开源桌面 AI Agent & CLI· 长期记忆 · 多 Agent/CLI Fleet · 语音TTS/ASR · 0 API Key · Open-source desktop AI agent & CLI — long-term memory, multi-agent, voice & a CLI worker fleet

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

🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!

A way to analyze tool call accuracy, structural correctness and tool recall for LLM's. Uses Native tool calling.

Public Evaluation Result Archieve for BFCL

A framework for efficient model inference with omni-modality models

Python bindings for llama.cpp

mcp的webui界面，支持客户端连接多个sse服务端，支持 openai、deepseek、qwen等大模型，另外附上构建的 agent的 stdio和sse的简单 天气查询的完整示例

vLLM plugin for tcu (hardwar backend demo name) for beginners to add a plugin to vllm

Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

sentence-transformers to onnx 让sbert模型推理效率更快

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

Build a simple CMD chat interface with llama.cpp and C++

程序开发相关的书籍与文档，多为 PDF 文件。

YoloX NPU for the RK3566/68/88

Integrate the DeepSeek API into popular software

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Awesome resources of yousan.ai(closely related to deep learning).

一键拥有你自己的 ChatGPT 网页服务。 One-Click to deploy your own ChatGPT web UI.（基于 langchain 实现的插件版本 Plugin version implemented based on langchain）

3D Visualization of an GPT-style LLM

Ready-to-use Media-over-QUIC / SRT / WebRTC / RTSP / RTMP / LL-HLS / MPEG-TS / RTP live media server and media proxy that allows to read, publish, proxy, record and playback real-time video and aud…

ffmpeg 拉取rtsp h264流， 使用mpp解码， 目前在firefly 板子上跑通了

books and docments

High-speed Large Language Model Serving for Local Deployment

《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

人工智能学习路线图，整理近200个实战案例与项目，免费提供配套教材，零基础入门，就业实战！包括：Python，数学，机器学习，数据分析，深度学习，计算机视觉，自然语言处理等热门领域

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …

Ultralytics YOLOv5 in PyTorch > ONNX > CoreML > TFLite

From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :)