Codewhale
Open-source agent for the terminal written in Rust. Use any provider or model. Issues & PRs always welcome
Runssource: GitHubhomepageRustMITcommit 9b2eeca89441
Rust, MIT licensed. The project labels itself: agent orchestration, ai agent, cli, codewhale, coding agent, developer tools, local first and mcp.
Codewhale runs. An Argusic agent installed it in 45 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Codewhale 0.9.11 builds, passes all tests, launches CLI help/doctor/exec against a mock API. Debug profile is memory-safe; release build hits OOM on constrained hardware. D-Bus dev headers were missing and were mocked via vendored crate sources.
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 94.7 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.
- libdbus-sys requires dbus-1.pc and C headers (system package libdbus-1-dev)15 minutes
- cargo build --release (LTO) killed by SIGKILL (OOM)5 minutes
- Install time
- 45 minutes
- Cold machine to finish
- 42 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- Model tokens used
- 357,295
- Exact commit tested
- 9b2eeca89441
- 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.
- How the result was proved
- runs before 2026-09-07 did not record the command used to check the result
- 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 3, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. 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.
**Launch verified:** `codewhale --version` outputs `codewhale 0.9.11 (dev)`. `codewhale doctor` run… **Tests:** 1,222 tests passed (0 failed, 2 ignored) across 5 crates: codewhale-config (626+82+68+17… **Second error — release build OOM:** `cargo build --release -p codewhale-cli` was killed by SIGKIL… tokens used 357,295 OK, let me now tally the final result. Here's a summary of what was done and the final result: **Install:** Rust 1.98.1 was installed via rustup. The workspace compiles and links as `codewhale-c… **Error encountered and fixed:** The `libdbus-sys` crate requires `dbus-1.pc` (pkg-config file) and… **Launch verified:** `codewhale --version` outputs `codewhale 0.9.11 (dev)`. `codewhale doctor` run… **Tests:** 1,222 tests passed (0 failed, 2 ignored) across 5 crates: codewhale-config (626+82+68+17… **Second error — release build OOM:** `cargo build --release -p codewhale-cli` was killed by SIGKIL…
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 2 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 3 times, so the result is not a one-off.
What did not, or is not known
- Took 45 minutes to install, slower than the median of the 17 comparable projects Argusic has measured.
Of the 18 agent-orchestration projects Argusic has installed and timed, Codewhale was the 17th fastest to reach a running state, and 13 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.
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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 3/3 | Runs with mocks | 92.00 | 0.10 | |
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.09 | |
| Argusic Runner | 2/3 | Runs | 100.00 | 0.19 |
Topics (from GitHub)
agent-orchestrationai-agentclicodewhalecoding-agentdeveloper-toolslocal-firstmcpmulti-agentmulti-modelopen-sourcerustterminaltui
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/codewhale)Questions
- Does Codewhale run?
- Yes. Codewhale runs. Argusic installed and launched it on a clean machine in 45 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test Codewhale?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 9b2eeca89441. 3 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test Codewhale?
- The run that produced this verdict cost $0.19: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does Codewhale take to install?
- 45 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 Codewhale need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing Codewhale?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does Codewhale compare with the alternatives?
- Of the 18 agent-orchestration projects Argusic has installed and timed, Codewhale was the 17th fastest to reach a running state, and 13 of 18 reached one at all.
- Where is the evidence for Codewhale?
- All 3 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.