Does nanobrowser run?

Yes. nanobrowser runs. Argusic installed and launched it on a clean machine in 15 minutes, hitting 2 errors on the way, and recorded the session.

How did Argusic test nanobrowser?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit 24a14b76e14a. 3 attempts are recorded, and the full method is on the methodology page.

What did it cost to test nanobrowser?

The run that produced this verdict cost $0.10: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.

How long does nanobrowser take to install?

14.8 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 nanobrowser need a GPU?

Not to start. Argusic reached a running state on a machine with no GPU.

What goes wrong when installing nanobrowser?

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.

Where is the evidence for nanobrowser?

All 3 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.

nanobrowser

Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Alternative to OpenAI Operator.

Runssource: GitHub homepageTypeScriptApache-2.0commit 24a14b76e14a

TypeScript, Apache-2.0 licensed. The project labels itself: agent, ai, ai agents, ai tools, automation, browser, browser automation and browser use.

nanobrowser runs. An Argusic agent installed it in 14.8 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Dependencies installed, project builds to dist/ (background.iife.js 1,848.81 kB, manifest.json), TypeScript type-check passes across all 15 packages, unit tests pass (14/14).
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 90.7 of 100 (the mean of this project's run scores).

At a glance

verdict: Runs
Argusic Score: 90.7 / 100
cost of the verifying run: $0.10 (measured)
recorded runs: 3
last tested: 2026-09-22
stars: 13,826
forks: 1,461
open issues: 83
watchers: 70
size: 1 MB
created: 2024-12-31
last push: 2026-08-18

Subject data from GitHub, linked at the top of this page, refreshed 2026-09-23. 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.

Time lost to each failure while testing nanobrowser, drawn from the recorded run — Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

chrome-extension/src/background/agent/helper.ts: ChatLlama overrode completionWithRetry on ChatOpenAI, but @langchain/openai v0.6.16 delegates this method to internal ChatOpenAICompletions instance, so the method doesn't exist on ChatOpenAI's type5 minutes
packages/schema-utils/index.ts exported non-existent modules './lib/json_gemini' and './lib/helpers' which don't exist in lib/3 minutes

Install time: 15 minutes
Cold machine to finish: 15 minutes
Errors hit and fixed: 2 hit, 2 fixed with no human help
How the result was proved: pnpm -F chrome-extension test: 1 test file passed, 14 tests passed, 0 failed. pnpm type-check: 12/12 tasks successful. pnpm -F chrome-extension build: extension builds to dist/ with manifest.json and background.iife.js
Model tokens used: 710,590
Exact commit tested: 24a14b76e14a
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 2, run 2026-09-11. The verdict above comes from a different attempt, so read this as one session and not as the current result. 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.

 Test Files  1 passed (1)
      Tests  14 passed (14)
   Start at  22:31:03
   Duration  319ms (transform 65ms, setup 0ms, collect 176ms, tests 8ms, environment 0ms, prepare 3…
=== TYPE-CHECK STATUS ===
 Tasks:    12 successful, 12 total
Cached:    0 cached, 12 total
  Time:    9.223s
All tasks verified. Here's the summary:
tokens used
710,590
All tasks verified. Here's the summary:

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 Apache-2.0, as reported by its host.
Measured 3 times, so the result is not a one-off.

What did not, or is not known

Took 14.8 minutes to install, slower than the median of the 32 comparable projects Argusic has measured.

Of the 33 agent projects Argusic has installed and timed, nanobrowser was the 24th fastest to reach a running state, and 25 of 33 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	3/3	Runs	100.00	0.10	2026-09-22 22:31 UTC
Argusic Runner	2/3	Runs with mocks	92.00	0.10	2026-09-11 11:10 UTC
Argusic Runner	1/3	Unverified	80.00	0.11	2026-09-11 10:36 UTC

Topics (from GitHub)

agent ai ai-agents ai-tools automation browser browser-automation browser-use chrome-extension comet dia extension manus mariner multi-agent n8n nano opensource playwright web-automation

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/nanobrowser.svg)](https://argusic.com/subject/nanobrowser)

Questions

Does nanobrowser run?: Yes. nanobrowser runs. Argusic installed and launched it on a clean machine in 15 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test nanobrowser?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit 24a14b76e14a. 3 attempts are recorded, and the full method is on the methodology page.
What did it cost to test nanobrowser?: The run that produced this verdict cost $0.10: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does nanobrowser take to install?: 14.8 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 nanobrowser need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing nanobrowser?: 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 nanobrowser compare with the alternatives?: Of the 33 agent projects Argusic has installed and timed, nanobrowser was the 24th fastest to reach a running state, and 25 of 33 reached one at all.
Where is the evidence for nanobrowser?: All 3 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.