{
 "schema_version": 1,
 "generated": "2026-10-20",
 "repo": "alanhuangyoo/crux",
 "name": "crux",
 "owner": "alanhuangyoo",
 "slug": "alanhuangyoo-crux",
 "github": "https://github.com/alanhuangyoo/crux",
 "what": "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.",
 "why": "",
 "language": "TypeScript",
 "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"
 ],
 "audience_note": "Engineers who run self-hosted coding models on long terminal tasks and want to measure or improve the agent layer around them.",
 "risk": "none",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Software and DevOps",
 "url": "https://dedupedai.com/use-cases/alanhuangyoo-crux/",
 "use_case_count": 3,
 "use_cases": [
  {
   "id": "alanhuangyoo-crux--benchmark-self-hosted-model-on-terminal-bench",
   "title": "Benchmark a self-hosted model on Terminal-Bench 2.1",
   "best": true,
   "url": "https://dedupedai.com/use-cases/alanhuangyoo-crux/benchmark-self-hosted-model-on-terminal-bench/",
   "json": "https://dedupedai.com/use-cases/u/alanhuangyoo-crux/benchmark-self-hosted-model-on-terminal-bench.json"
  },
  {
   "id": "alanhuangyoo-crux--compare-agent-versions-task-by-task",
   "title": "Test whether an agent change helps, task by task",
   "best": false,
   "url": "https://dedupedai.com/use-cases/alanhuangyoo-crux/compare-agent-versions-task-by-task/",
   "json": "https://dedupedai.com/use-cases/u/alanhuangyoo-crux/compare-agent-versions-task-by-task.json"
  },
  {
   "id": "alanhuangyoo-crux--diagnose-stalled-or-truncated-agent-runs",
   "title": "Find why long agent runs stall, truncate, or time out",
   "best": false,
   "url": "https://dedupedai.com/use-cases/alanhuangyoo-crux/diagnose-stalled-or-truncated-agent-runs/",
   "json": "https://dedupedai.com/use-cases/u/alanhuangyoo-crux/diagnose-stalled-or-truncated-agent-runs.json"
  }
 ],
 "disclaimer": "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."
}