Stars
An open-source AI agent that brings the power of Gemini directly into your terminal.
Open-source implementation of AlphaEvolve
Memory for AI Agents; Announcing OpenMemory MCP - local and secure memory management.
Code to automatically prove or verify estimates in analysis
程序员在家做饭方法指南。Programmer's guide about how to cook at home (Simplified Chinese only).
Lightweight coding agent that runs in your terminal
DeepSeek-VL: Towards Real-World Vision-Language Understanding
A One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks
Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory
Technical report of Kimina-Prover Preview.
Train transformer language models with reinforcement learning.
Cryptographic Primitive Code Generation by Fiat
Reasoning in LLMs: Papers and Resources, including Chain-of-Thought, OpenAI o1, and DeepSeek-R1 🍓
A curated list for Efficient Large Language Models
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
An introduction to theorem proving in Lean for the impatient.
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
verl: Volcano Engine Reinforcement Learning for LLMs
Ongoing Lean formalisation of the proof of Fermat's Last Theorem
The AI Browser Automation Framework
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)