ArcticInference: vLLM plugin for high-throughput, low-latency inference

ArcticTraining is a framework designed to simplify and accelerate the post-training process for large language models (LLMs)

Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch

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

An MCP-based chatbot | 一个基于MCP的聊天机器人

Echo: A desk mate can talk to you, translate, monitor PC , make memos. It even have AI camera.

⛄ 基于OpenCV开源的微信二维码引擎移植的二维码扫码识别库

Bytebot is a self-hosted AI desktop agent that automates computer tasks through natural language commands, operating within a containerized Linux desktop environment.

《Build a Large Language Model (From Scratch)》是一本深入探讨大语言模型原理与实现的电子书，适合希望深入了解 GPT 等大模型架构、训练过程及应用开发的学习者。为了让更多中文读者能够接触到这本极具价值的教材，我决定将其翻译成中文，并通过 GitHub 进行开源共享。

Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL.

Suna - Open Source Generalist AI Agent

ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models

🌐 WebAgent for Information Seeking bulit by Tongyi Lab: WebWalker & WebDancer & WebSailor https://arxiv.org/pdf/2507.02592

A MULTI-GENERATOR ENSEMBLE FRAMEWORK FOR NATURAL LANGUAGE TO SQL

Unified Vision-Language-Action Model

Official repository for the AAAI2025 paper (Can We Get Rid of Handcrafted Feature Extractors? SparseViT: Nonsemantics-Centered, Parameter-Efficient Image Manipulation Localization through Spare-Cod…

DAMO-ConvAI: The official repository which contains the codebase for Alibaba DAMO Conversational AI.

Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ

ModelScope-Agent: An agent framework connecting models in ModelScope with the world

Integrate cutting-edge LLM technology quickly and easily into your apps

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning, achieving state-of-the-art performance on 38 out of 60 public benchmarks.

cube studio开源云原生一站式机器学习/深度学习/大模型AI平台，支持sso登录，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，边缘计算，标注平台，自动化标注，大模型微调，vllm大模型推理，llmops，私有知识库，AI模型应用商店，支持模型一键开发/推理/微调，支持国产cpu/gpu/npu芯片，支持R…

基于大模型的视频监控危险行为检测系统，集成YOLOv8、GPT-4V等视觉和多模态AI模型，提供高精度危险行为识别、场景理解和智能告警分析。

Low cost (~$300) humanoid robot 🌱

Modified lerobot for bambot

System 2 Reasoning Link Collection