Awesome AI AgentsAgent Monitoring Tools

luccast/crabwalk

⭐ 879 TypeScript repository created 2026-01-25

Crabwalk is a real-time companion monitor for agents running on the OpenClaw (formerly Clawdbot) gateway. It connects to the gateway over a WebSocket and renders every active session as a node graph built with ReactFlow, so an operator can watch agents work across WhatsApp, Telegram, Discord and Slack at the same time. Nodes show thinking states, tool calls and response chains as they stream in, and expanding a node reveals the arguments and payloads of individual actions, which makes it usable for tracing why an agent took a particular step. Sessions can be filtered by messaging platform and searched by recipient. A workspace explorer exposes the files under the agent workspace directory, by default ~/.openclaw/workspace. Crabwalk ships as a single CLI binary. Running crabwalk starts the server on 0.0.0.0:3000, flags cover the port, bind address, gateway WebSocket URL and auth token, and start --daemon, stop, status and update manage a background instance. The CLI reads the gateway token automatically from ~/.openclaw/openclaw.json, so a local setup needs no configuration. On startup it prints a QR code through qrencode for opening the monitor on a phone. Installation options are a shell one-liner that pulls the latest release tarball, a prebuilt Docker image at ghcr.io/luccast/crabwalk with an accompanying docker-compose file, or building from source with npm. The README documents the networking caveats for Docker, including using host.docker.internal to reach a gateway bound to the host and switching to host networking when the gateway binds to loopback only. It can also be installed by pointing an OpenClaw agent at the published skill.md file. The stack is TanStack Start, ReactFlow, Framer Motion, tRPC and TanStack DB. The intended user is someone already operating OpenClaw agents who wants live observability rather than log files.

https://github.com/luccast/crabwalk

agent-monitoringobservabilityopenclawwebsocketreactflowdashboardtypescriptdocker

Also in Agent Monitoring Tools

raga-ai-hub/RagaAI-Catalyst

RagaAI Catalyst is a Python SDK platform for observability, monitoring, and evaluation of AI agents and LLM projects, featuring tracing, debugging, advanced analytics, and project management tools.

superset-sh/superset

Superset is a desktop application (macOS) designed to orchestrate and manage multiple CLI-based AI coding agents in parallel using isolated Git worktrees, featuring built-in diff viewing and IDE in...

MervinPraison/PraisonAI

PraisonAI is a production-ready Multi AI Agents framework that enables the creation and management of intelligent AI agents to automate and solve complex problems through collaboration and customization.

apache/hertzbeat

Apache HertzBeat is an AI-powered open source real-time observability system that unifies metrics and logs collection, alerting, and notification with high performance and customizable monitoring capabilities.

junhoyeo/tokscale

Tokscale is a CLI utility and dashboard for tracking and visualizing token usage and costs across various AI coding agents.

matt1398/claude-devtools

Desktop and Docker application that reads local Claude Code session logs and reconstructs tool calls, thinking steps, subagent trees and per-turn token attribution in a visual interface.

eumemic/ai-legion

AI Legion is a platform for autonomous agents powered by large language models that collaborate to accomplish tasks with minimal human intervention.

chiphuyen/sniffly

Sniffly is a local analytics dashboard that parses Claude Code logs to show usage statistics, error breakdowns and full message history, with optional shareable dashboards.