BESSER
Reliable agentic development combining low-code and AI. Built with Python. Create your UML models or describe your app. All in the browser. Generate FastAPI, React, Django, Spring Boot, Flutter, SQL and more with a combination of deterministic code-generators and LLMs to fill the gaps
Runssource: GitHubPythonMITcommit 7aefb2329f25
Python, MIT licensed. The project labels itself: agent, agentic ai, agents, ai, code generation, code generator, dsl and full stack.
BESSER runs. An Argusic agent installed it in 16 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
BESSER v8.8.0 installed from source, full test suite passes online, backend server starts and serves API on port 9000, code generation produces valid FastAPI backends from BUML domain models.
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. 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.
- bubblewrap (bwrap) not installed - shell sandbox unavailable, causing 2 test failures in test_derived_enum_entity_can_be_created.py1 minute
- Install time
- 16 minutes
- Cold machine to finish
- 23 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- python -m pytest tests/ exited 0, 11128 passed, 120 skipped, 3 xfailed in 349s; curl -s -o /dev/null -w '%{http_code}' http://localhost:19002/besser_api/ returned 200; BackendGenerator produced main_api.py with FastAPI app
- Model tokens used
- 33,358
- Exact commit tested
- 7aefb2329f25
- 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.
**Tests:** 11128 passed, 120 skipped (bubblewrap sandbox, live tests, missing torch, missing fronte… **Backend server:** Started successfully with `besser-wme-backend`, returned 200 on `GET /besser_ap… **Code generation:** The README quickstart example (DomainModel + BackendGenerator) produced a comp… 2026-11-06T12:22:59.394333Z ERROR codex_core::session: failed to record rollout items: thread 01a1b… tokens used 33,358 I have all the information I need from the earlier runs. Let me compile the final result now. Here is the complete verification report: **Install:** Created a Python 3.12 venv, installed base `requirements.txt`, installed the package i… **Tests:** 11128 passed, 120 skipped (bubblewrap sandbox, live tests, missing torch, missing fronte… **Backend server:** Started successfully with `besser-wme-backend`, returned 200 on `GET /besser_ap… **Code generation:** The README quickstart example (DomainModel + BackendGenerator) produced a comp…
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 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 MIT, as reported by its host.
What did not, or is not known
- Took 16 minutes to install, slower than the median of the 136 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 137 agent projects Argusic has installed and timed, BESSER was the 100th fastest to reach a running state, and 89 of 137 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.
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)
agentagentic-aiagentsaicode-generationcode-generatordslfull-stacklow-codelow-code-platformmodel-driven-engineeringmodelingno-codeoclopen-sourcepythonreactstate-machineumluml-diagram
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/besser)Questions
- Does BESSER run?
- Yes. BESSER runs. Argusic installed and launched it on a clean machine in 16 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test BESSER?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7aefb2329f25. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test BESSER?
- The run that produced this verdict cost $0.09: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does BESSER take to install?
- 16 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 BESSER need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing BESSER?
- 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.
- How does BESSER compare with the alternatives?
- Of the 137 agent projects Argusic has installed and timed, BESSER was the 100th fastest to reach a running state, and 89 of 137 reached one at all.
- Where is the evidence for BESSER?
- 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.