Sico
An open-source Digital Worker platform for reliable execution, continuous co-evolution, and building Enterprise AI assets.
Runs with mockssource: GitHubPythonMITcommit ee477dd874c5
Python, MIT licensed. The project labels itself: agent evolution, agent framework, agent management, agent platform, ai agent, bpo, co evolution and digital worker.
Sico runs, with stand-ins for the services it depends on. An Argusic agent installed it in 4 minutes and hit 7 errors on a clean machine with no GPU, and the whole session was recorded.
Core Python service tests pass (1564/1564), Go backend builds and passes 44 test packages, frontend SPA builds and app tests pass (161/161).
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 89.1 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.
- Go compiler not found2 minutes
- Python 3.12 installed, requires >=3.131 minute
- Missing @tailwindcss/oxide native binary for linux-x64-gnu1 minute
- uv not found
- pnpm not found
- Node v18.19.1 does not match required v24.13.0
- Install time
- 4 minutes
- Cold machine to finish
- 44 minutes
- Errors hit and fixed
- 7 hit, 6 fixed with no human help
- How the result was proved
- cd core && uv run pytest: 1564 passed, 23 skipped; cd backend && go test ./...: 44 packages passed; cd frontend && pnpm build: built; cd frontend/packages/app && pnpm test: 26 files, 161 passed; cd backend && go build ./cmd/sico-server: binary created
- Model tokens used
- 659,498
- Exact commit tested
- ee477dd874c5
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
| Backend test suites | `go test ./...` — 44 packages passed, 0 failed | | Frontend (Node 24/pnpm) deps | `pnpm install --frozen-lockfile` — all deps installed | | Frontend build | `pnpm build` — SPA built to `packages/app/dist/` | | Frontend app tests | `pnpm test` — 26 test files, 161 tests passed | **Issues fixed:** - Installed Python 3.13 (was 3.12), Go 1.23 (was missing), uv (was missing), Node 24.13.0 (was 18.1… - Added `@tailwindcss/oxide-linux-x64-gnu` to fix native binary loading on this glibc **Remaining notes:** - Backend server binary builds but requires MySQL/Redis at startup (expected for a compose-based st… - Frontend `shared` package tests (3525 tests) hang in this environment (environment limitation, no… - Docker Compose stack cannot run (no Docker in container), so full E2E verification is excluded - No real LLM API keys available; mocks/stubs used throughout core tests
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 4 minutes.
- Licensed MIT, as reported by its host.
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.
- Hit 7 errors during setup, 1 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
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 | 1/3 | Runs with mocks | 89.14 | 0.26 |
Topics (from GitHub)
agent-evolutionagent-frameworkagent-managementagent-platformai-agentbpoco-evolutiondigital-workerenterprise-agentsharness-evolutionhuman-in-the-loopllmproduction-ai
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/sico)Questions
- Does Sico run?
- Sico runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 4 minutes, hitting 7 errors on the way, and recorded the session.
- How did Argusic test Sico?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit ee477dd874c5. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test Sico?
- The run that produced this verdict cost $0.26: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does Sico take to install?
- 4 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 Sico need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing Sico?
- 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 Sico?
- 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.