minimax-code
An open-source coding agent for your terminal, powered by MiniMax.
Runssource: GitHubhomepageTypeScriptMITcommit 0f6ad5229ff1
TypeScript, MIT licensed. The project labels itself: coding agents, harness and minimax.
minimax-code runs. An Argusic agent installed it in 2.5 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
MiniMax Code 0.5.5 builds from source, passes 6003 of 6007 tests across smoke, BYOK, release-tools, status-contract, policy, sandbox, artifact, and capability suites, and answers to mcode --version.
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
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.
- Node.js 18.19.1 is too old (requires >=22.19). Installed nvm and Node.js 22.19.0.2.5 minutes
- Pre-existing test failure: 'caps a large nonzero-exit result' in packages/agent-tools/test/desktop/local-bash-output.test.ts — the head/tail truncation budget at 24KB max (22KB preview) cannot fit expectation `error-row-399-` alongside `error-row-0-`, the exit message, and the truncation footer.
- Install time
- 3 minutes
- Cold machine to finish
- 27 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- pnpm test:smoke passed 20/21 (1 skip), pnpm test:byok passed 3/3, pnpm test:release-tools passed 53/54 (1 skip), pnpm test:status-contract 9 passed, pnpm test:policy 142 passed, pnpm test:sandbox 26 passed 22 skipped, pnpm test:artifact 4 passed, pnpm typecheck no errors, pnpm check:source passed, pnpm check:standalone passed, node dist/cli.js --version returned '0.5.5'
- Model tokens used
- 196,921
- Exact commit tested
- 0f6ad5229ff1
- 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.
tsconfig.standalone.json paths match 128 package exports. > [email protected] check:standalone /work/repo > node scripts/check-standalone-boundary.mjs Standalone build dependency boundary passed. === mcode version === 0.5.5 Here's the complete summary of what I found and verified. The repo builds, launches, and tests nearly all pass — one pre-existing test fails in the capabilit… tokens used 196,921 Here's the complete summary of what I found and verified. The repo builds, launches, and tests nearly all pass — one pre-existing test fails in the capabilit…
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 2.5 minutes.
- 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.
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.
- A quick evaluation: it was running 2.5 minutes after the clone.
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/minimax-code)Questions
- Does minimax-code run?
- Yes. minimax-code runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test minimax-code?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 0f6ad5229ff1. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test minimax-code?
- The run that produced this verdict cost $0.12: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does minimax-code take to install?
- 2.5 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 minimax-code need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing minimax-code?
- 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 minimax-code?
- 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.