Auto-hébergé & Cloud

Une commande.
Une visibilité totale.

Installez ClawMetry localement gratuitement, ou connectez une flotte de Mac Minis à ClawMetry Cloud. Chiffré de bout en bout, un seul tableau de bord pour tout.

Commencer gratuitement Voir en action
Choisissez votre configuration

Quelle version vous convient ?

ClawMetry
OSS / Auto-hébergé
Gratuit & open source
  • ✓ Gratuit, pour toujours
  • ✓ Open source sur GitHub
  • ✓ Fonctionne entièrement en local. Une seule machine.
  • ✓ Vos données ne quittent jamais votre machine
  • ✓ Aucun compte requis
  • – Un seul nœud uniquement
  • – Pas d'accès à distance
Commencer gratuitement
LIVE
☁️
ClawMetry Cloud
Flotte gérée
  • ✓ Géré & toujours actif
  • ✓ Chiffré de bout en bout
  • ✓ Flotte multi-nœuds (10+ Mac Minis)
  • ✓ Accédez au tableau de bord où que vous soyez
  • ✓ Accès et partage en équipe
  • ✓ Zéro texte en clair sur nos serveurs
  • ✓ Une seule vue pour tous les nœuds
Commencer
Architecture

Pas de proxy. Aucune modification de code.

ClawMetry lit directement l'espace de travail d'OpenClaw - les mêmes fichiers et journaux qu'OpenClaw écrit déjà. Rien ne s'interpose entre vos agents et les modèles.

🤖
Your OpenClaw agents
Running normally.
Nothing changes.
reads files
ClawMetry
ClawMetry
Parses logs + sessions.
Serves dashboard.
shows you
📊
Your browser
localhost:8900
Live dashboard
Runs locally on the same machine as OpenClaw. Your data never leaves your box.
Observabilité des agents

Une vision aux rayons X de l'exécution de votre agent

ClawMetry correspond directement à l'architecture en 3 couches d'OpenClaw. Voyez exactement ce qui se passe à chaque couche - des messages entrants aux appels LLM jusqu'à l'exécution des outils.

Layer 1: Connectors
📲
Telegram
3 groups, 1 DM
💬
WhatsApp
1 group
🎮
Discord
2 channels
⌨️
CLI
main session
🔌
<plugin>
routes messages
Layer 2: Gateway Controller
Main
TG:group1
TG:group2
WA:chat
DC:chan1
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 USER Telegram "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

Surveillez une flotte de Mac Minis où que vous soyez

Chaque nœud chiffre ses données localement avant de les envoyer. ClawMetry Cloud ne voit jamais de texte en clair. Vous voyez chaque machine dans un seul tableau de bord, où que vous soyez.

🖥️ 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
anywhere
🌐
Your dashboard
Any browser,
anywhere
🔐
E2E Encrypted
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.
Installation

Opérationnel en moins d'une minute

Deux commandes. C'est tout.

terminal
1

Install with pip

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

2

Run clawmetry

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

3

That's it

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

Ce que vous voyez

Tout dans un seul tableau de bord

Six onglets. Chacun répond à une question différente sur ce que font vos agents.

🤖

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.

Live
🔀

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.

7-day history
💰

Token flow

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

Live
⏰

Cron jobs

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

Live
🩺

System health

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

Live
📜

Session history

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

Searchable
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.

Voyez ce que font réellement vos agents

Gratuit, open source, et opérationnel en moins d'une minute. Aucun compte requis.

pip install clawmetry
Commencer gratuitement Voir sur GitHub

Stay in the loop

Get notified about new features, alerting integrations, the Mac app, and everything else coming to ClawMetry.