Albatross

Open source, terminal-first AI coding agent with fully transparent multi-model routing. Local (Ollama, LM Studio, MLX, llama.cpp) or cloud, your keys, one TUI. No black box.

Runssource: GitHubhomepageRustMITcommit e458e4277f46

Rust, MIT licensed. The project labels itself: ai coding agent, ai coding assistant, cli, coding agent, developer tools, harness, llama cpp and llm.

Albatross 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.

Albatross 2.5.0 builds from source, passes all 712 unit tests, passes cargo fmt and clippy -D warnings, and can run a one-shot prompt against an Ollama-compatible API returning SSE streaming chunks.

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
$0.13 (measured)
recorded runs
1
last tested
stars
244
forks
23
open issues
8
watchers
4
size
9 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 Albatross, 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.

  • cargo clippy failed with clippy::double_must_use on Rust 1.99 (new lint on async_trait)2 minutes
  • Rust toolchain not installed1 minute
  • cargo fmt caught extra blank line after the allow annotation1 minute
Install time
15 minutes
Cold machine to finish
18 minutes
Errors hit and fixed
3 hit, 3 fixed with no human help
How the result was proved
cargo test exited 0 - 712 passed, 0 failed. Verified end-to-end via mock Ollama on port 11435: BACKEND=ollama OLLAMA_BASE_URL=http://127.0.0.1:11435/v1 ALBATROSS_NO_WIZARD=true ALBATROSS_NO_UPDATE_CHECK=true timeout 15 ./target/release/albatross --print "Say exactly one word: hello" printed hello and exited 0.
Model tokens used
456,843
Exact commit tested
e458e4277f46
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 1, 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.

async trait definitions in `src/agent.rs` and `src/tools/mod.rs`.
```
tokens used
456,843
The repo works. Here's a commit message for the fix applied:
```
chore: suppress new clippy::double_must_use lint on async traits
Rust 1.99 added `double_must_use` which fires on `async_trait`-generated
methods because they already carry `#[must_use]` through the pinned
Future return type.  Added `#[allow(clippy::double_must_use)]` to the two
async trait definitions in `src/agent.rs` and `src/tools/mod.rs`.
```

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 15 minutes.
  • 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.

What did not, or is not known

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

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 Runner1/3Runs100.000.13

Topics (from GitHub)

ai-coding-agentai-coding-assistantclicoding-agentdeveloper-toolsharnessllama-cppllmllmsmlxollamaopenrouterrustterminal

Embed the badge

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

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

Questions

Does Albatross run?
Yes. Albatross 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 Albatross?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit e458e4277f46. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test Albatross?
The run that produced this verdict cost $0.13: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does Albatross 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 Albatross need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing Albatross?
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.
Where is the evidence for Albatross?
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