🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

Monitor all your coding agents from one terminal - Claude Code, Cursor, OpenCode, pi and more

OpenTelemetry-based tracing SDK for AI agents and LLM applications

Security Dashboard for OpenClaw AI Agents - intercept, monitor, and control what OpenClaw does on your system.

📊 Real-time monitoring dashboard for Claude Code agent teams

Vault-0: Agent Security, Monitor & x402 Wallet for OpenClaw. Encrypted secret vault, real-time agent monitor, policy enforcement, and native x402 payments — built with Rust + Tauri.

The flight recorder for AI agents. Tamper-proof, ISO 42001 + HIPAA-compliant audit trails for everything AI agents do on your system. File changes + shell commands + PHI detection + agent identity.

OS-level runtime security for AI agents. Tamper-proof monitoring, behavioral detection, and audit trails.

TUI dashboard for monitoring Claude Code subagent hierarchy in real-time

This server remembers what just happened.

watches the watchers: a monitoring system for long-running Claude Code agents

Real-time mission control dashboard for Claude Code + Hermes + OpenClaw agent meshes. React + FastAPI + WebSockets. One command to run.

Put your AI on a short leash. Open-source AI agent visibility tool.

Lightweight Prometheus metrics exporter for AI agent pipelines.

P-MATRIX runtime governance monitor for OpenClaw — Safety Gate, Kill Switch, Live Grade

A full-stack observability and debugging platform for AI agents featuring vector-semantic search, real-time latency tracking, and visual distributed tracing.

P-MATRIX runtime governance monitor for Cursor — Safety Gate, Kill Switch, Live Grade

OpenClaw Lighthouse Diagnostic Skill: deterministic monitoring and remedies for AI agents—collects performance/financial metrics, flags latency/token spikes, suggests SCALE/MAINTAIN/KILL actions, and exports research packs (Markdown/NotebookLM-ready) for transparent diagnosis.

Unified AI Reliability Platform. One install, 12 diagnostic engines. Zero-dependency LLM pipeline monitoring.

Watchdog plugin for AI coding agents — detects stuck loops, stalls, and error spirals. Zero-config. Works with Claude Code and Copilot CLI.