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.

Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.

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

Fully Autonomous AI Research System with Self-Evolution, built natively on Claude Code

A self-improving loop for voice AI agents. Uses karpathy's autoresearch as foundation.

Autoresearch with PhD-level workflows and modular agent skills. Built for the autonomous AI Scientist.

No description provided.

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.

Deterministic runtime for agent evaluation

Autonomous AI skill improvement through iterative experimentation — inspired by Karpathy's autoresearch. An agent mutates skill instructions, evaluates against objective metrics, keeps improvements, reverts regressions. No human in the loop.

Autonomous robotics research with simulation feedback

Autonomous search engine experimentation on WSJ/TREC, with changes accepted only when retrieval quality improves without serious performance regressions.

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.

Asynchronous, massively collaborative coordination layer for agents.

An AI research partner that figures out what to measure and how to test it. Live dashboard and actionable results. Built on Karpathy's autoresearch.

Domain-agnostic MCP server for autonomous experimentation with metric-driven keep/rollback decisions and reproducible experiment history.

Distributed AI research platform. Volunteer compute for autonomous ML experimentation. SETI@home meets autoresearch.

Self-improving newsletter optimization system inspired by Karpathy's autoresearch. Hill-climbing loop: Claude Code analyzes campaign metrics → generates improved drafts → keeps what works.

Train transformers on Apple's Neural Engine. Autonomous hyperparameter search via Karpathy's autoresearch protocol. 43 experiments, 8 verified findings.

🔬 Autonomous code improvement for Claude Code. Inspired by Karpathy's autoresearch. One change, one measure, one decision — repeat forever.

Self-supervising TLA+ formal verification loop — an LLM agent iteratively writes specs and fixes bugs, using the TLC model checker as an incorruptible evaluator. Inspired by Karpathy's autoresearch.

Companion tools for Karpathy's autoresearch — smarter evaluation, guided steering, and multi-agent competitions for GPT pretraining

AutoLab is your local, distributed and autonomous research lab - multiple agents with independent compute run experiments in parallel, sync results, and self-direct research.

A living Obsidian mind map maintained by Codex, Git, and a mild superiority complex.

An introductory guide to autonomous ML research — an LLM iteratively optimizes a trading model

Cortex Research Suite — 26 self-evolving AI research skills with Karpathy's autoresearch pattern. Skill Organism (genetic evolution engine), browser experiment arena, LLM-as-Judge evaluation, and trilogy integration (social listening, intelligence analysis, scenario simulation). Cross-platform: Claude Code, MCP, LangChain, CrewAI, OpenAI.

Local-first dashboard for monitoring your own autoresearch loop with a tiny Python server and static HTML UI.

General-purpose autonomous research framework for AI agents. Inspired by Andrej Karpathy's autoresearch.

Autonomous ML research on Apple Silicon — Karpathy's autoresearch with MLX + Muon + live web dashboard