Trending AI projects

A curated, engineering-focused collection of prompts, frameworks, and papers for AI language models, covering both copy-paste templates and advanced prompt-engineering techniques.

A genuine AI‑agent skill set for 1C:Enterprise development, providing high‑level commands (create, build, edit, test, publish, etc.) for external processors, reports, forms, roles, databases, web testing, and more. Installable as Claude Code/Cursor/Codex plugins or via a helper script, with PowerShell (Windows) or Python runtimes.

This plugin adds Google Antigravity OAuth support to OpenCode, so you can authenticate with your Google account and use Antigravity models like gemini-3.1-pro and claude-opus-4-6-thinking while benefiting from Antigravity rate limits.

An open-source robot simulator providing a complete development environment to model, program, and simulate robots, vehicles, and mechanical systems.

RuoYi AI is an open‑source, enterprise‑grade AI assistant platform. It combines multi‑model LLM access, local RAG with Milvus/Weaviate/Qdrant, a Langchain4j‑based multi‑agent framework, and a drag‑and‑drop visual workflow designer. Built on Spring Boot 3 (backend) and Vue 3 (frontend), it ships with Docker compose files for one‑click deployment of the backend, admin UI, user UI, and supporting services (MySQL, Redis, vector DBs, MinIO). The project provides separate repos for backend, admin panel, user frontend, and demo apps, and is licensed under MIT.

A community-maintained catalog of connector skills and workflow templates designed to help users build safe, effective, and task-specific AI agents for Meta Muse.

An Android input method based on the Rime engine that provides Wubi and Pinyin support with AI-enhanced predictive text and offline speech recognition.

Open‑Inspect is an open‑source platform for AI‑driven background coding agents. It lets trusted team members launch AI sessions that run in full‑stack development sandboxes (Node, Python, git, browser automation) via a web UI, Slack, GitHub, Linear or webhooks. Sessions can span multiple repositories, support reusable “skills”, spawn parallel child sessions, and be triggered on schedules or events. The system runs on Cloudflare Workers (control plane) and various cloud sandbox backends, and supports multiple LLM providers (Claude, OpenAI, Grok, OpenCode).

一个中文求职技能包，三步自动完成岗位调研、简历改写（翻译真实经历而非编造）、分轮次面试准备，含严格的质量闸门和诚实底线，可通过一行命令装进 Claude Code 等 AI 工具，遵循 CC BY-NC-ND 4.0 许可证。

Type4Me is a free, open‑source macOS voice‑input app (macOS 14+) that transcribes speech in real time and can optionally send the text to any LLM for polishing, translation, Q&A, or Mac control. It offers cloud‑based or fully offline speech recognition, customizable prompt‑based modes, hot‑key activation, history tracking, and integration via a URL scheme. The project is MIT‑licensed and aims to provide a low‑cost, extensible alternative to commercial voice‑input solutions.

This repository contains the official code examples and exercise solutions for the third edition of the book Hands-on Machine Learning with Scikit-Learn, Keras and TensorFlow.

A structured prompt-based workflow and CLI tool that guides users through research, PRD creation, and technical design to build software projects with AI coding assistants.

Pillow is a friendly, actively maintained fork of the Python Imaging Library that adds comprehensive image processing and file format support to Python applications.

A collection of 86 modular skills for AI coding agents that ensures generated iOS and SwiftUI code follows the latest Apple frameworks and Swift 6.3 standards.

A lightweight server that provides a REST API and MCP interface for managing multiple WhatsApp accounts, enabling automated messaging, scheduling, and event-driven integrations.

A family of open-source speech and sound generation models providing high-fidelity TTS, multi-speaker dialogue, voice design, real-time streaming, and sound effect generation.

A deployable starter kit for building virtual towns where AI characters socialize, featuring a JS/TS framework and support for multiple LLM providers.

A simulation platform for physical AI and robotics that combines a multi-physics engine, photo-realistic rendering, and a cross-platform compiler for scalable research.

textbee is an open-source SMS gateway that lets you use your own Android phone to send and receive messages via API, avoiding the per-message fees of commercial providers.

A collection of AI agent skills following the Agent Skills specification to assist researchers in writing, illustrating, and managing literature for NSFC grant applications.

LLMForEverybody 是一个面向大语言模型学习者的开源资料库，配套网站 LearnLLM.AI。它包含精选面试题库、从 2017 年 Transformer 开始的系统化论文研读（30 余篇，每篇配有视频和讲解）、围绕 Agent/RAG/微调等方向的实战课程，以及按 11 个章节组织的“AGI 之路”系统文章（覆盖预训练、部署推理、微调、量化、并行、Prompt、Agent、评估等主题）。项目提供中英俄三种语言，配套视频教程在 Bilibili 和 YouTube 持续更新，并为 GitHub 用户提供优惠码。

z-skills is a collection of reusable local Agent Skills covering web scraping, video download, document parsing, audio generation, Markdown-to-Word/PDF, grounded Q&A, and more—designed to plug into Codex or Claude Code for Chinese content creation and automation. Each skill includes trigger words, scripts, and evaluation examples so agents can reliably carry out complex workflows.

A memory-augmented desktop writing system for long-form novels that prevents AI from losing track of plot, character consistency, and world-building details.

The official desktop application for ComfyUI that provides a self-contained, GPU-ready environment to install, run, and manage multiple independent AI generative workflows without dependency conflicts.

SOMA‑X is a Python library that offers a unified, differentiable representation of parametric human bodies and hands, supporting multiple identity models (MHR, SMPL‑X, MANO, etc.) and providing fast skinning via NVIDIA Warp. It includes `SOMALayer` and `SOMAHandLayer` for full‑body and hand meshes at several levels of detail, plus tools for pose inversion, rig control, and data I/O, making it useful for animation, pose‑estimation fitting, and synthetic data generation.

A collection of low-level agentic design patterns and skills for AI agents that prioritize subtraction and refinement to prevent AI-generated bloat and repository rot.

A Claude Code plugin that transforms a conversation into a full album production pipeline, coordinating research, lyrics, and audio mastering for AI-generated music.

The repository hosts Feynman, a CLI‑based AI research assistant that can perform literature reviews, paper audits, replication planning, and draft writing by orchestrating multiple LLM‑driven agents. It installs via script or npm, connects to model providers, queries many scholarly APIs, and stores results with provenance. Telemetry is optional.

LumiBot is an open‑source Python framework that lets you write a single trading strategy and run it as a backtest, paper‑trading bot, or live bot. It adds a built‑in LLM‑agent runtime (research, debate, risk‑check, execution) while keeping a deterministic Python gate before any broker order. Supports stocks, options, futures, forex, crypto and prediction markets, with integrations for 12 brokers (Alpaca, IBKR, Tradier, etc.). Install via pip, generate starter code with `lumibot init`, backtest on free Yahoo data, then paper‑trade or go live using the same code.

An interactive coding platform for practicing PyTorch implementations of operators and architectures from scratch to prepare for ML engineering interviews.

Speakr is a self-hosted, private platform that transcribes audio and video into searchable, intelligent notes, featuring speaker diarization, AI-powered summarization, and cross-recording semantic search.

OpenCode Telegram Bot is a Node.js client that lets you control a locally‑running OpenCode AI‑coding server from Telegram. It supports remote prompting, session management, live progress tracking, model switching, file browsing, scheduled tasks, voice input, and strong security (user‑ID whitelist). Install via npm, configure with a BotFather token and your Telegram ID, and interact through a set of slash commands.

A lightweight bot that bridges Feishu/Lark messenger with local Claude Code or Codex CLI, enabling chat-based interaction with local coding agents.

A Claude Code plugin that enables the AI to analyze videos and YouTube URLs by extracting frames and transcribing audio via multiple backends.

A multi-tenant AI agent platform built in Go that provides a unified gateway for 20+ LLM providers and 7 messaging channels with built-in multi-agent orchestration.

An open-source platform that unifies wearable device data from multiple providers into a single API, making health metrics accessible to AI agents and health applications.

A Python CLI that unifies job searching, welfare filtering, local short‑listing, AI‑enhanced resume work, and recruiter actions on BOSS 直聘, exposing all functions through a JSON‑enveloped, schema‑driven interface for both human users and AI agents.

A permanent memory system for AI agents that uses a binary tree of summaries and a CLI tool to maintain persistent knowledge across sessions.

herdr‑annotate is a Rust plugin for the Herdr terminal AI‑assistant that captures selected terminal text, formats it as numbered Markdown annotations, and lets you copy, archive, paste, or send those notes directly to the active LLM. The Full variant also includes a TUI (plannotator‑tui) for reviewing Markdown files and the agent’s previous replies. Installable on macOS, Linux, and Windows.

OpenSERP is an open‑source SERP API and CLI that scrapes Google, Bing, Yandex, Baidu, DuckDuckGo and Ecosia, returning structured JSON/markdown results without API keys. It supports single‑engine queries, multi‑engine “megasearch” with deduplication, optional page‑content extraction, image search, proxies, caching, Docker deployment, and has SDKs for JavaScript/TypeScript, Python, an MCP server for AI agents, and an n8n node. Ideal for LLM grounding, SEO tracking, and any workflow needing live web search data.

Typesense is an open-source, fast, typo-tolerant search engine built in C++ that serves as a simpler alternative to Elasticsearch and a self-hostable alternative to Algolia. It supports full-text, vector, semantic/hybrid, and conversational (RAG) search, plus image and voice search, all through a simple HTTP API.

SkyRL is an open‑source, modular RL framework for training LLMs to perform long‑horizon, tool‑use tasks. It bundles a core training stack (with Tinker API support), an agent layer, a Gymnasium‑style environment library, and a cross‑platform backend, and provides recipes for cutting‑edge models and real‑world applications.

The repository provides an AI‑driven “skill” that turns a software project’s recent updates into a short promotional video. It extracts changelog items, re‑uses the product’s UI components, writes copy, animates with GSAP/Three.js, synthesises music and sound effects, and finally exports an MP4 plus an editable video project. The skill is installed via the Vercel Skills CLI and works with Claude Code, Codex, or similar AI coding assistants.

A collection of on-device inference frameworks for Apple platforms providing speech-to-text, text-to-speech, and speaker diarization using Core ML.

A text-to-speech conversion tool that turns ePub, PDF, and text files into high-quality audio with synced subtitles using the Kokoro-82M model.

SeeCut is an AI-driven editing agent that automatically transforms talking-head videos into dynamic, evidence-backed short videos by using AI to watch, edit, and iteratively improve its own cuts.

LLM Zoomcamp is a free 10-week open-source course by DataTalks.Club that teaches you to build production-ready LLM applications hands-on, covering RAG, vector search, AI agents, evaluation, and monitoring. You can take it as a live cohort (with deadlines, peer review, and a certificate) or self-paced (no certificate). Prerequisites are basic Python, command line, and Docker — no ML experience or GPU needed. The course includes 7 modules, a capstone project, and strong community support via Slack.

AI Homepage is a Chrome extension that uses your Anthropic API key to send a brief summary of your recent browsing (up to 8 pages) to Claude, which then generates a personalized new‑tab page in any style you describe.