open-vetta
Open-source, local-first AI agent for coding and real work. BYOK models, MCP, skills, plugins, workflows, and private knowledge bases.
Runssource: GitHubhomepageTypeScriptApache-2.0commit fa6c1df3a28d
TypeScript, Apache-2.0 licensed. The project labels itself: agent tools, ai agent, byok, coding agent, cross platform, desktop app, developer tools and electron.
open-vetta runs. An Argusic agent installed it in 3 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Open Vetta monorepo installs, builds (CLI, all library packages, 14 presets), lints, passes all architecture guards, and runs the vetta CLI binary. Test suites across 39 packages pass with 2870+ passing tests covering AI providers, agent loop, runtime-core, coding-agent, MCP, storage, tools, subagents, agent-team, remote control, ecosystem hooks, skill presets, capability SDK, and all plugin presets (content-creation...
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 runtime not pre-installed; Node.js 18.x instead of required 20+2 minutes
- theme-ui: 2 E2E markdown-link tests fail due to require() of ESM unified module from CJS react-markdown
- Desktop tsc type-checking runs out of memory (773MB limit, ~2GB needed)
- Docs-site build fails: Next.js Turbopack loader fails on fumadocs-mdx ESM/CJS boundary
- Vite requires Node 22.12+ (we have 22.11.0) but builds still succeed for all 14 presets
- Install time
- 3 minutes
- Cold machine to finish
- 15 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- node apps/cli-host/dist/cli.js --version returned 0.0.1; node apps/cli-host/dist/cli.js agent --help returned help/usage text; bun run check:lint passed 4327 files; bun run check:guards passed all 16 checks; bun run test:quality passed 287/287; all 28 testable package suites passed
- Model tokens used
- 415,795
- Exact commit tested
- fa6c1df3a28d
- 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.
[test:pkg] runtime-storage passed in 1.0s
Test Files 9 passed (9)
Tests 67 passed (67)
[test:pkg] runtime-knowledge passed in 1.3s
[test:pkg] duration summary (slowest first)
runtime-mcp 4.2s passed
runtime-knowledge 1.3s passed
runtime-storage 1.0s passed
Now let me compile the final results.
tokens used
415,795
Now let me compile the final results.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 Apache-2.0, as reported by its host.
What did not, or is not known
- Took 3 minutes to install, slower than the median of the 6 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 7 agent-tools projects Argusic has installed and timed, open-vetta was the 5th fastest to reach a running state, and 4 of 7 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 3 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)
agent-toolsai-agentbyokcoding-agentcross-platformdesktop-appdeveloper-toolselectronharnessknowledge-basellmwikilocal-firstmcpplugin-systemprivacy-firstskillstypescriptvettaworkflow-automation
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/open-vetta)Questions
- Does open-vetta run?
- Yes. open-vetta runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test open-vetta?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit fa6c1df3a28d. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test open-vetta?
- 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 open-vetta take to install?
- 3 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 open-vetta need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing open-vetta?
- 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 open-vetta compare with the alternatives?
- Of the 7 agent-tools projects Argusic has installed and timed, open-vetta was the 5th fastest to reach a running state, and 4 of 7 reached one at all.
- Where is the evidence for open-vetta?
- 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.