Starred repositories
TradingAgents: Multi-Agents LLM Financial Trading Framework
🎨 Local-first, open-source Claude Design alternative. 🖥️ Native desktop app. ⚡ 259+ Skills · ✨ 142+ Design Systems 🖼️ Web · desktop · mobile prototypes · slides · images · videos · HyperFrames 📦 Sa…
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."
Unified data lake of 293M scientific papers from 8 scholarly sources + 13 ontologies (960 GB Parquet, queryable via DuckDB)
A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval
A local AI assistant running on your device. It turns your files into actionable memory.
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows
Easy Data Preparation with latest LLMs-based Operators and Pipelines.
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
🔥 OneThinker: All-in-one Reasoning Model for Image and Video [CVPR 2026]
[CVPR 2026] An official implementation of "Think Visually, Reason Textually: Vision-Language Synergy in ARC"
🚀 Efficient implementations for emerging model architectures
A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.
[ACL 2026] Official implement on 'Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs'
Official Repo of From Masks to Worlds: A Hitchhiker’s Guide to World Models.
Official code repo for our work "Native Visual Understanding: Resolving Resolution Dilemmas in Vision-Language Models"
[ICLR 2026] Official code for TraceRL: Revolutionizing post-training for Diffusion LLMs, powering the SOTA TraDo series.
OpenVision (ICCV 2025), OpenVision 2 (CVPR 2026), and OpenVision 3
A project to improve skills of large language models
slime is an LLM post-training framework for RL Scaling.
[EMNLP 2025] CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward