Pinned

WeClaws 是一个可快速部署的多用户（注册、登录）微信Agent机器人管理面板。可在Web端管理你的多个AI机器人，支持工具调用、Skills、MCP、子智能体、记忆、做梦、定时任务和沙盒执行等能力。

🤖 Free Search with AI, 💡 Open-Source Perplexity, 📍 Support Ollama/SearXNG, Support Docker deployment. 让AI大模型和搜索引擎回答你的问题，支持本地大模型(Ollama)、聚合搜索引擎SearXNG，支持Docker一键部署。

Claude/OpenAI 协议转换网关 CLI （可以在cc/codex中相互用对方的模型）

Run MCP stdio servers over SSE and SSE over stdio. AI gateway.

AI模型聚合管理中转分发系统，支持将多种大模型转为统一格式调用，支持OpenAI、Claude、Gemini等格式，可供个人或者企业内部管理与分发渠道使用。🍥 The next-generation LLM gateway and AI asset management system supports multiple languages.

LLM inference in C/C++ Fork from https://github.com/ggerganov/llama.cpp.git 自动化构建Docker镜像

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

https://github.com/vllm-project/FlashMLA.git

Fast and memory-efficient exact attention

https://github.com/oneapi-src/oneDNN.git

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

vLLM官方镜像部署DeepSeek模型，生产环境中提供类OpenAI接口服务。

DeepResearch Agent with LangGraph, using any LLM models, search engine, RAG retrieval.

Xorbits Inference(Xinference) is a powerful and versatile library designed to serve language, speech recognition, and multimodal models. With Xorbits Inference, you can effortlessly deploy and serve your or state-of-the-art built-in models using just a single command. Whether you are a researcher, developer, or data scientist...

SGLang is a fast serving framework for large language models and vision language models.