#autoresearch Repositories
Discover 20 active open source GitHub repositories tagged with #autoresearch, accumulating 40,850 total stars (averaging 2,042 stars per project). Leading this topic is alchaincyf/darwin-skill with 7,015 stars.
20 repositories total
达尔文.skill —— A system that infinitely evolves your Skills: evaluate→improve→test→keep or rollback | Autoresearch-inspired autonomous skill optimization for Claude Code. Evaluate, improve, test, keep or revert.
Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.
Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify, retain or discard, and repeat indefinitely. Inspired by Karpathy’s autoresearch concept.
A blueprint-driven AutoResearch runtime for orchestrating AI research workflows from idea generation and experiments to paper writing and peer review.
A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch.
The first distributed AGI system. Thousands of autonomous AI agents collaboratively train models, share experiments via P2P gossip, and push breakthroughs here. Fully peer-to-peer. Join from your browser or CLI.
Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.
AIDE: an LLM agent for machine learning engineering - the research Weco grew out of. Referenced in OpenAI MLE-bench.
Reusable AI agent skills for growing software farms: explore ideas, write specs, let agents build unattended, then curate what grew — weed, prune, and review. Works with Claude Code, Codex, and other skill-compatible agents.
turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.
a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task
A generalist autonomous research agent — runs experiments, researches, and iteratively optimizes, autonomously.
Principia extracts reusable principles, composes those principles into traceable research ideas, and helps researchers inspect why an idea may be worth testing.
Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026.
Curated list of AutoResearch use cases with optimization traces and open source implementations
A codex plugin for running optimization loops inside a codebase. It is useful when you have a measurable target and many possible changes to try: test runtime, build speed, bundle size, model loss, Lighthouse scores, memory use, query latency, or any other metric you can print from a script.
Give an AI a research direction: it runs literature synthesis, gap validation, hypothesis formation and experiment design itself. 267 markdown skills form a research graph: 51 operations built from 216 atomic steps, any order, explicit backtracking; the plan is approved before it runs and interrupted runs resume. npx install, no runtime, no API key
Frequently Asked Questions
What is the most popular #autoresearch repository on GitHub?
The top ranked open source #autoresearch project on GitHub is alchaincyf/darwin-skill with 7,015 stars. 达尔文.skill —— A system that infinitely evolves your Skills: evaluate→improve→test→keep or rollback | Autoresearch-inspired autonomous skill optimization for Claude Code. Evaluate, improve, test, keep or revert.
Which programming languages are most used in #autoresearch repositories?
Among the top ranked #autoresearch projects on GitHub, the most common programming languages are Python, HTML, JavaScript, Shell.
How is the #autoresearch repository ranking calculated?
We track 20 active open source repositories tagged with #autoresearch (500+ stars), totaling 40,850 stars with an average of 2,042 stars per repository. Rankings update daily from the GitHub API.