTRIBUTING.md for details.
π License
Airweave is released under the MIT license.
π Connect
- Discord - Get help and discuss features
- GitHub Issues - Report bugs or request features
- Twitter - Follow for updates