Type definitions and JSON schema validators for the AgentWatch protocol
AgentWatch SDK for AI agent observability
The Node.js SDK for AgentWatch. Stream exactly what your agent is doing to the AgentWatch dashboard in real-time.
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
Zero-config OpenAI usage tracking for AgentWatch — prompts never leave your server
TypeScript SDK for AgentWatch — observability for multi-agent AI systems
Multi-agent observability: cascade failure detection, heartbeats, and forensic replay
AI Agent Observability & Security — MCP server for tracing reasoning chains, tracking costs, detecting hallucinations, and monitoring agent behavior
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
AI API monitoring SDK — track costs, latency, and errors for OpenAI & Anthropic
Detect failures, investigate root causes, and hill-climb fixes for AI agents. Uses your Claude Code subscription.
Monitor AI coding agents (Claude, Cursor, Copilot, etc.) from the terminal
Core detection library for AgentWatch - identifies AI coding agents