agentfs-claude

Run Claude Code/Codex within AgentFS, orchestrated by LlamaIndex Workflows

Runssource: GitHubTypeScriptMITarchived upstreamcommit 135bf7393402

TypeScript, MIT licensed. The project labels itself: claude code, codex, coding agents and filesystem.

agentfs-claude runs. An Argusic agent installed it in 1 minute and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

TypeScript builds cleanly, all 10 tests pass, and the MCP server starts and serves all 5 filesystem tools (read_file, write_file, edit_file, file_exists, list_files) over HTTP on port 3000

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
$0.05 (measured)
recorded runs
1
last tested
stars
324
forks
31
open issues
0
watchers
5
size
1 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 agentfs-claude, 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.

  • Node.js v18.19.1 is too old for vitest 4.x (needs node:util.styleText, added in v21.7)2 minutes
  • rolldown native binding missing: @rolldown/binding-linux-x64-gnu was not installed1 minute
  • LlamaParseReader constructed at module import time, throwing before tests could skip1 minute
  • pnpm override removed @openai/codex-sdk from install; tsx not installed for mcp-start script1 minute
  • esbuild postinstall skipped, causing runtime issues1 minute
  • Compiled test files in dist/ caused AgentFS database lock conflicts with src/ tests1 minute
Install time
1 minutes
Cold machine to finish
6 minutes
Errors hit and fixed
6 hit, 6 fixed with no human help
How the result was proved
pnpm test exited 0, 10 passed (3 test files); MCP streamable HTTP server answered 200 on /mcp initialize and exposed all 5 filesystem tools via tools/list; tsc build exited cleanly
Model tokens used
341,517
Exact commit tested
135bf7393402
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.

   Duration  862ms (transform 127ms, setup 0ms, import 1.59s, tests 184ms, environment 0ms)
All tests pass. Let me now produce the final report.
**Time tracking:** I started shortly after the timestamp in the logs. Let me verify the build one l…
exec
/bin/sh -lc 'export PATH="/home/runner/.n/bin:/home/runner/.npm-global/bin:$PATH" && cd /work/repo …
 succeeded in 1359ms:
> [email protected] build /work/repo
> tsc
All tests pass (10/10), TypeScript builds clean, and the MCP server is verified. Here's my report:
tokens used
341,517
All tests pass (10/10), TypeScript builds clean, and the MCP server is verified. Here's my 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.
  • Installed in 1 minute, faster than the median of the 21 comparable projects Argusic has measured.
  • Recovered from all 6 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.

What did not, or is not known

  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 22 claude-code projects Argusic has installed and timed, agentfs-claude was the 7th fastest to reach a running state, and 22 of 22 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 1 minutes after the clone.

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 Runner1/3Runs100.000.05

Topics (from GitHub)

claude-codecodexcoding-agentsfilesystem

Embed the badge

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

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

Questions

Does agentfs-claude run?
Yes. agentfs-claude runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 6 errors on the way, and recorded the session.
How did Argusic test agentfs-claude?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 135bf7393402. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test agentfs-claude?
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 agentfs-claude take to install?
1 minute in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does agentfs-claude need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing agentfs-claude?
6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does agentfs-claude compare with the alternatives?
Of the 22 claude-code projects Argusic has installed and timed, agentfs-claude was the 7th fastest to reach a running state, and 22 of 22 reached one at all.
Where is the evidence for agentfs-claude?
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.

Discussion