Stars
基于 Claude Code 的诉讼法律服务智能分析系统，采用10个 SubAgents 协作的模式，将复杂的诉讼案件分析分解为多个可独立执行的工作流，实现法律文书的工程化生成。
Build resilient language agents as graphs.
ACE LangGraph: ReAct Agent with Adaptive Learning - Integrating ACE framework with LangGraph for self-improving agents
LLM agents built for control. Designed for real-world use. Deployed in minutes.
Easy to maintain open source documentation websites.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
前端智能化场景解决方案UI库，轻松构建你的AI应用，我们将持续完善更新，欢迎你的使用与建议。 官网地址：https://matechat.gitcode.com
"RAG-Anything: All-in-One RAG Framework"
这是一个通过多模态大模型+LangGraph实现的PPT生成系统，包含前端、后端以及Core核心三部分构成。
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
(CVPR 2025) Code of "Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models"
PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides [EMNLP 2025]
Code for the paper "AutoPresent: Designing Structured Visuals From Scratch" (CVPR 2025)
[CVPR 2025] Official implementation for "Empowering LLMs to Understand and Generate Complex Vector Graphics" https://arxiv.org/abs/2412.11102
[NeurIPS 2025] OmniSVG is the first family of end-to-end multimodal SVG generators that leverage pre-trained Vision-Language Models (VLMs), capable of generating complex and detailed SVGs, from sim…
Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning
RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.
AI 智能生成 PPT，通过主题/文件/网址等方式生成PPT，支持原生图表、动画、3D特效等复杂PPT的解析和渲染，支持用户自定义模板，支持智能添加动画，可在线体验。AI generates PowerPoint Presentation, Supports parsing and rendering of complex PPT features such as native charts…
The GPT-based Universal Web Scraper MVP is a solution that leverages GPT models and web scraping libraries to generate scraper code based on user input and website analysis, simplifying the web scr…
A microkernel os for ARM, well ported on Raspberry Pi(s)
verl: Volcano Engine Reinforcement Learning for LLMs
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
AutoCoA (Automatic generation of Chain-of-Action) is an agent model framework that enhances the multi-turn tool usage capability of reasoning models.