How do I monitor Aider chats?

Install ClawMetry (pip install clawmetry). The daemon auto-detects Aider and renders every chat, edit, model, and token in one dashboard at http://localhost:8900.

Does ClawMetry track Aider cost per model?

Yes. Aider swaps between models (Sonnet, GPT-4o, DeepSeek, Ollama) via /model; every turn is labelled with the model id and the Cost tab shows per-model spend, per-chat and per-hour rollups. Ollama and other local models are labelled and priced at $0 so you see local-vs-paid coverage clearly.

Can I see which files Aider edited most and what they cost me?

Yes. Aider's history includes the file-edit sequence per turn; ClawMetry surfaces a per-file edit tree so you can see the top-edited files, per-file token spend, and whether a chat is stuck regenerating the same file.

Does ClawMetry work with Aider's architect + editor split?

Yes. Aider's architect mode uses a stronger model for planning and a cheaper model for edits; ClawMetry labels each turn with its role (architect vs editor) so per-role cost is separable.

How much does ClawMetry cost for Aider?

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

Aider × ClawMetry

Observability and cost tracking for Aider

See every Aider chat, file edit, and token as it happens. ClawMetry detects Aider automatically and renders sessions, file-edit trees, tokens, and per-model cost in one dashboard. No SDK.

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

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

What ClawMetry sees on Aider

Once ClawMetry is running, your Aider 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: Per-turn token counts from Aider's history side-cars (Anthropic and OpenAI shapes both handled).
Cost per session, per model, per hour: cache-aware where the model supports caching.
Per-file edit attribution (which chat turn touched which file and what it cost): the Aider-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 Aider 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 Aider.

Start the free trial →

The one thing this catches that Aider alone does not

Left alone, Aider's failure mode is a chat that keeps regenerating the same file across many turns without you noticing. ClawMetry watches for it: cost per hour on the Aider 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.