convoviz
Export your ChatGPT history to Markdown: readable notes for Obsidian, plus private charts and word clouds of how you use ChatGPT. Runs locally.
Runssource: GitHubPythonMITcommit 7f68694701fe
Python, MIT licensed. The project labels itself: backup, chatgpt, chatgpt export, cli, conversations, data visualization, export and markdown.
convoviz runs. An Argusic agent installed it in 7 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
uv and convoviz are installed in this container, the project builds, all 159 tests plus ruff/ty pass, and convoviz converts a synthetic ChatGPT export into Markdown notes, an index, a Bases file, and a data-carrying insights.html with idempotent re-runs; inspect and config work as well.
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.
- Install time
- 7 minutes
- Cold machine to finish
- 3 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- uv run pytest -q exited 0 with 159 passed; ruff check and ty check both pass; convoviz --version printed 1.0.0; convoviz <zip> -o <out> --yes exited 0 writing 2 notes, index.md, Conversations.base, insights.html, .convoviz/state.json; re-run exited 0 reporting '2 unchanged'; inspect --json emitted a structure-only census; config init created the TOML; insights.html contains SVGs with aria-labels showing 'Jan 2026 · Prompts: 2' and 'Jan 2026 · gpt-5-2: 2'
- Model tokens used
- 142,185
- Exact commit tested
- 7f68694701fe
- 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.
All verifications are done and green. Wrapping up with the required report line. exec /bin/sh -lc 'export PATH="$HOME/.local/bin:$PATH"; cd /work/repo && uv run pytest -q 2>&1 | tail -3… succeeded in 1824ms: ........................................................................ [ 90%] ............... [100%] 159 passed in 1.49s exit: 0 ruff: pass ty: pass tokens used 142,185
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.
- Nothing broke on the way: zero errors between clone and running.
- 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 7 minutes to install, slower than the median of the 46 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 47 backup projects Argusic has installed and timed, convoviz was the 25th fastest to reach a running state, and 30 of 47 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 7 minutes after the clone.
- Following its own README: the documented path worked with nothing to fix.
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)
backupchatgptchatgpt-exportcliconversationsdata-visualizationexportmarkdownmarkdown-converterobsidianobsidian-mdopenaipersonal-knowledge-managementwordcloud
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/convoviz)Questions
- Does convoviz run?
- Yes. convoviz runs. Argusic installed and launched it on a clean machine in 7 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test convoviz?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7f68694701fe. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test convoviz?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does convoviz take to install?
- 7 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 convoviz need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing convoviz?
- Nothing did, in the recorded run: zero errors between clone and running.
- How does convoviz compare with the alternatives?
- Of the 47 backup projects Argusic has installed and timed, convoviz was the 25th fastest to reach a running state, and 30 of 47 reached one at all.
- Where is the evidence for convoviz?
- 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.