ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…

🔬 Harness Vibe Research with Self-evolving AI Scientists

🦞+🔬: NanoResearch: The Autonomous AI Research Assistant

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, Phi4, ...)…

Qwen3 Fine-tuning: Medical R1 Style Chat

一个高自由度的端到端的可定制AI-VTuber。支持对接哔哩哔哩直播间，以智谱API作为语言基座模型，拥有意图识别、长短期记忆（直接记忆和联想记忆），支持搭建认知库、歌曲作品库，接入了当前热门的一些语音转换、语音合成、图像生成、数字人驱动项目，并提供了一个便于操作的客户端。

AI吟美-人工智能主播-Vtuber-桌宠-智能体

AutoMQ is a diskless Kafka® on S3. 10x Cost-Effective. No Cross-AZ Traffic Cost. Autoscale in seconds. Single-digit ms latency. Multi-AZ Availability.

Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face running locally across platforms

Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.

AI Legal Agent Team project files and documentation

This repository shares end-to-end notebooks on how to use various Weaviate features and integrations!

The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.

Open-source vector similarity search for Postgres

Implementation of my RAG system that won all categories in Enterprise RAG Challenge 2

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

🚀WebUI integrated platform for latest LLMs | 各大语言模型的全流程工具 WebUI 整合包。支持主流大模型API接口和开源模型。支持知识库，数据库，角色扮演，mj文生图，LoRA和全参数微调，数据集制作，live2d等全流程应用工具

A Python-based Xiaozhi AI for users who want the full Xiaozhi experience without owning specialized hardware.

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.

A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval

LightRAG与GraphRAG在索引构建、检索测试中的耗时、模型请求次数、Token消耗金额、检索质量等方面进行对比

[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

GAG is a GUI for GPT-SoVITS inference. Just add it to the official integration package and run for a smoother experience.

StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization

基于Dify自主创建的AI应用DSL工作流，你可以免费获取，无论是出于个人需求还是学习目的，它都能为您开启一段充满无限可能的智能之旅。

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 …

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

本项目是一个面向小白开发者的大模型应用开发教程，在线阅读地址：https://datawhalechina.github.io/llm-universe/