anymd

Any file → clean Markdown for AI agents: PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images (OCR), audio and video (metadata, subtitles, transcripts). A fast Rust MCP server and CLI that runs on your machine. No API key.

Runssource: GitHubhomepageRustMITcommit 0a70224816e3

Rust, MIT licensed. The project labels itself: ai agents, cli, document conversion, docx, docx to markdown, epub, html to markdown and llm.

anymd runs. An Argusic agent installed it in 15 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Installation and build succeeded: bun 1.4.5, Rust 1.100.0, Node 18.19.1. The project built via cargo build --release -p anymd in 7 min 44 s with 8 harmless warnings (redundant homepage fields and deprecated rmcp::model::ServerInfo). All 75 TypeScript integration tests pass (MCP stdio, HTTP, boundary, production contract tests), all 484 Rust unit tests pass, typecheck passes.

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

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.07 (measured)
recorded runs
2
last tested
stars
1,076
forks
96
open issues
3
watchers
4
size
25 MB
created
last push

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.

Time lost to each failure while testing anymd, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • bun not found in PATH, and the bun install script requires unzip which is not installed (no root access)2 minutes
  • rustc/cargo not found: no Rust toolchain in container1 minute
  • npm install -g bun failed due to insufficient permissions
Install time
15 minutes
Cold machine to finish
17 minutes
Errors hit and fixed
3 hit, 3 fixed with no human help
How the result was proved
bun test exited 0: 75 tests passed, 329 expect() calls across 8 files; cargo test exited 0: 484 tests passed across 22 test binaries (anymd-core:312, anymd-formats:48+3, anymd-pdf:24, anymd-wasm:4, adobe-cmap-parser:79, pdf-extract:6+2+1); npx @sylphx/anymd version prints 'anymd 8.5.13'; ./target/release/anymd converts test/fixtures/sample.pdf to Markdown with correct headings and page markers
Model tokens used
120,745
Exact commit tested
0a70224816e3
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.

484 passed total
JS tests: 75 passed (already known)
Verification - npx install path works:
anymd 8.5.13
Cargo-built binary works:
anymd 8.1.0
CLI conversion works:
{"pages":[{"page_number":1,"text":"works"}]}
Here is my complete findings report.
tokens used
120,745
Here is my complete findings report.

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 3 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 MIT, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

What did not, or is not known

  • Took 15 minutes to install, slower than the median of the 123 comparable projects Argusic has measured.

Of the 124 ai-agents projects Argusic has installed and timed, anymd was the 98th fastest to reach a running state, and 96 of 124 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

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs100.000.07
Argusic Runner1/3Runs100.000.06

Topics (from GitHub)

ai-agentsclidocument-conversiondocxdocx-to-markdownepubhtml-to-markdownllmmarkdownmarkitdown-alternativemcpmodel-context-protocolocrpdfpdf-to-markdownpptxragrusttranscriptionxlsx

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/anymd.svg)](https://argusic.com/subject/anymd)

Questions

Does anymd run?
Yes. anymd runs. Argusic installed and launched it on a clean machine in 15 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test anymd?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 0a70224816e3. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test anymd?
The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does anymd take to install?
15 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 anymd need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing anymd?
3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does anymd compare with the alternatives?
Of the 124 ai-agents projects Argusic has installed and timed, anymd was the 98th fastest to reach a running state, and 96 of 124 reached one at all.
Where is the evidence for anymd?
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.

Discussion