{
 "schema_version": 1,
 "generated": "2026-10-26",
 "repo": "smol-env/smol",
 "name": "smol",
 "owner": "smol-env",
 "slug": "smol-env-smol",
 "github": "https://github.com/smol-env/smol",
 "what": "smol is a deliberately tiny agent loop in Python, with golfed versions in Go, Clojure and PHP, that talks to any OpenAI Responses API compatible endpoint and executes model-requested shell commands.",
 "why": "137 stars, launched 86 days ago",
 "language": "Python",
 "requirements": [
  "Python 3 or Go",
  "An OpenAI Responses API compatible endpoint, such as a local proxy that adds your key"
 ],
 "audience_note": "Developers who want to understand or build on an agent loop small enough to read in an afternoon.",
 "risk": "none",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Software and DevOps",
 "url": "https://dedupedai.com/use-cases/smol-env-smol/",
 "use_case_count": 3,
 "use_cases": [
  {
   "id": "smol-env-smol--learn-agent-loop-in-an-afternoon",
   "title": "Understand a full agent loop in one afternoon",
   "best": true,
   "url": "https://dedupedai.com/use-cases/smol-env-smol/learn-agent-loop-in-an-afternoon/",
   "json": "https://dedupedai.com/use-cases/u/smol-env-smol/learn-agent-loop-in-an-afternoon.json"
  },
  {
   "id": "smol-env-smol--compare-agent-loops-across-languages",
   "title": "Compare a minimal agent loop in four languages",
   "best": false,
   "url": "https://dedupedai.com/use-cases/smol-env-smol/compare-agent-loops-across-languages/",
   "json": "https://dedupedai.com/use-cases/u/smol-env-smol/compare-agent-loops-across-languages.json"
  },
  {
   "id": "smol-env-smol--run-smol-with-history-and-line-editing",
   "title": "Use Smol day to day with line editing and history",
   "best": false,
   "url": "https://dedupedai.com/use-cases/smol-env-smol/run-smol-with-history-and-line-editing/",
   "json": "https://dedupedai.com/use-cases/u/smol-env-smol/run-smol-with-history-and-line-editing.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."
}