Skip to main content
AgentX is a platform for testing and observing AI agents. It lets you:
  • Record production traces from any framework (LangChain, CrewAI, OpenAI Agents, Anthropic, plain Python) and see them in the Live Traces tab.
  • Evaluate agent quality against test datasets — scoring responses with LLM judges, vector similarity, and Jaccard similarity.
  • Gate releases with CI/CD — block merges or deploys when your agent’s pass rate drops below a threshold.

Quickstart

Send your first trace in under 5 minutes

Python SDK

Decorator and context manager tracing

CI/CD Evaluation

Gate releases with eval test sets

API Reference

REST endpoints for direct integration

​
How it works

Your agent (LangChain, CrewAI, etc.)
        │
        │  agentx-python SDK
        ▼
POST /api/v1/ingest/traces
        │
        ├── Live Traces tab  ──► evaluate against datasets
        │
        └── CI/CD gate  ──► PASS / FAIL ──► block or merge PR
AgentX sits outside your agent — there is no prompt injection and no changes to your agent’s logic. The SDK wraps your agent function with a single decorator or context manager.

​
Base URL

https://api.agentx.so
All API paths in this documentation are relative to this base URL.