awesome-autoresearch and autoresearch

These are ecosystem siblings where A is a curated discovery/reference resource for the autoresearch paradigm while B is a specific implementation of that paradigm for Claude Code plugins, allowing practitioners to find and apply autoresearch concepts.

awesome-autoresearch
59
Established
autoresearch
22
Experimental
Maintenance 23/25
Adoption 10/25
Maturity 9/25
Community 17/25
Maintenance 13/25
Adoption 0/25
Maturity 9/25
Community 0/25
Stars: 876
Forks: 64
Downloads:
Commits (30d): 39
Language:
License:
Stars:
Forks:
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No Package No Dependents
No Package No Dependents

About awesome-autoresearch

alvinunreal/awesome-autoresearch

A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch.

Organizes 50+ implementations across general-purpose descendants, research-agent systems, domain-specific adaptations, and hardware ports—each with distinct architectural patterns like closed-loop evaluation, swarm coordination, prompt evolution, and tree-search optimization. Covers both narrow autoresearch forks (Gemini-native with live search grounding, Claude Code skills with resumable sessions) and broader meta-systems that auto-generate agent architectures or orchestrate multi-loop optimization. Includes recent ICLR papers (ADAS, GEPA, ClawTeam) demonstrating self-improvement on coding benchmarks and prompt tuning via genetic-Pareto reflection.

About autoresearch

zircote/autoresearch

Autonomous skill improvement loop for Claude Code plugins — inspired by Karpathy's autoresearch. Modify → evaluate → keep/discard → repeat until convergence. Zero-touch quality iteration at scale.

Scores updated daily from GitHub, PyPI, and npm data. How scores work