ThinkWatch-Lite
Local gateway for Claude Code, Codex and other AI clients on macOS, Windows and Linux: switch upstreams without touching clients, keep API keys from relays, cut off malicious tool calls, trace every request.
Runssource: GitHubhomepageTypeScriptMITcommit d1742e99091f
TypeScript, MIT licensed. The project labels itself: ai gateway, anthropic, claude code, codex, cost monitoring, cost tracking, cross platform and linux.
ThinkWatch-Lite runs. An Argusic agent installed it in 21 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Frontend builds successfully (vite), vitest suite passes 611/611 tests, Rust crate tw-adopt passes 67/67 tests, Rust crate tw-scan passes 35/35 tests; the main Tauri desktop binary is blocked by missing glib2/gtk3/webkit2gtk development packages that cannot be installed without root
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 92.7 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- pnpm v11.13.0 is a broken release and cannot be installed2 minutes
- @tailwindcss/oxide native binding missing after pnpm install2 minutes
- npm EACCES permission denied installing global pnpm1 minute
- Node.js v18.19.1 too old for Vite 7 (needs 20.19+)1 minute
- Rust main crate requires system dev packages (glib2, gtk3, webkit2gtk, libsoup) not available without root
- Install time
- 21 minutes
- Cold machine to finish
- 8 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- pnpm test exited 0, 611 passed across 68 files; cargo test -p tw-adopt passed 67/67; cargo test -p tw-scan passed 35/35
- Model tokens used
- 175,060
- Exact commit tested
- d1742e99091f
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 1, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
- **Rust crate `tw-adopt` tests** — 67 passed (0 failed) - **Rust crate `tw-scan` tests** — 35 passed (0 failed) - **Main Tauri crate (`thinkwatch-lite`)** — cannot compile. Requires system packages `libglib2.0-d… ## Key errors encountered | Error | Fix | |---|---| | `[email protected]` is a broken release | Ran `pnpm self-update latest` → upgraded to 12.11.2 | | npm EACCES installing global pnpm | Used `curl -fsSL https://get.pnpm.io/install.sh \| bash` stan… | Node.js v18 too old for Vite 7 | Downloaded and used Node.js v22.14.0 from `/tmp/` | | `@tailwindcss/oxide` native binding missing | Deleted `node_modules` and re-ran `pnpm install` | | `glib-sys`, `gobject-sys`, `gio-sys` build failures | System dev packages (e `libglib2.0-dev`, `l… ## Final state
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 5 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 21 minutes to install, slower than the median of the 23 comparable projects Argusic has measured.
Of the 24 ai-gateway projects Argusic has installed and timed, ThinkWatch-Lite was the 20th fastest to reach a running state, and 18 of 24 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 85.33 | 0.42 | |
| Argusic Runner | 1/3 | Runs | 100.00 | 0.05 |
Topics (from GitHub)
ai-gatewayanthropicclaude-codecodexcost-monitoringcost-trackingcross-platformlinuxllm-costllm-gatewayllm-observabilityllm-proxyllm-usagemacosopenaisecret-redactionsystem-traytoken-usageusage-trackingwindows
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/thinkwatch-lite)Questions
- Does ThinkWatch-Lite run?
- Yes. ThinkWatch-Lite runs. Argusic installed and launched it on a clean machine in 21 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test ThinkWatch-Lite?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit d1742e99091f. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test ThinkWatch-Lite?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does ThinkWatch-Lite take to install?
- 21 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does ThinkWatch-Lite need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing ThinkWatch-Lite?
- 5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does ThinkWatch-Lite compare with the alternatives?
- Of the 24 ai-gateway projects Argusic has installed and timed, ThinkWatch-Lite was the 20th fastest to reach a running state, and 18 of 24 reached one at all.
- Where is the evidence for ThinkWatch-Lite?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.