Zero-config OpenAI usage tracking for AgentWatch — prompts never leave your server

AgentWatch CLI — MCP security proxy, HMAC audit chain, L0/L1 risk detection, and tamper-proof log verification

Type definitions and JSON schema validators for the AgentWatch protocol

The Node.js SDK for AgentWatch. Stream exactly what your agent is doing to the AgentWatch dashboard in real-time.

Multi-agent observability: cascade failure detection, heartbeats, and forensic replay

A live perch over your Claude Code agents. A zero-dependency terminal dashboard showing every active session in real time — what it's doing right now, its tokens, cost, and whether it needs you. The runtime sibling to agentmeter.

TypeScript SDK for AgentWatch — observability for multi-agent AI systems

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-overhead drift monitoring SDK for AI agents

AgentWatch SDK for AI agent observability

AI Agent Observability & Security — MCP server for tracing reasoning chains, tracking costs, detecting hallucinations, and monitoring agent behavior

Detect failures, investigate root causes, and hill-climb fixes for AI agents. Uses your Claude Code subscription.

Local AI coding agent session supervisor: detect rate limits, schedule reset resumes, and verify recovery for Claude and Codex-oriented sessions, including OMX runtimes.

See what AI coding agents do on your machine. Session logging + dashboard for Claude Code.

Drop-in OpenAI SDK wrapper with LLM governance, budget enforcement, and telemetry

See what your AI coding agent actually costs — and where it wastes tokens. Parses local Claude Code transcripts into a cost report (by project, day, tool, model, skill/plugin/MCP, main-loop vs subagent) plus an efficiency report (errors, duplicate calls,

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

AI agent observability and control — track LLM calls, costs, latency, and risk in production

CLI for Hill Climb eval harness — seed, test, and inspect mock connector state