Repo đang lênCập nhật hằng ngày từ GitHub

Achieve the llama3 inference step-by-step, grasp the core concepts, master the process derivation, implement the code.

让 AI 实时看见你的屏幕：按变化量筛选帧、多帧拼进一张图，静止画面几乎不花 token

A curated list for Self-Improvement in Foundation Model Based Agentic Systems.

GPU worker client for the Talos network. Pairs with your Talos account, serves open-model inference jobs over a WebSocket, and reports uptime for payouts.

Distill your knowledge, memories, and decisions into an open-source, inspectable AI Agent Twin.

A framework to evaluate the generalization capability of safety alignment for LLMs

CookHero是一个基于 LLM + RAG + Agent + 多模态的智能饮食与烹饪管理平台，支持智能菜谱查询、个性化饮食计划、AI 饮食记录、营养分析、Web 搜索增强，以及可扩展的 ReAct Agent / Subagent 工具体系，帮助厨房新手轻松成为“烹饪英雄”。

A tiny experimental language designed to be targeted by coding LLMs

Fast, stateless LLM for your shell: qq answers; qa runs commands

Fast integer versions of trained LSTM models

Java OCR 识别组件（基于Tesseract OCR 引擎）。能自动完成图片清理、识别 CAPTCHA 验证码图片内容的一体化工作。Java Image cleanup, OCR recognition component (based Tesseract OCR engine, automatically cleanup image and identification CAPTCHA verification code picture content).

A curated list of open source tools used in analytics platforms and data engineering ecosystem

Arbitrary object tracking at 50-100 FPS with Fully Convolutional Siamese networks.

Dream to Control: Learning Behaviors by Latent Imagination

🧿 AutorizePro是一款强大越权检测 Burp 插件，通过增加 AI 辅助分析 && 进一步优化检测逻辑，大幅降低误报率，提升越权漏洞检出效率。 [ AutorizePro is a authorization enforcement detection extension for burp suite. By adding Ai-assisted analysis, it significantly reduces the false positive rate and improves the efficiency of vulnerability detection.

AI-powered assistant workbench for FreeCAD — generate 3D models from natural language

a magical LLM desktop client that makes it easy for *anyone* to use LLMs and MCP

🚧 Under construction — no-training RefMod reference adapters for MiniMax H3 (compress reference images/videos into tiny latents, no training needed).

Open-Source Tracing Platform

[MSG-GAN] Any body can GAN! Highly stable and robust architecture. Requires little to no hyperparameter tuning. Pytorch Implementation

Trajectory Planner in Multi-Agent and Dynamic Environments

Build chatbots and conversational experiences using React

Turn detection for full-duplex dialogue communication

Secure memory management for AI Agents • Ensures data integrity • Reduces hallucinations • Maintains consistent long-term context

AI-Hedge-Fund for Crypto 🚀 AI-powered hedge fund for cryptocurrency trading, leveraging LLM agents for intelligent decision-making.

🎨ComfyUI standalone pack with 40+ custom nodes. | ComfyUI 大号整合包，预装大量自定义节点（不含SD模型）

Span-level grounding verification for RAG, code, and tool-grounded AI outputs.

The official implementation of our SIGGRAPH 2020 paper Interactive Video Stylization Using Few-Shot Patch-Based Training

Matlab implementation of the ECO tracker.

Kaggle datascience bowl 2017

:fire: Use pre-trained models in PyTorch to extract vector embeddings for any image

Just a VLM Agent Can Play Robots

C++ implementation of Qwen-LM

LLM for Long Text Summary (Comprehensive Bulleted Notes)

Synmetrix – production-ready open source semantic layer on Cube

Ollama alternative for Rockchip NPU: An efficient solution for running AI and Deep learning models on Rockchip devices with optimized NPU support ( rkllm )

Tesseract based OCR for android

Medical image processing in Python

A meta-skill that produces skills. Point it at any codebase and it distills the project's rules, workflows, and hard-won lessons into a dedicated skills/<name>/ directory — a project skill that becomes the single source of truth every AI agent (Cursor, Claude Code, Codex, Windsurf, Gemini) consults before every task.

Making decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet

OpenAmika: MekaHime's AI companion Amika, open source. Live2D avatar, real-time voice, long-term memory, OpenRouter or Ollama brain.

This is tensorflow implementation for paper "Deep Image Matting"

[ECCV 2026] A diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding.

Keras beit,caformer,CMT,CoAtNet,convnext,davit,dino,efficientdet,edgenext,efficientformer,efficientnet,eva,fasternet,fastervit,fastvit,flexivit,gcvit,ghostnet,gpvit,hornet,hiera,iformer,inceptionnext,lcnet,levit,maxvit,mobilevit,moganet,nat,nfnets,pvt,swin,tinynet,tinyvit,uniformer,volo,vanillanet,yolor,yolov7,yolov8,yolox,gpt2,llama2, alias kecam

Build fully-functioning computer vision models with PyTorch

Code for ACL 2018 paper: "Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting. Chen and Bansal"

Cursos completos de IA dictados por Humai

A prompt engineering functional programming language

The all-in-one RWKV runtime box with embed, RAG, AI agents, and more.