{
 "schema_version": 1,
 "generated": "2026-10-26",
 "repo": "Birfy/agentdescent",
 "name": "agentdescent",
 "owner": "Birfy",
 "slug": "birfy-agentdescent",
 "github": "https://github.com/Birfy/agentdescent",
 "what": "AgentDescent is a Python framework that runs many agents in parallel to propose edits to a shared skill, prompt, or harness, then merges and commits the best changes.",
 "why": "201 stars",
 "language": "Python",
 "requirements": [
  "Python 3.9 or newer",
  "pip to install the agentdescent package from PyPI",
  "For model-backed runs: an OpenAI-compatible endpoint, its base URL, and an API key set in environment variables (OPENAI_BASE_URL and OPENAI_API_KEY)",
  "For agent-plugin use: Claude Code or Codex installed, and git to clone the repo"
 ],
 "audience_note": "Developers and AI engineers who want to improve a prompt, skill, or agent setup against their own examples, with an offline demo for a first look.",
 "risk": "none",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Software and DevOps",
 "url": "https://dedupedai.com/use-cases/birfy-agentdescent/",
 "use_case_count": 4,
 "use_cases": [
  {
   "id": "birfy-agentdescent--see-a-skill-evolve-offline-demo",
   "title": "See a skill evolve in one offline demo run",
   "best": true,
   "url": "https://dedupedai.com/use-cases/birfy-agentdescent/see-a-skill-evolve-offline-demo/",
   "json": "https://dedupedai.com/use-cases/u/birfy-agentdescent/see-a-skill-evolve-offline-demo.json"
  },
  {
   "id": "birfy-agentdescent--evolve-a-prompt-against-your-own-examples",
   "title": "Evolve a prompt against your own labeled examples",
   "best": false,
   "url": "https://dedupedai.com/use-cases/birfy-agentdescent/evolve-a-prompt-against-your-own-examples/",
   "json": "https://dedupedai.com/use-cases/u/birfy-agentdescent/evolve-a-prompt-against-your-own-examples.json"
  },
  {
   "id": "birfy-agentdescent--improve-an-agent-skill-from-claude-code",
   "title": "Improve an agent skill from inside Claude Code",
   "best": false,
   "url": "https://dedupedai.com/use-cases/birfy-agentdescent/improve-an-agent-skill-from-claude-code/",
   "json": "https://dedupedai.com/use-cases/u/birfy-agentdescent/improve-an-agent-skill-from-claude-code.json"
  },
  {
   "id": "birfy-agentdescent--compare-self-evolution-algorithms-without-a-key",
   "title": "Compare published self-evolution algorithms with a dry run",
   "best": false,
   "url": "https://dedupedai.com/use-cases/birfy-agentdescent/compare-self-evolution-algorithms-without-a-key/",
   "json": "https://dedupedai.com/use-cases/u/birfy-agentdescent/compare-self-evolution-algorithms-without-a-key.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."
}