Lists (1)
Starred repositories
轻松一键续杯 Cursor Pro，保持14天试用不掉。【支持 Claude 4】
Mirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions intelligently. By capturing real-time visual data and consolidating it into structured mem…
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
Financial data platform for analysts, quants and AI agents.
Text-audio foundation model from Boson AI
Java raft/config/mq/rpc engine, zero dependencies, 10X faster
A multi-agent framework written in Rust that enables you to build, deploy, and coordinate multiple intelligent agents
A high performance and flexible authorization/permission engine built for developers and inspired by Google Zanzibar
Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, 20+ clouds, or on-prem).
Bootstrap Kubernetes the hard way. No scripts.
Automatically crawl arXiv papers daily and summarize them using AI. Illustrating them using GitHub Pages.
Build memory-native AI agents with Memory OS — an open-source framework for long-term memory, retrieval, and adaptive learning in large language models. Agent Memory | Memory System | Memory Manage…
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
SWE-bench: Can Language Models Resolve Real-world Github Issues?
Trae Agent is an LLM-based agent for general purpose software engineering tasks.
An open-source AI agent that brings the power of Gemini directly into your terminal.
Apache Airflow - A platform to programmatically author, schedule, and monitor workflows
slime is an LLM post-training framework for RL Scaling.
The simplest, fastest repository for training/finetuning small-sized VLMs.
Open-source Python library built for fast and reliable connections to different LLM providers
A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
轻量级大语言模型MiniMind的源码解读，包含tokenizer、RoPE、MoE、KV Cache、pretraining、SFT、LoRA、DPO等完整流程