AI Agent Observability & Security — MCP server for tracing reasoning chains, tracking costs, detecting hallucinations, and monitoring agent behavior
Local-only observability + control plane for every AI coding agent on your machine. TUI live tail + browser dashboard on localhost. Unified timeline across Claude Code, Codex, Gemini CLI, Cursor, Hermes, OpenClaw — token + cost accounting, compaction + an
autoai的js版本sdk
Multi-agent observability: cascade failure detection, heartbeats, and forensic replay
Type definitions and JSON schema validators for the AgentWatch protocol
Detect failures, investigate root causes, and hill-climb fixes for AI agents. Uses your Claude Code subscription.
全埋点 TrackJs sdk
Zero-config OpenAI usage tracking for AgentWatch — prompts never leave your server
See what AI coding agents do on your machine. Session logging + dashboard for Claude Code.
The reliability layer for AI agents — monitor, trace, and detect failures in production
The Node.js SDK for AgentWatch. Stream exactly what your agent is doing to the AgentWatch dashboard in real-time.
TypeScript SDK for AgentWatch — observability for multi-agent AI systems
全埋点 TrackJs sdk
AI API monitoring SDK — track costs, latency, and errors for OpenAI & Anthropic