Skip to content

Entry

autoresearch

Appears in 6 awesome lists

Andrej Karpathy's autonomous LLM research framework: AI agent runs overnight experiments on a real training setup, auto-editing code→5min training→evaluation in a loop, ~100 experiments per night on a single GPU

Open github.comkarpathy/autoresearch

Found in these lists

Awesome Ai For Science

Section: Autonomous Research Systems (2023-2025 Breakthroughs) · Andrej Karpathy's autonomous LLM research framework: AI agent runs overnight experiments on a real training setup, auto-editing code→5min training→evaluation in a loop, ~100 experiments per night on a single GPU

FreshScore 87

Awesome Autoresearch

Section: Platform ports and hardware forks · Adapts autoresearch for free T4 GPUs (Google Colab / Kaggle) with zero cost and zero local setup. Key changes: Flash Attention 3 → PyTorch SDPA, removes H100-only kernel dependency.

FreshScore 79

Awesome LLM Resources

Section: 研究 Research

FreshScore 91

Awesome Prompts

Section: Frameworks · Karpathy

FreshScore 96

awesome-python

Section: Other · AI agents running research on single-GPU nanochat training automatically

FreshScore 79

Awesome RSI (Recursive Self-Improvement)

Section: Automated Search / AI R&D · Runs an autonomous loop that edits an LLM training program, trains for five minutes, and keeps only changes that improve validation bits per byte.

FreshScore 85

wanshuiyin/Auto-claude-code-research-in-sleep

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

In 6 listsDetails

AI Scientist

First fully autonomous open-ended scientific discovery system with official implementation: hypothesis→experiment→writing→review simulation (13.8K+ stars, 2024)

In 6 listsDetails

AIDE

LLM-driven machine learning engineering agent using agentic tree search to autonomously draft, debug and benchmark ML code; wins 4× more medals than the best linear agent on OpenAI's MLE-Bench (75 Kaggle competitions) (1.3K+ stars, MIT License)

In 5 listsDetails

Supervisor-Skills:

将博导十年科研经验炼化为可直接调用的 AI 技能。从 Idea 构思到论文投稿,你的 AI 科研副导师。

In 2 listsDetails

aiming-lab/AutoResearchClaw

April 2026 open-source human-in-the-loop system with six intervention modes (full-auto, gate-only, checkpoint, step-by-step, co-pilot, custom), SmartPause confidence-driven dynamic suspension, and Intervention Learning from human corrections. The cost-guardrail system — aborting runs that exceed…

In 5 listsDetails

OpenEvolve

Open-source implementation of AlphaEvolve's evolutionary coding agent paradigm, enabling LLMs to autonomously discover and optimize algorithms through iterative evolution, matching the approach behind DeepMind's breakthrough matrix multiplication discovery (6.2K+ stars, 2025)

In 4 listsDetails

microsoft/RD-Agent

Open-source LLM-powered R&D agent framework automating data-driven AI solution building through automated research, development, and evolution; achieves top open-source performance on MLE-Bench with dual Researcher-Developer agents and supports research copilot, data mining, Kaggle, and quant R&D…

In 5 listsDetails

claude-scientific-skills

Comprehensive collection of 125+ ready-to-use scientific skill modules for Claude AI across bioinformatics, cheminformatics, clinical research, ML, and materials science

In 4 lists