Open Liberty is a highly composable, fast to start, dynamic application server runtime environment

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini C…

An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration

A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.

🎨 Local-first, open-source alternative to Anthropic's Claude Design. ⚡ 19 Skills · ✨ 71 brand-grade Design Systems 🖼 Generate web · desktop · mobile prototypes · slides · images · videos · HyperFra…

分享AI Infra知识&代码练习：PyTorch/vLLM/SGLang框架入门⚡️、性能加速🚀、大模型基础🧠、AI软硬件🔧等

The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.

Spec-driven development (SDD) for AI coding assistants.

从零开始学 AI Agent 开发 | 系统、全面、实战导向的 Agent 开发教程 | 每日自动追踪 arXiv 最新论文 | Learn AI Agent Development from Scratch

slime is an LLM post-training framework for RL Scaling.

A high-throughput and memory-efficient inference and serving engine for LLMs

Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

A clean, Chinese-focused PyTorch reproduction of Kimi Team's Attention Residuals, comparing standard residuals, Full AttnRes, and Block AttnRes on Qwen3-style causal LMs.

Nano vLLM

Autonomous skill evolution engine — fuses AutoResearch's self-driving loop, skill-creator's GT-based evaluation, and Meta-Harness's trace diagnosis to automatically optimize AI agent skills through…

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for p…

Claude Code Snapshot for Research. All original source code is the property of Anthropic.

AI agents running research on single-GPU nanochat training automatically

Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research

A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

Moonshot's most powerful model

CodeViewX is an intelligent code documentation generator based on Anthropic Claude and DeepAgents framework that automatically analyzes codebases and generates professional technical documentation.

Build Real-Time Knowledge Graphs for AI Agents

“AI-Compass”将为社区指引在 AI 技术海洋中航行的方向，无论你是初学者还是进阶开发者，都能在这里找到通往 AI 各大方向的路径。旨在帮助开发者系统性地了解 AI 的核心概念、主流技术、前沿趋势，并通过实践掌握从理论到落地的全过程。

A live stream development of RL tunning for LLM agents