# Airweave — Context Retrieval Layer for AI Agents, 50+ Integrations

> Open-source context retrieval layer connecting AI agents to 50+ apps including Notion, Slack, GitHub, and Jira. Unified search API with MCP support.

## Install

Merge the JSON below into your `.mcp.json`:

## Quick Use

Self-hosted (Docker):
```bash
git clone https://github.com/airweave-ai/airweave
cd airweave
./start.sh
```

Or use the hosted version at [app.airweave.ai](https://app.airweave.ai).

---

## Intro

Airweave is an open-source context retrieval layer for AI agents and RAG systems with 6,200+ GitHub stars. It connects to 50+ apps (Notion, Slack, GitHub, Jira, Salesforce, and more), continuously syncs data, and exposes everything through a unified search API. Query via Python SDK, TypeScript SDK, REST API, or MCP — making it the single infrastructure layer between your data sources and AI agents.

Best for: teams building AI agents that need access to company data across multiple SaaS tools. Works with: Claude Code, any MCP client, LangChain, LlamaIndex. Setup time: under 5 minutes with Docker.

---

## Airweave — Unified Data Layer for AI

### Supported Integrations (50+)

| Category | Tools |
|----------|-------|
| Project Management | Asana, Jira, Linear, Trello |
| Knowledge | Notion, Confluence, Google Docs |
| Communication | Slack, Discord, Gmail |
| Code | GitHub, GitLab, Bitbucket |
| CRM | Salesforce, HubSpot |
| Data | Airtable, Google Sheets, Snowflake |
| Storage | Google Drive, Dropbox, OneDrive |
| Support | Zendesk, Intercom |

### Query Methods

```python
# Python SDK
from airweave import Airweave
client = Airweave(api_key="your-key")
results = client.search("latest sprint tickets")
```

```typescript
// TypeScript SDK
import { Airweave } from '@airweave/sdk';
const client = new Airweave({ apiKey: 'your-key' });
const results = await client.search('latest sprint tickets');
```

### MCP Integration

Add to your `.mcp.json`:
```json
{
  "mcpServers": {
    "airweave": {
      "url": "http://localhost:8080/mcp"
    }
  }
}
```

### How It Works

1. **Connect** — Authenticate with your SaaS tools via OAuth
2. **Sync** — Airweave continuously indexes data from all connected sources
3. **Search** — Query all sources through a single unified API
4. **Retrieve** — Get relevant context for your AI agents with source attribution

### FAQ

**Q: What is Airweave?**
A: Airweave is an open-source context retrieval layer that connects AI agents to 50+ SaaS apps through a unified search API with continuous data syncing.

**Q: Is Airweave free?**
A: Yes, it's open source under the MIT license. A hosted version is also available at app.airweave.ai.

**Q: How do I connect Airweave to Claude Code?**
A: Self-host with Docker (`./start.sh`), then add the MCP endpoint to your `.mcp.json` configuration.

---

## Source & Thanks

> Created by [airweave-ai](https://github.com/airweave-ai). Licensed under MIT.
>
> [airweave](https://github.com/airweave-ai/airweave) — ⭐ 6,200+

Thank you for building the bridge between enterprise data and AI agents.

---

<!-- ZH -->

## 快速使用

自托管（Docker）:
```bash
git clone https://github.com/airweave-ai/airweave
cd airweave
./start.sh
```

或使用托管版本：[app.airweave.ai](https://app.airweave.ai)

---

## 简介

Airweave 是一个开源的 AI Agent 上下文检索层，拥有 6,200+ GitHub stars。它连接 50+ 应用（Notion、Slack、GitHub、Jira、Salesforce 等），持续同步数据，并通过统一搜索 API 暴露所有内容。支持 Python SDK、TypeScript SDK、REST API 或 MCP 查询。

---

## Airweave — AI 统一数据层

### 支持的集成（50+）

| 类别 | 工具 |
|------|------|
| 项目管理 | Asana, Jira, Linear, Trello |
| 知识库 | Notion, Confluence, Google Docs |
| 通信 | Slack, Discord, Gmail |
| 代码 | GitHub, GitLab, Bitbucket |

---

## 来源与感谢

> Created by [airweave-ai](https://github.com/airweave-ai). Licensed under MIT.
>
> [airweave](https://github.com/airweave-ai/airweave) — ⭐ 6,200+

---
Source: https://tokrepo.com/en/workflows/1abeff10-d6be-45f3-b47c-f5998d7a08a4
Author: MCP Hub