CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.

Open-source observability & evaluation platform for AI agents and coding agents. Trace LLMs, tools, prompts, costs & agent workflows with OpenTelemetry.

See your agent think. Zero-config observability & governance for 30 AI agent runtimes: Claude Code, OpenAI Codex, Hermes, OpenClaw & 26 more. Live token costs, sessions, tool calls, crons.

See what Claude Code and Codex actually send to the API — and what each part costs.

Tools for AI agents to test, fix and optimise your codebase