One command. Full visibility.

Install ClawMetry locally for free, or connect a fleet of Mac Minis to ClawMetry Cloud. E2E encrypted, one dashboard for everything.

Get started free See it in action

Choose your setup

Which version is right for you?

OSS / Self-Hosted

Free & open source

  • ✓ Free, forever
  • ✓ Open source on GitHub
  • ✓ Runs entirely local — one machine
  • ✓ Your data never leaves your box
  • ✓ No account required
  • – Single node only
  • – No remote access

Get started free

ClawMetry Cloud

Managed fleet

  • ✓ Managed & always on
  • ✓ End-to-end encrypted
  • ✓ Multi-node fleet (10+ Mac Minis)
  • ✓ Access dashboard from anywhere
  • ✓ Team access & sharing
  • ✓ Zero plaintext on our servers
  • ✓ One view for all nodes

Get Started

Architecture

No proxy. No code changes.

ClawMetry reads directly from OpenClaw's workspace - the same files and logs OpenClaw already writes. Nothing sits between your agents and the models.

Your OpenClaw agents

Running normally.

Nothing changes.

reads files

ClawMetry

Parses logs + sessions.

Serves dashboard.

Your browser

localhost:8900

Live dashboard

Runs locally on the same machine as OpenClaw. Your data never leaves your box.

Agent Observability

X-ray vision into your agent's runtime

ClawMetry maps directly to OpenClaw's 3-layer architecture. See exactly what happens at every layer - from incoming messages to LLM calls to tool execution.

Layer 1: Connectors

  • 📲 Telegram 3 groups, 1 DM
  • 💬 WhatsApp 1 group
  • 🎮 Discord 2 channels
  • ⌨️ CLI main session
  • 🔌 routes messages

Layer 2: Gateway Controller

  • Heartbeat: Each channel/group gets its own isolated session with full transcript
  • Cron Manager
  • Memory Mgmt
  • Session DB builds context + calls LLM

Layer 3: Agent Runtime

Environment

  • Claude Code
  • GCP
  • exe.dev

Providers

  • Opus 4.6
  • GPT 5.4
  • Sonnet 4.6

Tools

  • web_search
  • read_file
  • exec

Skills

  • weather
  • gh-issues
  • tmux

Brain Tab

Channel + Skill Badges

Every event tagged with which channel it came from and which skill triggered it. Filter by Telegram, WhatsApp, Discord, or CLI. Click any turn to see the full execution trace.

Context Tab

LLM Context Inspector

See exactly what context the LLM receives: system prompt breakdown, bootstrap files (SOUL.md, AGENTS.md), tool schemas, conversation history, and compaction events.

Skills Tab

Skills File Browser

IDE-like explorer for all installed skills. Click any skill to browse SKILL.md, scripts, and references. See fidelity stats: which skills are actually being used vs dead weight.

Per-Turn Execution Timeline

  • 18:12:50 USERTelegram "deploy to prod"
  • 5 steps 2 LLM 2 tools 5.6s
  • 18:12:52 EXEC git status
  • 18:12:52 READ deploy.sh
  • 18:12:53 THINK Checking deployment config...
  • 18:12:55 AGENT Deployed successfully to prod

LLM Context Composition

What the model actually sees each turn

Tooling

  • 3.0K

Skills headers

  • 1.5K

  • Bootstrap: SOUL.md

  • 750

  • Bootstrap: MEMORY.md

  • 1.0K

  • Tool schemas (JSON)

  • 7.0K

  • Conversation history

  • 38.5K

Total: 51.7K / 200K tokens (26%) Compaction threshold: ~160K

ClawMetry Cloud

Monitor a fleet of Mac Minis from anywhere

Each node encrypts its data locally before sending. ClawMetry Cloud never sees plaintext. You see every machine in one dashboard, wherever you are.

  • 🖥️Mac Mini 1 🔒
  • 🖥️Mac Mini 2 🔒
  • 🖥️Mac Mini 3 🔒
  • 🖥️Mac Mini 4 🔒
  • 🖥️Mac Mini 5 🔒
  • 🖥️Mac Mini 10+ 🔒

E2E encrypted

  • ClawMetry Cloud Zero plaintext on our servers
  • Any browser, anywhere

Data is encrypted on-device before it leaves your Mac Mini.

Zero plaintext on our servers

ClawMetry Cloud only ever sees ciphertext. Only you can decrypt.

Any node, one view

All your Mac Minis in one dashboard. Switch between nodes instantly.

Setup

Running in under a minute

Two commands. That's it.

$ curl -fsSL https://clawmetry.com/install.sh | bash

  1. Install with pip

Works wherever Python 3.8+ is installed. Same machine as OpenClaw.

  1. Run clawmetry

Auto-discovers your OpenClaw workspace. Opens the dashboard at localhost:8900.

  1. That's it

No account. No API key. No config file. Open your browser and start watching.

What you see

Everything in one dashboard

Six tabs. Each one answers a different question about what your agents are doing.

Main Agent

Live feed of every tool call your main OpenClaw agent makes - name, what it did, how long it took. Updates in real time as the agent works.

Sub Agents

7-day history of every sub-agent run. See what task it was given, when it started, when it finished, and what it did along the way.

Token flow

Real-time token usage broken down by model and session. Know exactly which sessions are burning through your budget.

Cron jobs

Every scheduled task in your OpenClaw setup - last run time, status, and run history. Catch a missed cron before it matters.

System health

Service status for your OpenClaw gateway and connected components at a glance.

Session history

Browse past sessions with a full timeline of what happened - tool calls, costs, duration. Useful for debugging anything that went wrong.

Under the hood

Reads from OpenClaw's workspace

ClawMetry doesn't intercept traffic or modify your setup. It reads the files OpenClaw already writes - session transcripts, cron job state, workspace files - and presents them as a live dashboard.

This means zero overhead on your agents and zero risk of ClawMetry breaking anything.

Session transcripts

Every tool call, model response, and agent turn, timestamped

Cron job registry

Scheduled tasks, run history, and last-fired timestamps

Workspace files

Memory files, SOUL.md, AGENTS.md - whatever your agent reads and writes

Gateway status

OpenClaw gateway health, active sessions, connected channels

  • ~/.openclaw/workspace
  • sessions/ ← session transcripts
  • memory/ ← memory files
  • MEMORY.md ← long-term memory
  • SOUL.md ← agent persona
  • HEARTBEAT.md
  • ~/.openclaw/cron
  • jobs.json ← cron jobs
  • ~/.openclaw/agents
  • main/ ← main agent sessions
  • sub-*/ ← sub-agent runs

ClawMetry reads these. Your agents keep writing them. Nothing changes.

See what your agents are actually doing

Free, open source, and running in under a minute. No account required.

pip install clawmetry

Get started free View on GitHub