§ DOCUMENTATION
Documentation.
Everything you need to integrate, configure, and operate Execlave.
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 →Already know what you're doing?
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: 'https://api.execlave.com' }); 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-startedGetting Started
Policies & Governance
Policy Engine
14 policy types — injection scanning, access control, cost limits, PII protection, output classification, budget caps, and more. Four enforcement modes: block, warn, monitor, require_approval.
Expression Policies (CEL)
Write custom governance rules using CEL expressions. Access 11 context variables including input, output, cost, tools, environment, and metadata.
Policy Chaining
Evaluate multiple policies in sequence. Control ordering, short-circuit behavior, and how violations from different policies interact.
Custom Validators (BYOV)
Register external HTTP endpoints as policy validators. Execlave calls them during enforcement with HMAC-signed payloads and retries on failure.
Observability & Incidents
Execution Traces
Capture inputs, outputs, token usage, cost, latency, and policy evaluations. Supports hierarchical spans, trace trees, similarity search, and CSV/JSON export.
Webhooks
Subscribe to 16 event types (policy_violated, kill_switch_triggered, budget_exceeded, and more). Deliveries are HMAC-SHA256 signed and retried with exponential backoff.
Alerts & Notifications
Define alert rules on metrics with configurable thresholds, severity levels, and time windows. Supports email, Slack, and webhook notification channels.
Anomaly Detection
ML-powered detection using EWMA with seasonal decomposition. Includes root cause analysis, time-series forecasting, and configurable baselines.
Security & Compliance
Authentication & API Keys
Authenticate via Logto JWT or environment-scoped API keys (exe_dev_, exe_stg_, exe_prod_). Four-role RBAC hierarchy: Owner > Admin > Developer > Viewer.
Compliance Frameworks
Generate digitally signed evidence reports for SOC 2, GDPR, HIPAA, ISO 27001, and EU AI Act. Verify report authenticity via the compliance API.
Audit Logs
Tamper-evident, append-only audit trail with cryptographic chain verification. Export as CSV/JSON or as a signed compliance package for auditors.
Approvals
Human-in-the-loop workflows for require_approval policies. SDKs poll for the decision while admins approve or deny from the dashboard.
Integrations
LangChain
Callback handler that instruments chains, LLMs, tools, agents, and retrievers — Python and TypeScript.
OpenAI Agents SDK
Tracing processor that captures agent/tool/generation spans and blocks disallowed tools before they run.
CrewAI
One call to instrument_crew() wires in step and task callbacks, chaining your existing callbacks.
AutoGen
Instrument AutoGen multi-agent conversations with trace capture and policy enforcement per agent turn.
LlamaIndex
Callback handler for LlamaIndex query engines, retrievers, and synthesis steps.
n8n
Gate your n8n AI workflows with Execlave policies and trace logging — no-code templates included.
All Integrations
Browse every first-party framework integration and what is on the roadmap.
Reference
SDK Reference
Full API reference for the TypeScript and Python SDKs — methods, config, error types.
REST API Reference
Every endpoint with request/response examples and cURL snippets.
CLI Reference
Install the execlave CLI, authenticate via env var, and run all 11 command groups from the terminal.
Comparisons
See how Execlave compares to other AI governance solutions, including Microsoft Agent Governance Toolkit.
Quick Reference
| Endpoint | Method | Description |
|---|---|---|
| POST /api/v1/agents | REST | Register a new AI agent |
| PATCH /api/v1/agents/:id/pause | REST | Kill switch — pause an agent |
| POST /api/v1/agents/authorize | REST | Agent-to-agent authorization check |
| POST /api/v1/policies | REST | Create a governance policy |
| POST /api/v1/policies/enforce | REST | Pre-execution policy enforcement |
| POST /api/v1/policies/test | REST | Dry-run policy test |
| POST /api/v1/policies/generate-from-text | REST | AI-generated policy from natural language |
| POST /api/v1/traces/ingest | REST | Submit execution traces (batched, up to 100) |
| GET /api/v1/traces/:id/tree | REST | Get hierarchical trace tree |
| POST /api/v1/webhooks | REST | Register a webhook endpoint |
| POST /api/v1/webhooks/:id/test | REST | Send a test delivery |
| POST /api/v1/alerts/rules | REST | Create an alert rule |
| GET /api/v1/alerts/history | REST | View alert history |
| GET /api/v1/incidents | REST | List incidents |
| GET /api/v1/approvals/pending | REST | List pending approvals |
| POST /api/v1/approvals/:id/decide | REST | Approve or deny an action |
| GET /api/v1/compliance/report | REST | Generate compliance evidence report |
| GET /api/v1/audit-logs/chain/verify | REST | Verify audit log chain integrity |
| POST /api/v1/anomaly/detect | REST | Run anomaly detection |
| POST /api/v1/anomaly/forecast | REST | Run time-series forecast |
| POST /api/v1/custom-validators | REST | Register a BYOV endpoint |
| GET /api/v1/analytics/overview | REST | Operational analytics overview |
Install
JavaScript / TypeScript
npm install @execlave/sdkPython
pip install execlave-sdkCLI (npm)
npm install -g @execlave/cliCLI (login)
execlave login