anydoc
Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.
Runssource: GitHubhomepageRustMITcommit 261fc257d17c
Rust, MIT licensed.
anydoc runs. An Argusic agent installed it in 6 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
The anydoc Rust library builds, the Node.js native binding and CLI build and pass all tests, the Python binding builds and passes all tests, and the CLI converts real docx/rtf/csv fixture files to correct GitHub-Flavored Markdown.
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
- 6 minutes
- Cold machine to finish
- 6 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- cargo test exited 0 with 296 passed; python -m unittest discovered -s tests exited 0 with 11 passed; npm test exited 0 with 19 passed; example converter converted docx/rtf/csv fixture files to correct GFM
- Model tokens used
- 55,307
- Exact commit tested
- 261fc257d17c
- 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.
- **CLI:** Verified converting real docx, rtf, and CSV fixture files produced correct Markdown All tests pass with no failures. The OCR tests (`--ocr hosted`) exercise Firecrawl Parse error path… tokens used 55,307 All systems are verified. Here's the summary: **Install & Build:** The Rust workspace compiled successfully with `cargo build`. Python bindings b… **Test Results:** - **Rust:** 296 tests passed (286 unit + 1 robustness + 9 snapshot + 0 doc-tests) - **Python:** 11 tests passed (`python -m unittest`) - **Node.js:** 19 tests passed (`node --test`) - **CLI:** Verified converting real docx, rtf, and CSV fixture files produced correct Markdown All tests pass with no failures. The OCR tests (`--ocr hosted`) exercise Firecrawl Parse error path…
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 6 minutes, faster than the median of the 17 comparable projects Argusic has measured.
- 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.
- Measured 2 times, so the result is not a one-off.
Of the 18 Rust projects Argusic has installed and timed, anydoc was the 8th fastest to reach a running state, and 17 of 18 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 6 minutes after the clone.
- Following its own README: the documented path worked with nothing to fix.
Run history
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/anydoc)Questions
- Does anydoc run?
- Yes. anydoc runs. Argusic installed and launched it on a clean machine in 6 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test anydoc?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 261fc257d17c. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test anydoc?
- 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 anydoc take to install?
- 6 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 anydoc need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing anydoc?
- Nothing did, in the recorded run: zero errors between clone and running.
- How does anydoc compare with the alternatives?
- Of the 18 Rust projects Argusic has installed and timed, anydoc was the 8th fastest to reach a running state, and 17 of 18 reached one at all.
- Where is the evidence for anydoc?
- 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.