Observability and per-edit history for Lovable
Lovable's agent builds your app in the cloud. Its GitHub sync writes one commit per accepted edit, and ClawMetry turns your local clone of that repo into a per-edit activity timeline: who prompted what, and when, with zero config.
All 30 runtimes ClawMetry observes
Lovable is one of them; the other 29 are listed below. Free on every plan: OpenClaw, NVIDIA NemoClaw, Goose. Paid on Cloud Pro or Self-Hosted Pro: the rest.
What ClawMetry sees on Lovable
Point ClawMetry at the machine that holds your clones of Lovable's GitHub-synced repos, and each project shows up as:
- A per-edit timeline: Lovable writes one commit per accepted edit, so every accepted change appears as its own event, in order, with its timestamp.
- Who prompted what: each edit carries its author attribution, so on a shared project you can see which teammate accepted which change.
- Projects as sessions: one session per Lovable project, with first and last activity, total accepted edits, and the files each edit touched.
- Edit cadence: bursts and quiet stretches per project, so you can tell an afternoon of heavy prompting from a project nobody has touched in a week.
- The same dashboard as the rest of your fleet: Lovable projects sit next to your Claude Code, Cursor and OpenClaw sessions, in one place.
git fetch of the synced repo.
Rejected drafts never reach the repo, so only accepted edits appear.
ClawMetry observes only; it cannot pause or stop a Lovable agent.
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.cmdAlready have Python? pip works too; onboard is the interactive first-run wizard.
# Any OS with Python 3.9+
pip install clawmetry && clawmetry onboardOr skip the terminal entirely and grab the desktop app: macOS (.dmg) · Windows (.exe) · Linux (.AppImage). It installs and updates ClawMetry for you.
2. Clone your Lovable project and run the daemon
clawmetryConnect your Lovable project to GitHub (Lovable's built-in sync), clone the repo where ClawMetry runs, and the daemon picks it up. No env var, no config.
3. Open the dashboard
Open http://localhost:8900. Switch the runtime chip to Lovable.
Start the free trial →The one thing this catches that Lovable alone does not
Lovable shows you a project one editor tab at a time. ClawMetry shows you every Lovable project on the machine at once, as a flat history of accepted edits with names and timestamps. When something in the app broke on Thursday, you can scroll to Thursday and read exactly which accepted edits landed that day, and who accepted them, without opening the cloud editor at all.
It is an audit trail, not a meter. Spend stays in Lovable's own credit ledger, and this page will not pretend otherwise.
Starred by the people building AI
Engineers and founders from OpenAI, Google, PostHog and more have starred ClawMetry on GitHub. One of them helped build it.
