OpenBot
Open-source AI coworkers that each get a computer of their own: a browser, files and tools, with every action decided before it happens and recorded after. Bring any AG-UI agent.
Could not verifysource: GitHubhomepageTypeScriptMITcommit 3c73cf00efba
TypeScript, MIT licensed. The project labels itself: ag ui, agent governance, ai agents, browser automation, copilotkit, generative ui and mcp.
Argusic could not get OpenBot running. An Argusic agent installed it in 6 minutes and hit 7 errors on a clean machine with no GPU, and the whole session was recorded.
bun install and all 3985 non-integration unit tests pass. The 69 failures are all infrastructure-gated (no PostgreSQL for integration tests, no Docker for compose tests, 2 pre-existing Mastra .env leakage failures).
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 77.1 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 installed3 minutes
- agent-mastra dependencies missing2 minutes
- agent-bot dependencies missing (@ag-ui/encoder, openai)1 minute
- agent-computer dependencies missing (playwright)1 minute
- agent-langgraph dependencies missing1 minute
- Docker not available (compose tests fail)
- Install time
- 6 minutes
- Cold machine to finish
- 49 minutes
- Errors hit and fixed
- 7 hit, 6 fixed with no human help
- How the result was proved
- bun test ran 4081 tests across 386 files: 3985 pass, 27 skip, 69 fail. The 69 failures break down as: 63 integration-test errors (no PostgreSQL), 2 test-database-url failures (no PostgreSQL), 1 compose test failure (no Docker), 3 tests/smoke skipped (no deployment). 3 agent-bot tests fixed by installing missing workspace deps. Typecheck (tsc --noEmit) passes for server.
- Model tokens used
- 218,305
- Exact commit tested
- 3c73cf00efba
- 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
- Whether it works at all
- this run verified nothing, so this page makes no claim either way
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
succeeded in 391ms: bun test v1.4.2 (744846f84) tests/agent-bot.test.ts: (pass) agent-bot refuses to start when the model key is empty [77.56ms] (pass) agent-bot still refuses to start without its server token [65.61ms] (pass) agent-bot refuses a model it cannot drive however the name is spaced [199.95ms] 3 pass 0 fail 10 expect() calls Ran 3 tests across 1 file. [533.00ms] tokens used 218,305
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
- Installed in 6 minutes.
- 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
- An agent with no time limit did not get it running.
- Hit 7 errors during setup, 1 of which were not solved.
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 | Unverified | 77.14 | 0.33 | |
| Argusic Runner | 1/3 | Ran out of time | 0.00 | 0.28 |
Topics (from GitHub)
ag-uiagent-governanceai-agentsbrowser-automationcopilotkitgenerative-uimcp
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/openbot)Questions
- Does OpenBot run?
- Argusic could not verify that OpenBot runs. Argusic installed and launched it on a clean machine in 6 minutes, hitting 7 errors on the way, and recorded the session.
- How did Argusic test OpenBot?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 3c73cf00efba. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test OpenBot?
- The run that produced this verdict cost $0.33: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does OpenBot take to install?
- 6 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 OpenBot need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing OpenBot?
- 7 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for OpenBot?
- 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.