writer-framework
No-code in the front, Python in the back. An open-source framework for creating data apps.
Runssource: GitHubhomepagePythonApache-2.0commit 53eef36becc2
Python, Apache-2.0 licensed. The project labels itself: ai, ai in, data apps, data visualization, developer tools, interface, interface builder and models.
writer-framework runs. An Argusic agent installed it in 11 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Writer Framework v1.27.0 is fully installed with all Python and JS dependencies, the CLI creates and runs apps, the UI builds and serves correctly, and 396 backend tests 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.
- PEP 668 externally-managed-environment blocked pip install poetry2 minutes
- Vite JS build OOM (heap limit) with default Node 182 minutes
- writer.ui import error on CLI after poetry install — static UI not yet built2 minutes
- Template hello not found — apps:build copied files incorrectly into app_templates1 minute
- Install time
- 11 minutes
- Cold machine to finish
- 9 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- poetry run pytest tests -v exited 0 with 396 passed, 33 deselected; poetry run writer run apps/hello --port 5001 started and served HTML on port 5001; curl http://127.0.0.1:5001 returned 200
- Model tokens used
- 44,428
- Exact commit tested
- 53eef36becc2
- 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
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 2, run , the attempt that decided the verdict above. 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.
4. **writer.ui import error** when running `writer --help` initially - Fixed by building the UI (`n…
5. **"Template hello couldn't be found"** - Fixed by re-running `npm run apps:build` which correctl…
Let me do a final run to clean up and verify.
2026-11-15T04:25:21.099260Z ERROR codex_core::tools::router: error=exec_command failed: CreateProce…
exec
/bin/sh -lc "python3 -c \"import shutil; shutil.rmtree('/tmp/test_app', ignore_errors=True)\"" in /…
succeeded in 0ms:
Now let me compile the final JSON result. The entire process took approximately 11 minutes (readme/…
2026-11-15T04:25:26.521385Z ERROR codex_core::session: failed to record rollout items: thread 01a1d…
tokens used
44,428
Now let me compile the final JSON result. The entire process took approximately 11 minutes (readme/…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 4 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.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 11 minutes to install, slower than the median of the 236 comparable projects Argusic has measured.
Of the 237 ai projects Argusic has installed and timed, writer-framework was the 178th fastest to reach a running state, and 168 of 237 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)
aiai-indata-appsdata-visualizationdeveloper-toolsinterfaceinterface-buildermodelsno-codepythonuiui-componentswebsockets
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/writer-framework)Questions
- Does writer-framework run?
- Yes. writer-framework runs. Argusic installed and launched it on a clean machine in 11 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test writer-framework?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 53eef36becc2. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test writer-framework?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does writer-framework take to install?
- 11 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 writer-framework need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing writer-framework?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does writer-framework compare with the alternatives?
- Of the 237 ai projects Argusic has installed and timed, writer-framework was the 178th fastest to reach a running state, and 168 of 237 reached one at all.
- Where is the evidence for writer-framework?
- All 2 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.