Does little-coder run?

Yes. little-coder runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 2 errors on the way, and recorded the session.

How did Argusic test little-coder?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit a9e467f2be43. 2 attempts are recorded, and the full method is on the methodology page.

What did it cost to test little-coder?

The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.

How long does little-coder take to install?

2 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 little-coder need a GPU?

Not to start. Argusic reached a running state on a machine with no GPU.

What goes wrong when installing little-coder?

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.

Where is the evidence for little-coder?

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.

little-coder

A harness optimized to smaller LLMs

Runssource: GitHub homepageTypeScriptApache-2.0commit a9e467f2be43

TypeScript, Apache-2.0 licensed. The project labels itself: ai coding assistant, aider polygot, benchmark, code generation, coding agent, coding agents, local llm and ollama.

little-coder runs. An Argusic agent installed it in 2 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

little-coder v1.19.0 installs and runs: npm install succeeds (182 packages), all 715 vitest tests pass, 4/4 pytest RPC client tests pass, TypeScript typechecks cleanly, the CLI launcher starts pi and lists available models correctly
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 96 of 100 (the mean of this project's run scores).

At a glance

verdict: Runs
Argusic Score: 96 / 100
cost of the verifying run: $0.02 (measured)
recorded runs: 2
last tested: 2026-09-18
stars: 2,612
forks: 180
open issues: 6
watchers: 13
size: 2 MB
created: 2026-04-11
last push: 2026-09-18

Subject data from GitHub, linked at the top of this page, refreshed 2026-09-23. 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 little-coder, 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 below the required >=22.19.01 minute
Playwright browser binaries missing (3 vitest integration tests failed)1 minute

Install time: 2 minutes
Cold machine to finish: 4 minutes
Errors hit and fixed: 2 hit, 2 fixed with no human help
How the result was proved: vitest run exited 0 with 715 tests passed (52/55 test files, 3 skipped); pytest test_rpc_client.py passed 4/4; tsc --noEmit clean; little-coder --help and --list-models and --version all produce correct output
Model tokens used: 42,271
Exact commit tested: a9e467f2be43
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.

Now let me verify the `--version` flag works too
exec
/bin/sh -lc 'export NVM_DIR="$HOME/.nvm"
[ -s "$NVM_DIR/nvm.sh" ] && '"\\. \""'$NVM_DIR/nvm.sh"
cd /work/repo
node bin/little-coder.mjs --version 2>&1' in /work/repo
 succeeded in 358ms:
0.83.0
All good. Here's the summary:
tokens used
42,271
All good. Here's the summary:

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 2 minutes, faster than the median of the 4 comparable projects Argusic has measured.
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 Apache-2.0, as reported by its host.
Measured 2 times, so the result is not a one-off.

Of the 5 ai-coding-assistant projects Argusic has installed and timed, little-coder was the 1st fastest to reach a running state, and 5 of 5 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 2 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 by	attempt	outcome	score	cost USD	when
Argusic Runner	2/3	Runs	100.00	0.02	2026-09-18 01:20 UTC
Argusic Runner	1/3	Runs with mocks	92.00	0.03	2026-09-05 01:07 UTC

Topics (from GitHub)

ai-coding-assistant aider-polygot benchmark code-generation coding-agent coding-agents local-llm ollama qwen small-language-models terminal-bench tool-use

Embed the badge

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

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

Questions

Does little-coder run?: Yes. little-coder runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test little-coder?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit a9e467f2be43. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test little-coder?: The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does little-coder take to install?: 2 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 little-coder need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing little-coder?: 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 little-coder compare with the alternatives?: Of the 5 ai-coding-assistant projects Argusic has installed and timed, little-coder was the 1st fastest to reach a running state, and 5 of 5 reached one at all.
Where is the evidence for little-coder?: 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.