diri
The best way to work with coding agents. Run fifty in parallel, let them spawn each other, review everything in one place.
Runssource: GitHubhomepageRustAGPL-3.0commit 1a8e9d96091b
Rust, AGPL-3.0 licensed. The project labels itself: claude code, codex, coding agents, gpui and rust.
diri runs. An Argusic agent installed it in 18 minutes and hit 5 errors on a clean machine with no GPU, and the whole session was recorded.
All headless Rust crates compile, pass clippy and fmt checks, and 114+691 tests pass; the diri-remote binary probes platform metadata and captures remote environments; the GPUI desktop app compiles through cargo check but cannot link in this 8GB container.
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 92 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.
- Missing system -dev packages (libasound2-dev, libfontconfig-dev, libglib2.0-dev, libwayland-dev, libx11-xcb-dev, libxkbcommon-dev, libxkbcommon-x11-dev, libfreetype-dev, zlib1g-dev, libpng-dev, libbrotli-dev, libexpat1-dev, libxcb1-dev) — no root access to install them5 minutes
- Dangling symlinks in build-deps (libxcb.so.0, libxkbcommon.so.0, libxkbcommon-x11.so.0) caused linker errors1 minute
- Missing field foreground_ports in SessionView test initializer at crates/diri-engine/src/registry.rs:50481 minute
- 3 pre-existing test failures in control::claude_accounts and control::codex_accounts — credential file permission checks fail in this container environment (also fail on unmodified code)
- Full desktop binary linking (diri-app) runs out of memory in 8GB container — cargo check succeeds but final ld OOMs
- Install time
- 18 minutes
- Cold machine to finish
- 34 minutes
- Errors hit and fixed
- 5 hit, 3 fixed with no human help
- How the result was proved
- cargo test -p diri-terminal-state -p diri-proto -p diri-remote -p dirijor-mcp -p diri-client -p diri-pty -p diri-telemetry -p diri-usage passed 114 tests; cargo test -p diri-engine -- --skip identity_snapshot --skip shared_claude_switch --skip login_files_are_private passed 691 tests, 7 ignored; ./target/release/diri-remote probe returned valid JSON with protocol v1.15; ./target/release/diri-remote environment captured 42 environment variables
- Model tokens used
- 1,440,281
- Exact commit tested
- 1a8e9d96091b
- 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.
tokens used 1,440,281 Here's my final report on the Diri repository. The project is a Rust workspace under `diri/` with multiple crates including a desktop GPUI app, CL… **What I did and observed:** 1. **Rust was not installed** — installed via `rustup` (the pinned toolchain 1.97.1 was auto-downlo… 2. **Missing system -dev packages** — without root (no sudo), the required `libasound2-dev`, `libfo… 3. **Dangling symlinks in build-deps** — the extracted dev libraries' `.so` symlinks pointed to ver… 4. **Missing `foreground_ports` field** — test code in `diri/crates/diri-engine/src/registry.rs:504… 5. **All headless crates compile and test pass** — `cargo check --workspace`, `cargo fmt --all -- -… 6. **`diri-remote` binary works** — release build succeeded, `probe` outputs correct JSON with prot… 7. **The desktop app (`diri-app`) links correctly through `cargo check`** but cannot be linked as a…
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.
- Ran without a GPU, so it does not need one to start.
- Licensed AGPL-3.0, as reported by its host.
What did not, or is not known
- Took 18 minutes to install, slower than the median of the 21 comparable projects Argusic has measured.
- Hit 5 errors during setup, 2 of which were not solved.
- 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, diri was the 21st 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.
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)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/diri)Questions
- Does diri run?
- Yes. diri runs. Argusic installed and launched it on a clean machine in 18 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test diri?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 1a8e9d96091b. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test diri?
- The run that produced this verdict cost $0.33: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does diri take to install?
- 18 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 diri need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing diri?
- 5 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 diri compare with the alternatives?
- Of the 22 claude-code projects Argusic has installed and timed, diri was the 21st fastest to reach a running state, and 22 of 22 reached one at all.
- Where is the evidence for diri?
- 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.