BizClaw
✨A Rust-based self-hosted multi-tenant AI Agent platform with trait-driven modular architecture, supporting 15 LLM providers, 9 communication channels, and MCP protocol extension, deployable from Raspberry Pi to cloud servers, suitable for Vietnam market and enterprises requiring data localization.
OtherRAGModel Context Protocol
Ragent
✨Enterprise-grade RAG Agent platform built on Java 17 + Spring Boot 3 + React 18, featuring multi-channel retrieval, intent recognition, conversation memory, model fault tolerance, and MCP tool integration.
OtherModel Context ProtocolAI Agents
MLX-Audio
✨A text-to-speech (TTS), speech-to-text (STT), and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis optimized for Apple Silicon.
AgentGPT
✨A browser-based platform that enables you to configure, deploy, and run autonomous AI agents that can work toward any goal you set.
ChatWiki
✨An AI-powered chat-based wiki knowledge tool that supports collaborative editing and intelligent Q&A features.
Planning with Files
✨A file-based planning and organization tool that enhances productivity by storing tasks, goals, and ideas in a structured filesystem。
OpenOutreach
✨An open-source LinkedIn automation tool for B2B lead generation that simulates human-like behavior to send personalized connection requests and follow-up messages, with complete local deployment to avoid cloud service risks.
RuoYi AI
✨A full-stack AI development platform that helps developers quickly build and deploy personalized AI applications, featuring multi-model integration, AI platform compatibility, and local RAG solutions。
Agent Rules
✨A collection of reusable rules and knowledge documents for AI coding assistants like Claude Code and Cursor, designed to help developers collaborate more effectively with AI.
LLaMA Factory
✨A unified, efficient fine-tuning framework for 100+ LLMs and VLMs, published at ACL 2024. It integrates various fine-tuning methods (LoRA, QLoRA, Full) and training algorithms (DPO, PPO), enabling efficient training on consumer-grade GPUs. Featuring a Web UI (LLaMA Board), it significantly lowers the barrier from data preparation to model deployment.