Starred repositories
Codex plugin that turns attached object images into code-only, animation-ready procedural Three.js models.
Simulation platform for general-purpose robotics & embodied AI learning.
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
Must-read papers on Repository-level Code Generation & Issue Resolution 🔥
Fully open reproduction of DeepSeek-R1
Minimal reproduction of DeepSeek R1-Zero
Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning
slime is an LLM post-training framework for RL Scaling.
SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration
Research code artifacts for Code World Model (CWM) including inference tools, reproducibility, and documentation.
Reinforcement Learning via Self-Distillation (SDPO)
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Reference PyTorch implementation and models for DINOv3
This repo is meant to serve as a guide for Machine Learning/AI technical interviews.
Post-training with Tinker
🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…
🙌 OpenHands: AI-Driven Development
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
DocAgent is a system designed to generate high-quality, context-aware code documentation for Python codebases using a multi-agent approach and hierarchical processing.
Train transformer language models with reinforcement learning.
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming