omnara
The open-source alternative to Claude Managed Agents
Runssource: GitHubhomepageGoApache-2.0commit 7435b5995514
Go, Apache-2.0 licensed. The project labels itself: agent infrastructure, coding agents, durable agents and managed agents.
omnara runs. An Argusic agent installed it in 35 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Omnara builds, all 124 unit test packages pass, all 34 integration test packages pass against live PostgreSQL 18 + Redis 7 + MinIO S3, all 4 server binaries build and the API binary starts and responds on port 8080, and the frontend web app builds successfully
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.
- go test ./internal/emailaddr/ failed: TestNormalize/capital_sharp_s_maps_per_UTS_46 expected [email protected] but got [email protected]2 minutes
- Install time
- 35 minutes
- Cold machine to finish
- 43 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- make unit: 124 Go packages passed with 0 failures; integration tests: ./internal/storage/, ./internal/dbmigrate/, ./internal/httpapi/, ./internal/harness/, ./internal/machinepool/, ./internal/modelprovider/, ./internal/notifications/, ./internal/redistore all passed with 0 failures; curl to localhost:8080 returned HTTP 404 for / and HTTP 401 for /api/v1/ confirming the API serves requests; frontend pnpm build completed in 50s producing dist/ with index.html
- Model tokens used
- 627,210
- Exact commit tested
- 7435b5995514
- 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.
setsid /tmp/omnara-api > /tmp/api.log 2>&1 &
sleep 2 && curl -s -o /dev/null -w \"%{http_code}\" http://127.0.0.1:8080/ && echo \"\" && \\
curl -s -o /dev/null -w \"%{http_code}\" http://127.0.0.1:8080/api/v1/ && echo \"\"" in /work/repo
succeeded in 1886ms:
404
401
Here's the final report.
2026-09-17T22:59:18.899325Z ERROR codex_core::session: failed to record rollout items: thread 01a0b…
2026-09-17T22:59:18.899879Z ERROR codex_core::session: failed to record rollout items: thread 01a0b…
tokens used
627,210
Here's the final report.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 35 minutes.
- Recovered from all 1 error 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 2 times, so the result is not a one-off.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Run history
Topics (from GitHub)
agent-infrastructurecoding-agentsdurable-agentsmanaged-agents
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/omnara)Questions
- Does omnara run?
- Yes. omnara runs. Argusic installed and launched it on a clean machine in 35 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test omnara?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7435b5995514. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test omnara?
- The run that produced this verdict cost $0.27: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does omnara take to install?
- 35 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 omnara need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing omnara?
- 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.
- Where is the evidence for omnara?
- 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.