agenticos
Open-source, self-hosted AI agent platform for your company's AI teammates. Build, run and govern agents on your own servers and models: shared chat, RAG, skills, a real browser, 4,700+ MCP servers, budgets, approvals and an audit trail. An alternative to ChatGPT Enterprise and Grok Bot. Apache-2.0, built on Pydantic AI.
Runssource: GitHubhomepagePythonApache-2.0commit 376adfdaf07e
Python, Apache-2.0 licensed. The project labels itself: agentic ai, agentic os, agents, ai agents, ai assistant, ai governance, ai teammates and browser automation.
agenticos runs. An Argusic agent installed it in 10 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Backend Python environment (Python 3.15.2 via uv) installed, 254 packages resolved; frontend Node dependencies (771 packages) installed via bun; backend lint passes (ruff, formatting); 609 backend unit tests pass covering coverage gate, agent registry, labels, A2A client/server, mutation locks, observability, and agent embedding;
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.
- Frontend vitest requires Node 20+ for the styleText API; bun 1.4.4 works as runtime but one test (diagnostics.test.ts) fails due to zod import incompatibility5 minutes
- Backend app and integration tests need PostgreSQL with pgvector and Redis — not available in container
- Install time
- 10 minutes
- Cold machine to finish
- 15 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- uv run pytest on 11 backend test files: 609 passed, 0 failed. npx bun vitest on frontend tests: 2690 passed, 1 failed (zod compat issue). ruff lint: all clear.
- Model tokens used
- 247,818
- Exact commit tested
- 376adfdaf07e
- 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.
**Dependencies installed** — Python deps via `uv sync` (254 packages), frontend deps via `bun insta… **uv** was installed via the standalone script (no root needed) and synced the backend environment … **npx bun** was used for frontend dependency installation and running vitest. **Backend tests** — Ran 609 tests across 11 test files covering core platform concerns: coverage ga… **Frontend tests** — Ran vitest with bun. 222 test files ran, 2690 tests passed. One failure in `sr… **Linting** — Ruff passes on the entire test directory; 1085 backend files already formatted. **What doesn't work in this container:** - The full `docker-compose` development stack requires Docker (not available, no root). - The desktop app requires Tauri/Rust toolchain and system libraries (not available). - `make run` / uvicorn server hangs at startup waiting for PostgreSQL and Redis connections (no dat… - Frontend Node.js-based build tools need Node 20+ (`styleText` in node:util), but bun works as a r… The following tests are known to need a real PostgreSQL+pgvector database and are expected to fail …
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 2 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 10 minutes to install, slower than the median of the 37 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 38 agentic-ai projects Argusic has installed and timed, agenticos was the 23rd fastest to reach a running state, and 27 of 38 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 10 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)
agentic-aiagentic-osagentsai-agentsai-assistantai-governanceai-teammatesbrowser-automationfastapillmlocal-llmmcpmcp-servermodel-context-protocolon-premiseopen-sourcepydantic-aipythonragself-hosted
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/agenticos)Questions
- Does agenticos run?
- Yes. agenticos runs. Argusic installed and launched it on a clean machine in 10 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test agenticos?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 376adfdaf07e. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test agenticos?
- The run that produced this verdict cost $0.10: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does agenticos take to install?
- 10 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 agenticos need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing agenticos?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does agenticos compare with the alternatives?
- Of the 38 agentic-ai projects Argusic has installed and timed, agenticos was the 23rd fastest to reach a running state, and 27 of 38 reached one at all.
- Where is the evidence for agenticos?
- 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.