# airweave-ai/airweave

Open-source context retrieval layer for AI agents

Repository: https://github.com/airweave-ai/airweave
Canonical: https://ross.abutalabs.com/products/airweave
Homepage: https://airweave.ai
Language: Python
License: MIT
License Family: permissive
Topics: llm, rag, search, agent-infrastructure, ai, ai-agents, ai-infrastructure, api, context-retrieval, data-connectors, developer-tools, enterprise-data, information-retrieval, integration, open-source, retrieval, retrieval-augmented-generation, sdk, search-api, semantic-search
Last push: 2026-06-05T09:52:19+00:00

## Health v2 (maintenance only)
Score: 74/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 86, release rhythm 75, longevity 44
- inputs: {"age_days": 617, "days_push": 89, "days_rel": 89, "gap_med": 0, "n_releases_24m": 470}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6564, forks 816 (observed 2026-08-28T04:09:45.215291+00:00)

## What it is
Airweave is an open-source context retrieval layer that connects to apps, databases, and documents and exposes their data through a single unified search API for AI agents and RAG pipelines. It continuously syncs data from source connections and offers Python/Node SDKs, an MCP server, a CLI, and a self-hostable Docker deployment.

## Use cases
- give my AI agent search across all our SaaS tools and databases
- build a RAG pipeline over Stripe, Slack, and Google Drive data
- sync enterprise data into a searchable knowledge base for LLMs
- expose company data to agents via MCP
- avoid writing custom integrations for every data source
- self-host a retrieval layer for context-heavy LLM apps

## When to choose
- you need unified semantic search across many apps and databases for agents or RAG
- you want continuously synced, source-grounded context instead of static embeddings
- you want MCP support or SDKs for Python and Node
- you prefer an MIT-licensed, self-hostable option with a hosted cloud alternative

## When to avoid
- you only need a simple vector database without connectors or sync
- you need a lightweight in-process retrieval library rather than a deployable service
- your data sources are unsupported by the available connectors

## Facets
- artifact type: service
- maturity: active
- function: search-engine, rag, etl, api-framework, sdk, mcp, self-hosted
- domain: large-language-models, developer-tools, self-hosted
- platform: self-hosted, python, cloud
- tags: context-retrieval, data-connectors, semantic-search, vector-search, agent-infrastructure, sync, retrieval-augmented-generation, ai-agents, search, docker, web-server, nodejs

## Member repositories
- airweave-ai/airweave (main) score 74

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:45.215291+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:43:41.156944+00:00, confidence not recorded.
  - readme: https://github.com/airweave-ai/airweave (fetched 2026-08-28T04:09:45.215291+00:00, sha 547f21fe8647)
  - homepage: https://airweave.ai (fetched 2026-08-29T08:40:21.897845+00:00, sha 8f8018b9dd8f)
  - site_page: https://docs.airweave.ai/welcome (fetched 2026-08-29T08:40:21.906868+00:00, sha dfee40456678)
  - site_page: https://docs.airweave.ai/quickstart (fetched 2026-08-29T08:40:21.908694+00:00, sha 8ae312ca8345)
- Data as of 2026-08-30T08:39:29.467469+00:00.