Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.
-
Updated
Mar 24, 2026 - Shell
Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.
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.
AIDE: AI-Driven Exploration in the Space of Code. The machine Learning engineering agent that automates AI R&D.
A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch.
Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.
a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task
Curated list of AutoResearch use cases with optimization traces and open source implementations
🦞+🔬: NanoResearch: The Autonomous AI Research Assistant
Fully Autonomous AI Research System with Self-Evolution, built natively on Claude Code
One file. Your AI agent becomes a scientist. 30+ experiments while you sleep.
A self-improving loop for voice AI agents. Uses karpathy's autoresearch as foundation.
multi-agent evolution organization for autoresearch and more
Autoresearch with PhD-level workflows and modular agent skills. Built for the autonomous AI Scientist.
Autonomous code optimization that works while you sleep (Autoresearch with Claude Code). Define a metric, point it at your code, go to bed. Wake up to a faster, smaller, better system — with correctness verified at every step.
Can LLMs beat classical HPO? A benchmark comparing classical, LLM-based, and hybrid methods on Karpathy's autoresearch.
Autonomous goal-directed iteration for Gemini CLI. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.
A curated list of awesome autonomous researcher frameworks
Agent Digivolve Harness is built around a simple observation: for many agent workflows, the first draft is not the hard part. The hard part is iteration.
Give AI coding agents (Claude Code, Cursor, Aider, Codex) a structured autonomous loop with guardrails — boundaries, 5 verification gates, 3-layer self-reflection, and autonomous remediation. pip install ouro-loop. Zero dependencies.
Add a description, image, and links to the autoresearch topic page so that developers can more easily learn about it.
To associate your repository with the autoresearch topic, visit your repo's landing page and select "manage topics."