DEDUPED Hot AI repos, turned into use cases Get 5 a day

What you can do with Crux

Crux is a coding agent built on the pi agent, re-engineered for long-horizon terminal tasks, with a Terminal-Bench 2.1 benchmark harness.

Trended earlier

alanhuangyoo/crux on GitHub

Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk.

What do you want to do?

3 use cases

  • Benchmark a self-hosted model on Terminal-Bench 2.1

    Run the Crux agent on 89 Terminal-Bench 2.1 tasks to get a pass@1 score for your own model.

    View prompt
    Use the alanhuangyoo/crux repository. Go to its benchmark folder, run `uv sync`, then run harbor against the terminal-bench/terminal-bench-2-1 dataset with agent crux.pi_agent:CruxPiAgent and model openai/<your-model>. Report the pass@1 score over the full run and the number of tasks evaluated, and confirm the run covered 89 tasks.

  • Test whether an agent change helps, task by task

    Compare two agent versions on the same tasks with a paired sign test instead of one total score.

    View prompt
    Use the alanhuangyoo/crux repository benchmark folder. Run the same Terminal-Bench 2.1 dataset and model for two agent versions, <baseline> and <changed>, then compare them task by task with the paired sign test. Output the per-task outcome counts and the test result, and verify that both runs used the same model and task set.

  • Find why long agent runs stall, truncate, or time out

    Use the documented failure modes and trial outcome classes to explain a failed terminal run.

    View prompt
    Use the alanhuangyoo/crux repository. Read the 'What changed from pi' section of its README, then run the failing <task> from Terminal-Bench 2.1 through harbor with crux.pi_agent:CruxPiAgent. Report which failure class the trial outcome falls into (compaction, truncated output, or idle time) and name the matching agent-layer feature, then verify the classification against the trial output.

How to use Crux

  1. Check you have what it needs: uv installed, since the benchmark is set up with `uv sync`; harbor installed, since the benchmark runs through `harbor run`; Access to the terminal-bench/terminal-bench-2-1 dataset.
  2. Open alanhuangyoo/crux on GitHub and read the README and license.
  3. Clone the repository and open the benchmark folder with cd benchmark.
  4. Install the harness dependencies with uv sync.
  5. Finish the --model argument after openai/ with the name of your served model, since the README command is cut off there. (inferred, check the README)
  6. Run harbor run --dataset terminal-bench/terminal-bench-2-1 --agent crux.pi_agent:CruxPiAgent --model openai/<your-model>. (inferred, check the README)

These steps come from our top use case, Benchmark a self-hosted model on Terminal-Bench 2.1, which also has a copy-paste agent prompt.

Crux alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forEngineers who run self-hosted coding models on long terminal tasks and want to measure or improve the agent layer around them.
  • Why it is hot
  • LanguageTypeScript
  • Sourcegithub.com/alanhuangyoo/crux · Back to Hot repos

Requirements

  • uv installed, since the benchmark is set up with `uv sync`
  • harbor installed, since the benchmark runs through `harbor run`
  • Access to the terminal-bench/terminal-bench-2-1 dataset
  • A model endpoint you can reach through the `openai/` model prefix used in the README command
Maintain Crux? Add the Featured on Deduped badge

Paste this into your README:

[![Featured on Deduped](https://dedupedai.com/badge/alanhuangyoo-crux.svg)](https://dedupedai.com/use-cases/alanhuangyoo-crux/?ref=badge)

More badge styles and HTML

Questions about Crux

What is Crux?

Crux is a coding agent built on the pi agent, re-engineered for long-horizon terminal tasks, with a Terminal-Bench 2.1 benchmark harness. It is an open-source project on GitHub: https://github.com/alanhuangyoo/crux.

Who is Crux for?

Engineers who run self-hosted coding models on long terminal tasks and want to measure or improve the agent layer around them.

What can I do with Crux?

3 use cases so far, for example: Benchmark a self-hosted model on Terminal-Bench 2.1; Test whether an agent change helps, task by task; Find why long agent runs stall, truncate, or time out. Each has steps and a copy-paste agent prompt.

What do I need to run Crux?

uv installed, since the benchmark is set up with `uv sync`; harbor installed, since the benchmark runs through `harbor run`; Access to the terminal-bench/terminal-bench-2-1 dataset; A model endpoint you can reach through the `openai/` model prefix used in the README command.

What are alternatives to Crux?

Other hot AI repos in Software and DevOps: Harness2, iFixAi, Orca, Diagram Design, AI Memory.

Is Crux safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.