Trending AI projects

A real-world reinforcement learning pipeline for SO101 and AgileX robotic arms that enables iterative data collection, value function training, and policy deployment.

AllData is a comprehensive data middle-platform that provides an end-to-end suite for data integration, storage, governance, and AI application development.

agentcookie is a tool that continuously and securely syncs your browser cookies from a local macOS machine to remote Linux environments, enabling automated agents to access authenticated websites without manual login.

Recommenders is a toolkit of classical and deep learning recommendation algorithms, along with utilities for data preparation, evaluation, hyperparameter tuning, and deployment. It helps researchers and developers prototype and bring recommendation systems to production.

A robotic intelligence stack for the Unitree Go2 that enables autonomous navigation, dynamic obstacle avoidance, and semantic scene understanding using the Odin1 sensing module.

A Python library that automatically learns web scraping rules from sample data, eliminating the need for manual CSS selectors or XPath expressions.

Oumi is an open‑source platform that covers the entire lifecycle of foundation models—data prep, training (SFT, LoRA, DPO, GRPO), tool‑using agentic fine‑tuning, multimodal support, evaluation with LLM judges, and fast inference/deployment via vLLM or cloud endpoints. It offers a CLI, Docker image, and a large library of ready‑to‑run YAML recipes for models ranging from 10 M to 400 B parameters.

A modular development environment for Termux on Android that provides a unified CLI to install and manage programming languages, databases, and AI coding agents.

A personalized diet management platform that uses LLMs, RAG, and multimodal AI to provide intelligent meal planning, nutritional tracking, and recipe recommendations.

A secure proxy for Model Context Protocol (MCP) servers that allows AI agents to scale to hundreds of tools while reducing token costs and preventing tool poisoning attacks.

LightlyTrain is a framework for the entire computer vision model lifecycle, enabling users to pretrain, fine-tune, and distill state-of-the-art models for detection and segmentation tasks with support for edge deployment.

A step-by-step AI video production workflow for Codex and WorkBuddy that guides users from topic selection to final rendering of story-based videos.

AI Creator Academy is a free, open-source curriculum that teaches creators and agencies how to turn AI-generated image, video, and audio into priced, sellable services. Each module ends with real pricing ranges and client-finding steps, not just tool tutorials.

一个精心整理的网页开发资源合集，收录了AI提示词（粘贴到ChatGPT、Claude、Cursor等即可生成完整网页）和现成可运行的网页代码，每个条目都附有预览截图和使用说明，帮助开发者快速构建精美页面。

A curated, categorized directory of Agent Skills (instruction packages for AI coding tools) that also ships example skills and installer scripts for a quick start; notably, the installer only sets up the repo's own bundled examples, not every project the list links to.

A collection of recipes and tools for TinyFish, an API layer that enables AI agents to search the web, fetch clean content, and perform complex browser-based automation tasks.

This repository contains the source code, build scripts, and technical examples for the book "Learning Deep Representations of Data Distributions," enabling users to compile the text or reproduce its figures.

Speech Swift is an open‑source Swift package that provides on‑device speech AI for Apple Silicon. It bundles many modern ASR, TTS, translation, and voice‑agent models (e.g., Qwen3‑ASR, Whisper‑ASR, Omnilingual ASR, Qwen3‑TTS, CosyVoice, PersonaPlex) built on MLX and Core ML, so you can run inference locally with no cloud calls. Each model is a separate Swift‑Package‑Manager product, making it easy to add only what you need. The repo includes quick‑start code, SwiftUI UI helpers, Homebrew install, and extensive documentation.

A native AI keying runtime and OFX plugin for DaVinci Resolve and Foundry Nuke that provides automated, ML-accelerated background removal for video editors.

A guided, browser-based exercise in which you use GitHub Copilot to maintain a small school website, learning how to have the AI explain, write, plan, and review code — complete in under an hour.

A repository of 141 Bible translations in 85 languages, formatted as clean per-verse JSON/XML files intended for app development and AI use. Code and data are MIT-licensed (with original text rights reserved to owners). Comes with known caveats: built via a crawler, so minor encoding/syntax issues may exist, and some versions are incomplete or have quirks.

Machinist is a self-hosted control plane for orchestrating AI coding agents, allowing teams to run and manage autonomous development workflows on their own infrastructure.

A training-free universal inpainting sampler for ComfyUI that enables high-quality image, video, and audio inpainting across almost any pretrained diffusion model.

roboflow/notebooks is a GitHub repository containing 61 Jupyter notebook tutorials for computer vision, covering models like YOLO, SAM, Gemini, and Qwen2.5-VL. Each notebook can be opened in Colab, Kaggle, or SageMaker Studio Lab, and includes links to related blog posts, videos, and papers. It's designed for hands-on learning of tasks like object detection, segmentation, OCR, and data extraction.

A searchable reference repository collecting deep learning techniques and example projects for satellite and aerial image analysis, organized by task (classification, segmentation, object detection, etc.) with a companion website.

A toolset for AI Agents to create and edit Word documents following Chinese academic formatting standards, featuring Markdown-to-docx conversion and LaTeX-to-native-formula support.

OpenAnt (knostic/OpenAnt) is a genuine open-source software project that applies LLMs to security: it scans code repositories to find and verify vulnerabilities, and can generate and vet trusted patches. It's a practical, system-level tool with a CLI, configurable LLM adapters, and a web UI — not a list or tutorial.

A curated, community-maintained list of the latest research papers and code implementations for time series analysis, covering topics like forecasting, anomaly detection, and foundation models.

LangGraph 101 is a curated set of hands-on notebooks and standalone agent examples that teach you to build LLM agents with LangChain, LangGraph, and Deep Agents — from basic tool-using agents to production-grade multi-agent systems with human oversight.

Bencium Marketplace is a plugin marketplace for Claude Code that offers 17 skills and tools for design, marketing, architecture, and productivity. It provides a simple way to install specialized skills, from UX design to AI-assisted build loops.

Agentic-RL-Most-Detailed-Intro is a learning hub for Agentic RL, offering a visualization dashboard for comparing experiments, a runnable code implementation, and curated technical papers. It aims to help newcomers and practitioners understand and apply reinforcement learning for tool-using agents.

A comprehensive, curated directory of official Anthropic resources, developer tools, and community-built integrations for the Claude AI ecosystem.

An async-first agent harness that provides a durable framework for managing LLM sessions, tool execution, and session persistence.

A KV cache compression library for LLM inference that uses orthogonal rotation and optimal quantization to reduce VRAM usage and extend context windows.

cc‑sdd is an npm‑installed toolkit that adds a spec‑driven, autonomous SDLC workflow to eight AI coding agents. It creates structured markdown specs, runs per‑task implementation with test‑driven development, independent review, and auto‑debug, and supports customization of templates and rules. The default install uses Claude Code; other agents (Codex, Cursor, Copilot, etc.) are available via flags.

This is an awesome list curating papers, open models, benchmarks, and commentary around System One models and Jev, a type of AI model that outputs calibrated probabilities for typed decisions. It provides a single organized reference for the Jev ecosystem.

A local-first AI-powered desktop workbench for novelists to manage world-building, plot outlines, and chapter writing with an extensible skill-based AI assistant.

Agent Craft is a systematic open-source teaching project that guides you through building full-stack AI agents in Python, from basic LLM calls to RAG, LangGraph, MCP, and deployment. It provides 15 modular, runnable examples with blog explanations to help you understand not just how to call frameworks but how agents think, decide, and act.

Bub is a framework and application for building and running customizable AI agents that can be embedded into Python projects or used as a standalone tool with plugins and integrations.

A privacy-preserving human pose estimation system that uses WiFi Channel State Information (CSI) and machine learning to detect poses without cameras.

A collection of reproducible Jupyter Notebook labs for the textbook An Introduction to Statistical Learning, featuring automated environment setup and dependency management.

A tool for rewriting long documents like academic papers to reduce AI-generated traces while preserving original formatting and document structure.

A hands-on educational course that teaches developers how to use GitHub Copilot CLI to perform coding tasks, debugging, and workflow automation directly from their terminal.

franken_ocr is a pure-Rust, CPU-only engine that runs specialized vision-language models for document parsing, chart extraction, and music transcription without requiring GPUs or Python.

A scalable and lightweight object storage service that uses Postgres for metadata management and supports multiple protocols including HTTP, TUS, and S3.

A curated collection of DESIGN.md files that provides AI agents with the necessary specifications to generate accurate, high-quality Japanese web UI with proper typography and layout rules.

This project is a curated, regularly updated repository of academic papers focused on LLM-based multi-agent systems, categorized by framework, application, and simulation use cases.

A curated list of research papers, datasets, and benchmarks on spatial intelligence in Vision-Language Models, organized as an awesome-list with tables of methods and links to code.