Democratizing AI scientists with ToolUniverse

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

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

This repository contains the official implementation for the series of NAIP family.

The academic Cloud Lab is primarily for the use of the CMU research community and CMU educational purposes, providing access to a wide array of instrumentation. The Academic Cloud Lab has already been used to teach courses for both undergraduate and graduate students, and CMU researchers have conducted research using ECL facilities.

🔬 LabOS — 下一代全自动科研实验平台 | Next-Gen AI Research Automation Platform | 四阶段流水线 · 多LLM配置 · Codex集成 · 远程GPU执行 · 记忆系统

One Day’s Operation, One Year’s Discovery

Benchmark for statistically valid AI scientist systems, using audit-closed protocols, transparency logs, and sequential inference to prevent false discoveries in autonomous research agents.

Automated Concept Discovery of Quantum Error Correction Codes

Automate code improvement by detecting issues, fixing bugs, and simplifying code on separate branches before merging to main.

Port Apple Silicon support for Karpathy’s autoresearch to run fixed-time training loops natively without PyTorch or CUDA dependencies.