universea Follow 
Stars
AI agents running research on single-GPU nanochat training automatically
Train the smallest LM you can that fits in 16MB. Best model wins!
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
U-Bench: A Comprehensive Understanding of U-Net through 100-Variant Benchmarking
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
LabClaw – Operating Layer for LabOS (Stanford-Princeton AI Co-Scientists)
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…
A cross-platform desktop All-in-One assistant tool for Claude Code, Codex, OpenCode, openclaw & Gemini CLI.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
"🐈 nanobot: The Ultra-Lightweight OpenClaw"
Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video” (ECCV 2024)
Official Python client library for the OpenReview API
Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are commi…
Reference PyTorch implementation and models for DINOv3
This is backend for the aixiv: https://www.aixiv.co
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning
[NeurIPS2025] "AI-Researcher: Autonomous Scientific Innovation" -- A production-ready version: https://novix.science/chat
Trae Agent is an LLM-based agent for general purpose software engineering tasks.
PyTorch Lightning Optical Flow models, scripts, and pretrained weights.