How do I monitor LangChain Deep Agents?

Install ClawMetry (pip install clawmetry). The daemon auto-detects Deep Agents and renders every run, tool call, and per-node token in one dashboard at http://localhost:8900. Decoded read-only.

Does ClawMetry show the full nested sub-agent tree?

Yes. Deep Agents nests agents multiple levels deep; ClawMetry renders the full tree with per-node token totals rolled up under each parent. A parent that spawns 4 nested sub-agents that each burn 50k tokens shows the 200k total under the parent, not four separate mysteries.

Which Deep Agents providers does ClawMetry cover?

All of them. Deep Agents can route to Anthropic, OpenAI, Groq, local models via Ollama, or any LangChain-compatible provider; ClawMetry normalises every turn to input, output, cache, and reasoning tokens regardless of provider, so cost is comparable across them.

Is ClawMetry safe to point at a running Deep Agents install?

Yes. ClawMetry only observes. It never writes to Deep Agents state, and it cannot change how your agents run.

How much does ClawMetry cost for Deep Agents?

Free forever on your own machine. Cloud starts at $9/node/mo (Starter) or $19/node/mo (Pro).

Deep Agents × ClawMetry

Observability and cost tracking for LangChain Deep Agents

See every Deep Agents run, tool call, and token as it happens. ClawMetry detects Deep Agents automatically and renders runs, tool trees, tokens, and per-provider cost in one dashboard.

Supported runtime Zero config, auto-detected Read-only Free trial Official Deep Agents site ↗

📦 631k+ installs 🌍 128+ countries ⭐ 392 on GitHub 🏆 #5 Product Hunt

What ClawMetry sees on Deep Agents

Once ClawMetry is running, your Deep Agents activity shows up as:

Sessions: started at, last activity, model, message count, per-session token totals.
Live activity: every tool call as it lands, with args and result. Turn-level tokens split.
Per-turn tokens: input, output, and cached tokens per turn, rolled up per run and per agent.
Cost per session, per model, per hour: cache-aware where the model supports caching.
Sub-agent-of-sub-agent trees (Deep Agents nests LangGraph agents multiple levels deep): the Deep Agents-specific signal ClawMetry surfaces that generic dashboards do not.
Approval and kill switch: watch for token-maxing signals (message repeat, no-progress heuristic, cost-per-hour threshold), pause or kill before the next call.

Enable it in about two minutes

1. Install ClawMetry

Pick the line that matches your OS. Windows users: paste the install.cmd line, not the shell one.

# macOS or Linux
curl -fsSL https://clawmetry.com/install.sh | bash

# Windows (cmd.exe or PowerShell)
curl -fsSL https://clawmetry.com/install.cmd -o install.cmd && install.cmd

Already have Python? pip works too; onboard is the interactive first-run wizard.

# Any OS with Python 3.9+
pip install clawmetry && clawmetry onboard

Or skip the terminal entirely and grab the desktop app: macOS (.dmg) · Windows (.exe) · Linux (.AppImage). It installs and updates ClawMetry for you.

2. Run the daemon

clawmetry

The daemon auto-detects Deep Agents and starts reading immediately. No env var, no config, no runtime restart.

3. Open the dashboard

Open http://localhost:8900. Switch the runtime chip to Deep Agents.

Start the free trial →

The one thing this catches that Deep Agents alone does not

Left alone, Deep Agents's failure mode is a nested sub-agent that spawns its own sub-agents and quietly outspends the parent by 10x. ClawMetry watches for it: cost per hour on the Deep Agents runtime, message-repeat detection, and per-session token-growth curves. Set a threshold, and the approval queue pauses before the next call. Kill switch (Pro) stops it.