Stars
Build Real-Time Knowledge Graphs for AI Agents
FlowGram is a node-based flow building engine that helps developers quickly create workflows in either fixed layout or free connection layout modes
chat log tool, easily use your own chat data. 聊天记录工具，轻松使用自己的聊天数据
This is a speech interaction system built on an open-source model, integrating ASR, LLM, and TTS in sequence. The ASR model is SenceVoice, the LLM models are QWen2.5-0.5B/1.5B, and there are three …
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
eBPF Observability - Distributed Tracing and Profiling
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Converts MCP protocol's SSE transport layer to a standard HTTP request/response.
A vector search SQLite extension that runs anywhere!
🍒 Cherry Studio is a desktop client that supports for multiple LLM providers.
🐬DeepChat - A smart assistant that connects powerful AI to your personal world
A powerful multi-database server implementing the Model Context Protocol (MCP) to provide AI assistants with structured access to databases.
A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。
Making large AI models cheaper, faster and more accessible
⚡️Wren AI is your GenBI Agent, that you can query any database with natural language → get accurate SQL(Text-to-SQL), charts(Text-to-Charts) & AI-generated insights in seconds.
Community maintained hardware plugin for vLLM on Ascend
SuperSonic is the next-generation AI+BI platform that unifies Chat BI (powered by LLM) and Headless BI (powered by semantic layer) paradigms.
A MULTI-GENERATOR ENSEMBLE FRAMEWORK FOR NATURAL LANGUAGE TO SQL
cube studio开源云原生一站式机器学习/深度学习/大模型AI平台，算法链路全流程，支持大数据平台对接，notebook在线开发，拖拉拽任务流pipeline编排，多机多卡分布式训练，超参搜索，推理服务VGPU虚拟化，边缘计算，标注平台，自动化标注，deepseek等大模型sft微调/奖励模型/ppo强化学习训练，vllm/ollama/mindie大模型多机推理，私有知识库，AI模型…
CRProxy (Container Registry Proxy) is a generic image proxy
A powerful tool for creating fine-tuning datasets for LLM
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the si…
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
SGLang is a fast serving framework for large language models and vision language models.