Skip to main content
Airweave Hero Light

​
What is Airweave?

Airweave is an open-source platform that connects to your apps, tools, and databases, continuously syncs their data, and exposes it through a unified, LLM-friendly search interface. AI agents query Airweave to retrieve relevant, grounded, up-to-date context from multiple sources in a single request.

Connect your data sources

50+ integrations including GitHub, Notion, Slack, Stripe, Gmail, and databases

Search with natural language

AI-powered semantic search with filters, reranking, and query expansion

Build AI agents

Native integrations with agent frameworks via SDKs, REST API, and MCP

Deploy anywhere

Cloud-hosted at app.airweave.ai or self-hosted with Docker

​
Where it fits

Airweave sits between your data sources and AI systems as shared retrieval infrastructure. It handles authentication, ingestion, syncing, indexing, and retrieval so you don’t have to rebuild fragile pipelines for every agent or integration.

​
How it works

1

Connect your data sources

Authenticate with your apps and databases using OAuth, API keys, or database credentials. Airweave supports 50+ integrations including:
  • Productivity: Notion, Slack, Gmail, Google Drive, Confluence
  • Development: GitHub, GitLab, Bitbucket, Jira, Linear
  • Business: Stripe, HubSpot, Salesforce, Zendesk
  • Databases: PostgreSQL, MySQL, MongoDB
2

Data syncs automatically

Airweave continuously syncs data from your sources, extracts entities (documents, issues, emails, customers), and indexes them for semantic search. Configure sync schedules or enable real-time continuous syncing.
3

Search with natural language

Query your collections using the Python SDK, TypeScript SDK, or REST API. Results are ranked by relevance, filtered by source and metadata, and optionally reranked with AI for improved accuracy.
4

Retrieve grounded context

Get relevant, up-to-date information from all your connected sources in a single request. Perfect for RAG systems, AI agents, and semantic search applications.

​
Example: Search across all your data

from airweave import AirweaveSDK

client = AirweaveSDK(api_key="YOUR_API_KEY")

# Search across GitHub, Notion, and Slack
results = client.collections.search(
    readable_id="engineering-docs",
    query="How do we handle authentication in the API?"
)

for result in results.results:
    print(f"Source: {result['payload']['source_name']}")
    print(f"Content: {result['payload']['md_content'][:200]}")
    print(f"Score: {result['score']}\n")

​
Key features

Create collections that group multiple data sources together. Search across GitHub, Notion, Slack, databases, and more with a single query. No need to query each source separately or manage multiple APIs.
Set up a source connection once and Airweave handles the rest. Data syncs automatically on a schedule or continuously. Incremental syncing ensures you only process changes, not entire datasets.
Filter results by source, date range, status, or custom metadata. Apply recency bias to prefer newer content. Set score thresholds for high-confidence results only.
Built on PostgreSQL, Vespa, Temporal, and Redis. Scales to millions of documents. Self-host with Docker or use the managed cloud service. SOC 2 Type II compliant.
Works with popular AI frameworks out of the box. Model Context Protocol (MCP) server included. Python and TypeScript SDKs with full type safety. REST API for any language.

​
Get started in minutes

Cloud (Recommended)

Hosted service with free tier. No setup required.

Self-hosted

Run locally with Docker in under 5 minutes.

Follow the quickstart

Create your first collection and search in under 10 minutes

​
Community and support

Discord

Join our community for help and discussions

GitHub

Star the repo and contribute

Twitter

Follow for updates and announcements