agentbus
AgentBus acts as a central hub for receiving information from various online services and then directing that information to artificial intelligence systems. It solves the problem of needing to build custom connections for each service you want to integrate with your AI, simplifying the process significantly. Businesses using AI agents for tasks like customer service, data analysis, or automation would find this helpful. AgentBus allows these agents to react to events happening elsewhere, like a new customer inquiry or a change in a database. It’s useful because it streamlines the connection between external data sources and AI, saving time and technical effort. The ability to route events based on their content and manage them in a queue makes it a flexible and reliable solution.
README
<p align="center">
<h1 align="center">AgentBus</h1>
<p align="center">The open-source event bus for AI agents. Webhooks in. Agent actions out.</p>
</p>
<p align="center">
<a href="https://www.npmjs.com/package/agentbus"><img src="https://img.shields.io/npm/v/agentbus?color=blue" alt="npm version" /></a>
<a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-green" alt="MIT License" /></a>
<a href="https://www.typescriptlang.org/"><img src="https://img.shields.io/badge/TypeScript-5.7-blue" alt="TypeScript" /></a>
<a href="https://github.com/agentbus/agentbus/actions"><img src="https://img.shields.io/github/actions/workflow/status/agentbus/agentbus/ci.yml?label=CI" alt="CI Status" /></a>
</p>
---
## Why
AI agents need events to act on. But connecting webhooks to agents means writing custom HTTP servers, parsing payloads, handling retries, and managing queues — for every single integration.
AgentBus is a lightweight, self-hosted event bus that handles all of that. **Receive webhooks. Route to agents. Dispatch actions.** Works with any AI framework: CrewAI, LangGraph, OpenAI Agents SDK, or plain HTTP.
## Quick Start
```bash
npm install agentbus
```
```typescript
import { AgentBus } from 'agentbus';
const bus = new AgentBus({
handlers: [
{
name: 'issue-triage',
pattern: 'github:issues.*',
handle: async (ctx) => {
ctx.logger.info(`New issue: ${ctx.event.payload.title}`);
// Call your AI agent here
return { success: true };
},
},
],
});
// Receive an event
await bus.emit({
source: 'github',
type: 'issues.opened',
payload: { title: 'Bug: login fails', labels: ['bug'] },
});
```
## Features
| Feature | Community (Free) | Pro |
|---------|-----------------|-----|
| Webhook Ingestion | ✅ Unlimited | ✅ + Verified Sources |
| Routing | ✅ Glob Patterns | ✅ + Content-based |
| Queue | ✅ In-Memory + BullMQ | ✅ + Rate Limiting |
| Storage | ✅ SQLite + PostgreSQL | ✅ + Event Replay, DLQ |
| Agents | ✅ HTTP Adapter | ✅ + A2A, MCP Server |
| Dispatch | ✅ Unlimited | ✅ + Dedup, Filters |
| Support | GitHub Issues | Priority Email |
## Architecture
```
Webhooks (GitHub, Stripe, Sentry, ...)
│
▼
┌──────────────┐
│ AgentBus │
│ ┌──────────┐ │
│ │ Router │ │ ← Glob pattern matching
│ └──────────┘ │
│ ┌──────────┐ │
│ │ Queue │ │ ← In-memory or BullMQ
│ └──────────┘ │
│ ┌──────────┐ │
│ │ Store │ │ ← SQLite or PostgreSQL
│ └──────────┘ │
└──────────────┘
│
▼
AI Agents (HTTP, CrewAI, LangGraph, ...)
```
## Integrations
AgentBus works with any AI agent framework:
- **HTTP** — POST events to any endpoint
- **CrewAI** — Trigger crew tasks from webhooks
- **LangGraph** — Send events to LangGraph workflows
- **OpenAI Agents SDK** — Dispatch to OpenAI agents
- **A2A Protocol** — Agent-to-agent communication (Pro)
- **MCP Server** — Model Context Protocol integration (Pro)
## Documentation
Visit [agentbus.dev](https://agentbus.dev) for full documentation.
## Contributing
See [CONTRIBUTING.md](CONTRIBUTING.md) for development setup and guidelines.
## License
[MIT](LICENSE) — AgentBus core is free and open source.
[@agentbus/pro](https://agentbus.dev/pro) is available under a commercial license.
PUBLIC HISTORY
IDENTITY
Identity inferred from code signals. No PROVENANCE.yml found.
Is this yours? Claim it →METADATA
README BADGE
Add to your README:
