Self-Hosted at Cloud

Isang command.
Buong visibility.

I-install ang ClawMetry nang lokal nang libre, o ikonekta ang isang fleet ng Mac Mini sa ClawMetry Cloud. E2E encrypted, isang dashboard para sa lahat.

Magsimula nang libre Tingnan ito sa aksyon
Piliin ang iyong setup

Aling bersyon ang tama para sa iyo?

ClawMetry
OSS / Self-Hosted
Libre at open source
  • ✓ Libre, habambuhay
  • ✓ Open source sa GitHub
  • ✓ Tumatakbo nang ganap na lokal. Isang makina.
  • ✓ Nananatili ang iyong data sa iyong machine
  • ✓ Walang kailangang account
  • – Single node lang
  • – Walang remote access

Paid self-hosted licenses unlock all runtimes and paid features locally. See pricing.

Magsimula nang libre
LIVE
☁️
ClawMetry Cloud
Pinamamahalaang fleet
  • ✓ Pinamamahalaan at laging nakabukas
  • ✓ End-to-end encrypted
  • ✓ Multi-node na fleet (10+ Mac Minis)
  • ✓ I-access ang dashboard kahit saan
  • ✓ Access at pagbabahagi para sa team
  • ✓ Walang plaintext sa aming mga server
  • ✓ Isang view para sa lahat ng node
Magsimula
Arkitektura

Walang proxy. Walang pagbabago sa code.

Binabasa ng ClawMetry ang mga session file at log na isinusulat na ng iyong mga agent runtime: OpenClaw, Claude Code, Codex, Cursor + 13 pa. Walang namamagitan sa iyong mga agent at sa mga model.

🤖
Ang iyong mga AI agent
OpenClaw, Claude Code, Codex
+ 15 more. Nothing changes.
reads files
ClawMetry
ClawMetry
Parses logs + sessions.
Serves dashboard.
shows you
📊
Your browser
localhost:8900
Live dashboard
Tumatakbo nang lokal sa parehong machine ng iyong mga agent. Ang iyong data ay nasa isang lokal na database sa machine na iyon.
Mga suportadong runtime

17 runtime. Isang dashboard.

Awtomatikong dine-detect ng ClawMetry ang bawat suportadong runtime sa iyong machine at ipinapakita ang mga ito nang magkakatabi, parehong mga tab, parehong live feed, parehong cost attribution. Walang SDK, walang pagbabago sa code.

OpenClaw NVIDIA NemoClaw NanoClaw PicoClaw Claude Code Codex Cursor Aider Goose OpenCode Qwen Hermes Pi Deep Agents n8n Antigravity GitHub Copilot

Libre ang OpenClaw at NVIDIA NemoClaw sa bawat plan.

Observability ng Agent

X-ray vision sa runtime ng iyong agent

Direktang naka-map ang ClawMetry sa 3-layer na arkitektura ng OpenClaw. Tingnan nang eksakto ang nangyayari sa bawat layer, mula sa mga papasok na mensahe hanggang sa mga LLM call hanggang sa pag-execute ng tool.

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

Subaybayan ang fleet ng Mac Minis kahit saan

Bawat node ay nag-e-end-to-end encrypt ng mga pag-uusap at aktibidad ng iyong mga agent bago ipadala; ikaw lang ang may hawak ng key, kaya ciphertext lang na hindi nito mababasa ang iniimbak ng cloud. Ang mga simpleng kabuuan tulad ng gastos at health ay ligtas na nagsi-sync, at nakikita mo ang bawat machine sa iisang dashboard, nasaan ka man.

🖥️ 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.
Setup

Tumatakbo nang wala pang isang minuto

Dalawang command. Ayun lang.

terminal
1

Install with pip

Gumagana saanman naka-install ang Python 3.8+. Sa parehong machine ng iyong mga agent.

2

Run clawmetry

Auto-discovers the AI agent runtimes on your machine. Opens the dashboard at localhost:8900.

3

That's it

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

Ang nakikita mo

Lahat sa isang dashboard

Anim na tab. Bawat isa ay sumasagot sa ibang tanong tungkol sa ginagawa ng iyong mga agent.

🤖

Main Agent

Live feed ng bawat tool call na ginagawa ng iyong mga agent, sa OpenClaw, Claude Code, Codex at lahat ng iba pang runtime. Pangalan, ano ang ginawa nito, gaano katagal, naka-update nang real time.

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

Bawat naka-iskedyul na task sa iyong agent setup, kailan huling tumakbo, status, at run history. Mahuli ang na-miss na cron bago pa ito magdulot ng problema.

Live
🩺

System health

Status ng serbisyo ng iyong agent gateway at mga nakakonektang component sa isang tingin.

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

Binabasa ang sariling mga file ng bawat runtime

Hindi hinaharang ng ClawMetry ang traffic o binabago ang iyong setup. Bawat runtime ay nagsusulat na ng aktibidad nito sa disk: ang OpenClaw sa workspace nito, ang Claude Code at Codex sa kanilang session transcript, ang Cursor sa lokal na state nito. Binabasa ng ClawMetry ang mga native na file na iyon at ipinapakita ang mga ito bilang isang live na 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 - parsed from each runtime's native format
⏰
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

Other runtimes (auto-detected)
📁 ~/.claude/projects/ ← Claude Code
📁 ~/.codex/sessions/ ← Codex
📄 …/Cursor/…/state.vscdb ← Cursor
📄 + 13 more runtimes

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

Tingnan kung ano talaga ang ginagawa ng iyong mga agent

Libre, open source, at tumatakbo nang wala pang isang minuto. Walang kailangang account.

pip install clawmetry
Magsimula nang libre Tingnan sa GitHub

Stay in the loop

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