Agent Monitoring GitHub Repositories

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

Latitude is the open-source AI monitoring platform.

See your agent think. Zero-config observability & governance for 20+ AI agent runtimes: OpenClaw, Claude Code, OpenAI Codex, Cursor, Aider, Goose, NVIDIA NemoClaw, NanoClaw & more. Live token costs, sessions, tool calls, crons.

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

OpenTelemetry-native SDK for AI agent observability, tracing, evaluation, debugging, governance, and runtime policy enforcement. Framework-agnostic and built for OpenAI Agents, LangGraph, CrewAI, and LLM applications in production.

Real-time gamified dashboard for monitoring Claude Code and Codex AI agents in a medieval fantasy setting

All of your agents, shells, and TUIs in one durable terminal workspace

AgentX python SDK. Build multi-agent AI workforce. Run evaluation. Trace your agent. Full Observability.

📊 Real-time monitoring dashboard for Claude Code agent teams

Claude Code 에이전트 활동을 실시간으로 시각화하는 로컬 대시보드. 나의 활동기반으로 잔디를심고 게임을 곁들인!

The runtime reliability layer for AI agents.

Mindlas catches your coding agent drifting before the bad code lands. Real-time tracking and correction for context rot, unverified done claims, patch sprawl, and tool loops in your Claude Code session.

See, steer, and remember every coding agent session — Claude Code, Codex, Cursor, Gemini. Team memory, live steering from any device, line-level agent attribution.

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

🚥 Live Codex / Claude Code session monitoring via a 5x5x5 WLED cube

A police department for your Claude Code agents — a logging-only hook + CLI that audits the main agent and every subagent and reports rule offenses (permission bypass, out-of-scope & credential access, self-permissioning, disallowed tools, redundant, off-task) with quoted evidence. Catch-and-report, never blocks.

Deterministic, local-only audit reports for Claude Code AI agent sessions. Rust + SQLite. Zero network calls. MCP server for agents.

Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.

Open-source middleware for AI agents — catches mid-run failures,compresses stale context, and grows a reasoning library across runs. Any model, any framework.

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.

DevTools for multi-agent AI — trace, visualize and debug agent workflows in real time

A local-first macOS menu bar app for monitoring multiple Codex tasks in real time.

A fast multi-platform agent monitoring utility

Databricks App for cross-workspace AI stack governance. Unified view of agents, serving endpoints, knowledge bases, and AI Gateway usage, backed by system tables + Lakebase with auto-refreshing discovery workflows.

Local-first SIEM flight recorder for AI coding agents: MITRE-mapped audit trail, sequence detection, DLP

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.

The Operating System for AI Agent Fleets - monitor, orchestrate, and persist knowledge across your AI agents from a single dashboard.

Self-healing observability for AI agents. Discover, monitor, and auto-recover multi-agent systems — without a cloud dependency.

macOS menu-bar mission-control for your Claude Code sessions — see, hear and reply to every agent so none sits idle waiting on you. Rust + Tauri, event-driven on native hooks, fully local.

See what your AI agents do, whether it's worth it, and what it costs - a manager-readable report + local dashboard from Langfuse/LangSmith traces (or a one-line live callback). Open source, runs locally.