Getting Started

Integrate Execlave into my project using the JavaScript/TypeScript SDK. Here's what you need to do: 1. Install the SDK: npm install @execlave/sdk 2. Add this environment variable to my .env file: EXECLAVE_API_KEY=<my-api-key> 3. Create a file called "execlave.ts" (or .js) in my project's lib/ or utils/ folder with this initialization code: import { Execlave, AgentPausedError, PolicyBlockedError } from '@execlave/sdk'; export const ag = new Execlave({ apiKey: process.env.EXECLAVE_API_KEY!, baseUrl: process.env.EXECLAVE_BASE_URL || 'http://localhost:4000', environment: process.env.NODE_ENV || 'development', debug: process.env.NODE_ENV !== 'production', }); // Register agent on startup (idempotent — safe to call multiple times) export async function initAgent() { return ag.registerAgent({ agentId: 'my-agent', name: 'My AI Agent', type: 'chatbot', platform: 'custom', }); } // Wrap any LLM call with automatic tracing export function traceCall<T>(fn: (input: string) => Promise<T>, agentId = 'my-agent') { return ag.wrap(fn, { agentId }); } // Export error types for catch blocks export { AgentPausedError, PolicyBlockedError }; 4. In my main application entry point (e.g. index.ts, app.ts, or server.ts), call initAgent(): import { initAgent } from './lib/execlave'; await initAgent(); 5. Wrap my LLM calls with tracing. For example: import { ag } from './lib/execlave'; async function handleUserMessage(userMessage: string) { const trace = ag.startTrace({ agentId: 'my-agent' }); trace.setInput(userMessage); try { const response = await myLLM.call(userMessage); trace.setOutput(response).setModel('gpt-4').finish(); return response; } catch (error) { trace.finish('error', String(error)); throw error; } } 6. Add graceful shutdown to catch process exit: process.on('SIGTERM', async () => { await ag.shutdown(); process.exit(0); }); The SDK has zero runtime dependencies and automatically: - Buffers and batch-flushes traces in the background - Detects prompt injection attempts client-side - Respects kill-switch (throws AgentPausedError if agent is paused) - Caches policy enforcement decisions (60s TTL) - Implements circuit breaker (3 failures → 60s backoff)