ouroboros
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.
Runs with mockssource: GitHubhomepagePythonMITcommit 55aa1aa9871d
Python, MIT licensed. The project labels itself: agent os, agentic ai, ai agent, ai coding agent, claude code, cli, codex and coding agent.
ouroboros runs, with stand-ins for the services it depends on. An Argusic agent installed it in 3 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
All unit tests pass (0 failures in ~21000 tests across 34 unit directories), ruff lint and format clean, CLI boots with correct version, MCP server help displays correctly, 2 Windows-specific bugs were caught and fixed.
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 88.7 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.
- Two Windows path-capacity unit tests fail on Linux: expected_artifacts=("nested/" + "a" * 200,) does not exceed 260 UTF-16 units on Linux because os.path.realpath("C:\...") produces a different length2 minutes
- Install time
- 3 minutes
- Cold machine to finish
- 73 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- uv run pytest tests/unit/ (all unit directories) all passed after applying fix; ruff format/check all clean; uv run ouroboros --version returned "Ouroboros version 0.1.dev1"
- Model tokens used
- 549,512
- Exact commit tested
- 55aa1aa9871d
- 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.
Final gated checks summary: **`ruff format`** — 1408 files already formatted **`ruff check`** — All checks passed **CLI boots** — `ouroboros --version` returned `Ouroboros version 0.1.dev1` **Tests fixed + verified** — 2 Windows-path tests repaired (`"a" * 200` → `"a" * 215`); all unit di… tokens used 549,512 Final gated checks summary: **`ruff format`** — 1408 files already formatted **`ruff check`** — All checks passed **CLI boots** — `ouroboros --version` returned `Ouroboros version 0.1.dev1` **Tests fixed + verified** — 2 Windows-path tests repaired (`"a" * 200` → `"a" * 215`); all unit di…
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 3 minutes.
- 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 4 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.
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 | 0.28 | |
| Argusic Runnerescalation | 1/3 | Runs with mocks | 85.33 | 2.23 | |
| Argusic Runner | 2/3 | Ran out of time | 0.00 | 0.11 | |
| Argusic Runner | 1/3 | Ran out of time | 0.00 | 0.19 |
Topics (from GitHub)
agent-osagentic-aiai-agentai-coding-agentclaude-codeclicodexcoding-agentdeepseekdeveloper-toolsdshdsh-pluginllm-evaluationllm-orchestrationloop-engineeringmcpopencodeskillskills
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/ouroboros)Questions
- Does ouroboros run?
- ouroboros runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 3 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test ouroboros?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 55aa1aa9871d. 4 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test ouroboros?
- The run that produced this verdict cost $0.28: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does ouroboros 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 ouroboros need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing ouroboros?
- 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 ouroboros?
- 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.