openbrowser
Let AI agents browse the web. An autonomous toolkit for browser-based AI agents.
Runssource: GitHubTypeScriptMITcommit 067fc45d649b
TypeScript, MIT licensed. The project labels itself: ai agents, automation, claude, playwright, puppeteer and sandbox.
openbrowser runs. An Argusic agent installed it in 7 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Bun 1.4.2 installed, all 42 npm dependencies resolved, TypeScript builds pass for all 3 packages, 364/364 core tests pass, CLI prints help/version correctly, and a headless Playwright browser opens and navigates to https://example.com/
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 100 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.
- Bun not available in container; npm install -g bun failed (EACCES, can't write to /usr/local/lib)4 minutes
- Playwright browser not found at /home/runner/.cache/ms-playwright/chromium_headless_shell-12082 minutes
- Install time
- 7 minutes
- Cold machine to finish
- 8 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- bun test in core package: 364 pass, 0 fail. CLI: open-browser --version returned 0.1.0. open-browser open https://example.com --headless created session and navigated to URL
- Model tokens used
- 84,434
- Exact commit tested
- 067fc45d649b
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
**Launch**: The CLI works. `bun run packages/cli/src/index.ts --help` renders all commands. `bun ru… **Tests**: `bun test` in the core package — **364 pass, 0 fail**, 894 expect calls across 10 files.… **Errors encountered**: None in the final state. The only friction was installing bun itself and Pl… 2026-09-27T16:23:50.771971Z ERROR codex_core::session: failed to record rollout items: thread 01a0e… 2026-09-27T16:23:50.772260Z ERROR codex_core::session: failed to record rollout items: thread 01a0e… tokens used 84,434 Here's the complete verified report: **Install**: `bun install` succeeded (42 packages), `bun run build` (type check) passed with exit c… **Launch**: The CLI works. `bun run packages/cli/src/index.ts --help` renders all commands. `bun ru… **Tests**: `bun test` in the core package — **364 pass, 0 fail**, 894 expect calls across 10 files.… **Errors encountered**: None in the final state. The only friction was installing bun itself and Pl…
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 2 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.
What did not, or is not known
- Took 7 minutes to install, slower than the median of the 24 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 25 ai-agents projects Argusic has installed and timed, openbrowser was the 15th fastest to reach a running state, and 16 of 25 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.
- A quick evaluation: it was running 7 minutes after the clone.
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
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/openbrowser)Questions
- Does openbrowser run?
- Yes. openbrowser runs. Argusic installed and launched it on a clean machine in 7 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test openbrowser?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 067fc45d649b. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test openbrowser?
- The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does openbrowser take to install?
- 7 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 openbrowser need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing openbrowser?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does openbrowser compare with the alternatives?
- Of the 25 ai-agents projects Argusic has installed and timed, openbrowser was the 15th fastest to reach a running state, and 16 of 25 reached one at all.
- Where is the evidence for openbrowser?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.