Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.
-
Updated
Mar 13, 2026 - Python
#
autoresearch
Here are 25 public repositories matching this topic...
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.
decentralized p2p agi artificial-general-intelligence autonomous-agents ai-agents ai-research collaborative-ai llm distributed-ai autonomous-agents- autoresearch
-
Updated
Mar 14, 2026
Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.
-
Updated
Mar 14, 2026
Autoresearch with PhD-level workflows and modular agent skills. Built for the autonomous AI Scientist.
-
Updated
Mar 14, 2026 - Python
-
Updated
Mar 11, 2026 - Python
Deterministic runtime for agent evaluation
reliability-engineering specification agents ai-agents benchmarking-framework autogen fastapi langchain observability-platform ai-evaluation-framework agent-benchmark deterministic-testing autoresearch
-
Updated
Mar 14, 2026 - Python
Autonomous search engine experimentation on WSJ/TREC, with changes accepted only when retrieval quality improves without serious performance regressions.
-
Updated
Mar 13, 2026 - Shell
Apple Silicon dual-backend port of autoresearch (PyTorch MPS + MLX) with full Muon optimizer
-
Updated
Mar 14, 2026 - Python
Autonomous robotics research with simulation feedback
-
Updated
Mar 10, 2026 - Python
Collaborative knowledge sharing for autonomous LLM training agents. Fork of karpathy/autoresearch with experiment cards, multi-agent coordination, and multi-platform support (CUDA/MPS/CPU).
-
Updated
Mar 8, 2026 - Python
Domain-agnostic MCP server for autonomous experimentation with metric-driven keep/rollback decisions and reproducible experiment history.
-
Updated
Mar 14, 2026 - Python
Train transformers on Apple's Neural Engine. Autonomous hyperparameter search via Karpathy's autoresearch protocol. 43 experiments, 8 verified findings.
training machine-learning transformer neural-engine apple-silicon llm apple-neural-engine autoresearch
-
Updated
Mar 14, 2026 - Objective-C
What if the AI agent guessed first? 251 experiments. The predicting agent adapted to a 5x compute shift on try one. The reflecting agent took 7. The searching agent never caught up.
machine-learning deep-learning agi first-principles openai hyperparameter-optimization transfer-learning autonomous-agents ai-safety ai-agents karpathy claude prediction-error scientific-method meta-learning ai-research autonomous-research anthropic llm-agents autoresearch
-
Updated
Mar 10, 2026 - Python
Distributed AI research platform. Volunteer compute for autonomous ML experimentation. SETI@home meets autoresearch.
electron python distributed-systems machine-learning typescript deep-learning neural-network distributed-computing pytorch artificial-intelligence hyperparameter-optimization volunteer-computing research-platform fastapi autoresearch
-
Updated
Mar 12, 2026 - Python
Autonomous experimentation framework for AI agents. Define a problem, launch an agent, walk away. It experiments while you sleep.
python machine-learning optimization experimentation hyperparameter-tuning codex autonomous-agents ai-agents claude llm prompt-engineering autoresearch
-
Updated
Mar 11, 2026 - Python
Local-first dashboard for monitoring your own autoresearch loop with a tiny Python server and static HTML UI.
-
Updated
Mar 13, 2026 - HTML
Karpathy's autoresearch running on Mac Mini — no NVIDIA GPU required. Auto-detects CUDA, Apple Silicon (MPS), or CPU.
-
Updated
Mar 14, 2026 - Python
Give AI coding agents (Claude Code, Cursor, Aider, Codex) a structured autonomous loop with guardrails — boundaries, verification gates, self-healing, and autonomous remediation. Zero dependencies. Inspired by Karpathy's autoresearch.
python developer-tools cursor codex ai-safety agent-framework ai-agent aider llm-agent ai-guardrails vibe-coding claude-code ai-coding-agent autonomous-coding claude-code-hooks self-healing-code autonomous-remediation self-healing-agent bounded-autonomy autoresearch
-
Updated
Mar 14, 2026 - Python
Recursive research intelligence that gets smarter every time you use it. MCP server + CLI + REST API. Prediction-error learning, surprise detection, persistent brain.
cli research rest-api mcp brain ai-agents prediction-error tool-use recursive-search litellm agent-protocol tavily persistent-learning autoresearch surprise-detection
-
Updated
Mar 12, 2026 - Python
A practical playbook for running evidence-driven autoresearch loops.
-
Updated
Mar 14, 2026
Improve this page
Add a description, image, and links to the autoresearch topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the autoresearch topic, visit your repo's landing page and select "manage topics."