browser-ai
In-browser AI model providers for the Vercel AI SDK, built to make client-side AI integration simpler and more consistent across vendors.
Runssource: GitHubhomepageTypeScriptNOASSERTIONcommit a53509d4f923
TypeScript, NOASSERTION licensed. The project labels itself: ai, ai sdk, browser, browser ai, built in ai, chrome ai, edge and inference.
browser-ai runs. An Argusic agent installed it in 18 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
All 4 @browser-ai packages build with tsup and all 330 tests pass on Node 18.19.1
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 98 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.
- [email protected] requires Node >= 20 (container has 18.19)8 minutes
- [email protected] requires Node >= 203 minutes
- [email protected] requires Node >= 202 minutes
- Install time
- 18 minutes
- Cold machine to finish
- 23 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- Ran vitest run in each of the 4 package directories: shared (69 passed), core (141 passed), transformers-js (51 passed), web-llm (69 passed), 330 total tests passed
- Model tokens used
- 96,857
- Exact commit tested
- a53509d4f923
- 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.
**Errors encountered and fixed**: 1. **`[email protected]` requires Node >= 20** — all 4 packages declared `vitest: "^4.1.0"` and `"@vitest/… 2. **`[email protected]` requires Node >= 20** — all 4 packages used `jsdom: "^28.1.0"` for vitest's jsdom… 3. **`[email protected]` requires Node >= 20** — the hoisted vite version (6.4.3) was pulled in by vitest 3.… **Verified testing output**: ``` @browser-ai/shared: 2 test files passed, 69 tests passed @browser-ai/core: 7 test files passed, 141 tests passed @browser-ai/transformers-js: 6 test files passed, 51 tests passed @browser-ai/web-llm: 4 test files passed, 69 tests passed ``` **Total: 19 test files, 330 tests — all passing.**
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.
- Installed in 18 minutes.
- Recovered from all 3 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.
- Measured 4 times, so the result is not a one-off.
What did not, or is not known
- Its license file could not be classified automatically, so check it yourself before using it.
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
Topics (from GitHub)
aiai-sdkbrowserbrowser-aibuilt-in-aichrome-aiedgeinferencellmtransformer-modelstransformerstransformers-jsvercelwebllm
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/browser-ai)Questions
- Does browser-ai run?
- Yes. browser-ai runs. Argusic installed and launched it on a clean machine in 18 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test browser-ai?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit a53509d4f923. 4 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test browser-ai?
- The run that produced this verdict cost $0.14: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does browser-ai take to install?
- 18 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 browser-ai need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing browser-ai?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for browser-ai?
- All 4 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.