open-multi-agent
Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it.
Runs with mockssource: GitHubhomepageTypeScriptMITcommit dcffce18c8ad
TypeScript, MIT licensed. The project labels itself: agent framework, agent orchestration, agentic ai, ai agents, ai governance, anthropic, claude and claude code.
open-multi-agent runs, with stand-ins for the services it depends on. An Argusic agent installed it in 0.5 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The monorepo installs, builds, passes 2350 unit tests across all 4 workspaces plus the benchmark harness, and the CLI prints help, all with Node.js 22, no API keys or network required.
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 92 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.
- Node.js v18.19.1 is installed but the project requires >=200.2 minutes
- Install time
- under a minute
- Cold machine to finish
- 4 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- npm test exited 0, 2207 passed (core) + 31 (scaffold) + 17 (otel) + 59 (release-bot) + 36 (bench) = 2350 total tests passed; lint and build also passed; oma CLI help printed
- Model tokens used
- 29,202
- Exact commit tested
- dcffce18c8ad
- 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
- Behaviour against real services
- this run was verified against stand-in services only
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 1, run . 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.
- **Lint**: `npm run lint` passed across all 4 workspaces + bench. - **CLI**: `oma help` prints the full usage tree. The one error was the stale Node.js 18 runtime, fixed by upgrading to 22.14.0. No API keys were nee… tokens used 29,202 All checks pass. Here's the summary: - **Install + build**: `npm ci` (304 packages) and `npm run build` (typeScript compilation across a… - **Node.js**: Upgraded from v18.19.1 to v22.14.0 via `npx n` (the repo requires >=20). - **Tests**: `npm test` — 2350 tests passed across all workspaces and the benchmark suite. - **Lint**: `npm run lint` passed across all 4 workspaces + bench. - **CLI**: `oma help` prints the full usage tree. The one error was the stale Node.js 18 runtime, fixed by upgrading to 22.14.0. No API keys were nee…
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 0.5 minutes, faster than the median of the 62 comparable projects Argusic has measured.
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
- Measured 3 times, so the result is not a one-off.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
Of the 63 agent-framework projects Argusic has installed and timed, open-multi-agent was the 8th fastest to reach a running state, and 50 of 63 reached one at all.
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 with mocks | 92.00 | 0.02 | |
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.02 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.03 |
Topics (from GitHub)
agent-frameworkagent-orchestrationagentic-aiai-agentsai-governanceanthropicclaudeclaude-codedeepseekgeminillmlocal-llmmcpmulti-agentobservabilityollamaopenaiself-hostedtypescript
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/open-multi-agent)Questions
- Does open-multi-agent run?
- open-multi-agent runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 1 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test open-multi-agent?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit dcffce18c8ad. 3 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test open-multi-agent?
- 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 open-multi-agent take to install?
- 0.5 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-multi-agent need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing open-multi-agent?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does open-multi-agent compare with the alternatives?
- Of the 63 agent-framework projects Argusic has installed and timed, open-multi-agent was the 8th fastest to reach a running state, and 50 of 63 reached one at all.
- Where is the evidence for open-multi-agent?
- 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.