See every AI agent running on your machine. One local dashboard for sessions, cost, tools, transcripts, alerts and approvals, across 22 agent runtimes.
pip install clawmetry && clawmetryOpens at http://localhost:8900. Zero config: it finds the agent runtimes you already have, reads them read-only, and changes nothing about how they run.
🌐 Read this in: English · 简体中文 · 日本語 · 한국어 · Español · Português (BR) · Français · Deutsch · हिन्दी · العربية · Русский · more →
Free in the open source app: 🦞 OpenClaw · 🟩 NVIDIA NemoClaw
On a paid plan: ◆ Claude Code · ⬡ OpenAI Codex · Cursor · 🪿 Goose · ⚡ Hermes · opencode · ◈ Qwen Code · Aider · NanoClaw · PicoClaw · Pi · Deep Agents · 🔗 n8n · 🪐 Antigravity · 🐙 GitHub Copilot · Grok · QM · 🐋 DeepSeek Harness · 🦾 Exo · 🌙 Kimi CLI
Every runtime gets the same dashboard. Run several at once and the header switcher re-scopes every tab to one of them.
Built your own agent on an SDK instead? The interceptor tracks its LLM calls too. See docs/SDK_TRACKING.md.
- Sessions & transcripts: what each agent did, turn by turn, with replay
- Cost & tokens: per runtime, model, session and day, with anomaly flags
- Flow: live diagram of messages moving through channels, models and tools
- Brain: the reasoning and tool-call event stream as it happens
- Memory & skills: the files and skills each runtime actually loaded
- Health & logs: disk, memory, error rates, rate limits, live log stream
- Alerts: budget caps, error spikes, agent-offline, routed to Slack, Discord, PagerDuty, Telegram, Email
- Approvals: pause risky tool calls before they run and approve from your phone (how)
| Plan | What it covers | Price |
|---|---|---|
| Free | OpenClaw + NVIDIA NemoClaw, full dashboard, local only | $0 |
| Starter | Every other runtime above, fleet view, cloud sync | $9 per node / month |
| Pro | Starter + governance: approvals, tool-risk policies, evals, anomaly detection, cost optimizer, OTel export | $19 per node / month |
Annual plans, Enterprise and the current numbers live at
clawmetry.com/pricing. Self-hosted license
keys work without the cloud (clawmetry license). The exact free/paid split is
in docs/ENTITLEMENTS.md.
ClawMetry reads local session files and logs. Nothing leaves your box unless
you run clawmetry connect. Even then the snapshot is end-to-end encrypted
with a key that never leaves your machine, and decrypted in your browser.
pip install clawmetry # then: clawmetryOr the one-liner: curl -sSL https://raw.githubusercontent.com/vivekchand/clawmetry/main/install.sh | bash
Needs Python 3.8+ on macOS, Linux or Windows, and at least one agent runtime on the same machine. Docker instructions: docs/DOCKER.md.
| Runtime compatibility | What each adapter reads, and how to add a runtime |
| Entitlements | Free vs paid, tier matrix, license CLI |
| Approvals & policies | Pre-execution gating, risk scoring, phone approvals |
| OpenTelemetry | Export traces anywhere, ingest OTLP from anything |
| SDK tracking | Cost attribution for agents you built yourself |
| Chat channels | The chat adapters shown in Flow |
| NemoClaw / OpenShell | Sandboxed NVIDIA NemoClaw setups |
| Docker | Image, compose, volume mounts |
| Architecture · Development | How it works inside; running from source |
| Telemetry | The anonymous install ping, and how to turn it off |
![]() |
![]() |
| Overview: tokens, sessions, health | Brain: live agent event stream |
![]() |
![]() |
| Cost: by model and session | Approvals: gate risky tool calls |
More, per runtime: docs/RUNTIME_SCREENSHOTS.md.
MIT · Built by @vivekchand · clawmetry.com




