Back to Dashboard
Documentation
Everything you need to integrate, configure, and operate Execlave.
Recommended
Quick Start Guide
Go from zero to your first traced LLM call in under 5 minutes. Includes copy-paste prompts for your AI coding assistant.
Get started
5 min
Already know what you're doing?
Jump straight to the reference documentation.
Copy this prompt to your AI coding assistant
Integrate Execlave into my project. Install @execlave/sdk (npm) or execlave-sdk (pip).
Initialize with:
const ag = new Execlave({ apiKey: process.env.EXECLAVE_API_KEY, baseUrl: 'http://localhost:4000' });
Register my agent:
await ag.registerAgent({ agentId: 'my-agent', name: 'My Agent', type: 'chatbot', platform: 'custom' });
Wrap LLM calls:
const trace = ag.startTrace({ agentId: 'my-agent' });
trace.setInput(userMessage);
const response = await llm.call(userMessage);
trace.setOutput(response).setModel('gpt-4').finish();
Add shutdown handler:
process.on('SIGTERM', () => ag.shutdown());
See full guide: /docs/getting-started
Getting Started
Guides
Reference
Quick Reference
| Endpoint | Method | Description |
|---|---|---|
| POST /api/agents | REST | Register a new AI agent |
| POST /api/traces/ingest | REST | Submit execution traces (batched) |
| POST /api/policies | REST | Create a governance policy |
| POST /api/policies/enforce | REST | Pre-execution policy check |
| PATCH /api/agents/:id/pause | REST | Kill switch — pause an agent |
| POST /api/agents/:id/grants | REST | Create agent-to-agent access grant |
| POST /api/agents/authorize | REST | Check agent authorization |
| POST /api/webhooks | REST | Register a webhook |
Install
JavaScript / TypeScript
npm install @execlave/sdk
Python
pip install execlave-sdk