Repo đang lênCập nhật hằng ngày từ GitHub

Model Activity Visualiser

KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.

💪🏻 Blazing-Fast and Extremely-Lightweight Internet Reader driven by AI! Your AI-Powered think tank assistant.(Built with Rust, Tauri & Svelte)

A collection of useful datasets for robotics and computer vision

DanceNet -💃💃Dance generator using Autoencoder, LSTM and Mixture Density Network. (Keras)

A service mesh implementation for connecting, control, and observe services in spring-cloud.

An open source distributed tracing & observability platform

Urban sound classification using Deep Learning

Structural implementation of RL key algorithms

Data-Driven Evaluation for LLM-Powered Applications

Goink 桌面 AI 小说创作助手，对话式写作 + 自动状态追踪 + 本地语义搜索。跨平台开箱即用。AI Agent Novel Generator.

An SSH tool dedicated to addressing all pain points · (macOS/Windows/Linux/Android/iOS/ohos(mobile&pc))

Design, conduct and analyze results of AI-powered surveys and experiments. Simulate social science and market research with large numbers of AI agents and LLMs.

On-device meeting capture, dictation, and vault-native knowledge layer for macOS. Nothing leaves your Mac.

Aqueduct is no longer being maintained. Aqueduct allows you to run LLM and ML workloads on any cloud infrastructure.

Open-source Enterprise Grade Search Engine Software

Object detection on multiple datasets with an automatically learned unified label space.

Reproduces ResNet-V3 with pytorch

Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"

GeoTorchAI: A Framework for Training and Using Spatiotemporal Deep Learning Models at Scale

A simple self-driving car module for humans 🚘 🛣️

Deep learned, NVIDIA-accelerated 3D object pose estimation

Production-ready MVP for securely chatting with your documents using pgvector

Run coding agents like infrastructure, not terminal sessions. Warren manages isolation, lifecycle, spend, recovery, and Git delivery on compute you control.

Design hardware-friendly model architectures and migrate existing LLMs with minimal performance loss

RESTai is an AIaaS (AI as a Service) open-source platform. Supports many public and local LLM suported by Ollama/vLLM/etc. Precise embeddings usage, tuning, analytics etc. Built-in image/audio generation with dynamic loading generators. Live chat deployment. Built-in block based graphical language. Prompt versioning and much more...

A Gym for Agentic LLMs

Mac compatible Ollama Voice

零基础入门 AI Agent 的基础教程。不只是教程，也是一个能在本地跑起来的 Agent：读写文件、执行命令、MCP、长期记忆，自带网页端看清每一步。从 100 行最小循环开始，一课加一个能力，最后拆解 Claude Code、Codex 等主流 Agent

Object detection project for real-time (webcam) and offline (video processing) application.

Android client for Hermes Agent - chat with your Hermes sessions from a phone or tablet over local Wi-Fi or a private Tailscale network.

Sequence-to-Sequence learning using PyTorch

Analyze the unstructured data with Towhee, such as reverse image search, reverse video search, audio classification, question and answer systems, molecular search, etc.

推量牛 BullFlow — 开源企业级 RAG 解决方案：从企业知识库、营销内容自动化生产到全域内容分发 | Open-source enterprise RAG solution: knowledge base → automated marketing content → omnichannel publishing. 知识库全链路本地开源模型，无需付费模型；AI Agent 创作图文 / 图片 / 视频，一键发布抖音、小红书、公众号、LinkedIn、YouTube 等 17 个平台。Commercial-grade, multi-tenant, billing & admin built in. MIT

🌥️ 云雾API | OpenAI官方中转服务 🌥️ https://yunwu.ai 🔥 官方价格0.5:1 🔥 0.5元=1$ Token 🔥 高性价比 稳定快速！🔥 | 全球直连 | 无需代理 | 企业级稳定 | gpt3.5 | gpt4 | gpt4o | gpt4o-mini | 207+模型支持

🕵️‍♂️ Library designed for developers eager to explore the potential of Large Language Models (LLMs) and other generative AI through a clean, effective, and Go-idiomatic approach.

Official implementation of GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

[ICLR'25] BigCodeBench: Benchmarking Code Generation Towards AGI

XR Blocks is a lightweight WebXR + AI library for rapidly prototyping advanced AI + XR experiences.

一个基于NoneBot框架的Ai聊天插件，对接OpenAi文本生成接口，实现了机器人的人格 自定义/切换，聊天记忆等功能

ICPR 2020: Facial Expression Recognition using Residual Masking Network

Tool-box for efficient build and debug in Python. Especially for Scientific Computing and Computer Vision.

Code for FLAVR: A fast and efficient frame interpolation technique.

Pytorch implementation of SIREN - Implicit Neural Representations with Periodic Activation Function

Train high-quality text-to-image diffusion models in a data & compute efficient manner

Source-available, self-hosted platform for building AI agent flows - visual editor over a Django backend.

A curated list of awesome AI agents inspired by OpenClaw

Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s on agent tasks, ~41 in fast mode, 512K context. Plus GLM-5.3-Flash, Qwen3.8 and LFM3-Omni. MoE experts tiered across VRAM, pinned RAM and NVMe, with Xolotl Direct NVMe->VRAM. OpenAI + Anthropic API.

赛博医生项目——”赛博华佗“，基于多模态大模型的多功能智能体，一键搭建本地多模态大模型。接入医疗健康相关的知识图谱和知识库后可以进行疾病初诊，病历分析，专业知识问答等功能，成为你的私人医生。赛博华佗项目能帮助实现医疗资源的跨地域传播，让更多人借助大模型改善健康水平。"Cyber ​​Huatuo" - Easy to build a personal doctor agent based on LLM and Knowledge Graph/Knowledge Database.

Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Hermes · VS Code · Windsurf.