jentic-one
Self-hosted execution layer for AI agents: connect any agent to real APIs, scope exactly what it can touch, and keep credentials out of the agent's hands.
Runssource: GitHubhomepagePythonApache-2.0commit c8af96ea88a6
Python, Apache-2.0 licensed. The project labels itself: agent infrastructure, agent security, agentic, ai agents, api gateway, audit, claude and codex.
jentic-one runs. An Argusic agent installed it in 10 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Jentic One backend+borker run on local SQLite in this container; an admin created an agent and executed a real brokered call to httpbin.org/get (HTTP 200) while a non-allowed registered operation returned HTTP 403, and the unit, arch, and SQLite integration test suites pass.
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.
- UI build crashed on bundled Node v18.19.1 (node:util lacks styleText)2 minutes
- Rolldown native binding not installed under Node 22.11 (engine needs >=22.12)2 minutes
- uv tool missing; Python deps could not be installed1 minute
- Playwright browser missing for UI browser tests1 minute
- Local integration tests default to Postgres (unavailable without Docker)
- 1 of 2873 UI tests failed (SegmentedToggle pill width 64>0) under headless Chromium
- Install time
- 10 minutes
- Cold machine to finish
- 34 minutes
- Errors hit and fixed
- 6 hit, 6 fixed with no human help
- How the result was proved
- curl broker at http://127.0.0.1:8100/https://httpbin.org/get with agent bearer token returned HTTP 200 with httpbin body; /headers returned HTTP 403 action_denied. Suites: pytest tests/unit -n0 -> 6433 passed; tests/arch -> 346 passed; JENTIC_TEST_BACKEND=sqlite tests/integration -> 2076 passed; npm run test:run -> 2872 passed 1 failed. App /health and /app/ both HTTP 200.
- Model tokens used
- 773,393
- Exact commit tested
- c8af96ea88a6
- 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.
- Built the frontend SPA (`ui/dist`) and confirmed it's served at `/app` (HTTP 200); root 307-redir… **Errors I hit and fixed** (all environment/toolchain gaps, not repo defects): 1. Missing `uv` → installed portable to `~/.local/bin`. 2. UI build failed with Node 18 (`node:util` missing `styleText`) → used portable Node 24.4.1. 3. Rolldown native binding missing under Node 22.11 (engine `>=22.12.0` unsatisfied) → used Node 24… 4. Integration tests defaulted to unavailable Postgres → reran with `JENTIC_TEST_BACKEND=sqlite`. 5. Playwright browser missing for UI tests → `npx playwright install chromium`. 6. One UI test (`SegmentedToggle` pill-bounds) failed under headless Chromium (CSS rendering measur… **Gaps recorded:** Go toolchain (needed for the `jentic`/`jenticctl` CLIs) and Docker (needed for P… **test_depth** = `tier1_real`, because the broker executed a real upstream call to httpbin.org. ```text ```
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 10 minutes, faster than the median of the 5 comparable projects Argusic has measured.
- Recovered from all 6 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
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 6 agent-infrastructure projects Argusic has installed and timed, jentic-one was the 3rd fastest to reach a running state, and 6 of 6 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)
agent-infrastructureagent-securityagenticai-agentsapi-gatewayauditclaudecodexcredential-brokercredential-managercursorleast-privilegemcpoauthopenapiopenapi3openclawpermissionspolicyself-hosted
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/jentic-one)Questions
- Does jentic-one run?
- Yes. jentic-one runs. Argusic installed and launched it on a clean machine in 10 minutes, hitting 6 errors on the way, and recorded the session.
- How did Argusic test jentic-one?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit c8af96ea88a6. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test jentic-one?
- The run that produced this verdict cost $0.45: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does jentic-one 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 jentic-one need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing jentic-one?
- 6 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.
- How does jentic-one compare with the alternatives?
- Of the 6 agent-infrastructure projects Argusic has installed and timed, jentic-one was the 3rd fastest to reach a running state, and 6 of 6 reached one at all.
- Where is the evidence for jentic-one?
- 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.