Trending AI projects

An automated tool for downloading YouTube videos and re-uploading them to AcFun and Bilibili, featuring AI-driven subtitle generation, translation, content moderation, and hardware-accelerated transcoding.

A local desktop application that automatically identifies and extracts highlight clips from long video files using custom detection rules and transparent, explainable analysis.

Awwwards-mcp is an open-source server that enables AI agents to search for design inspiration, perform deep technical analysis of web animations and structures, and generate functional code projects based on real-world websites.

A personal collection of AI-generated patches for the Morphe framework, designed to modify and customize various Android applications.

A Python SDK for building Gemini‑powered or locally‑run AI agents. It provides high‑level `Agent`/`Conversation` APIs, streaming responses, multimodal inputs, custom tool registration, safety policies, and support for both Google Vertex AI and offline Gemma‑4 models via LiteRT‑LM.

A repository of standards‑compliant, AI‑driven plugins (called *skills*) that let large‑language‑model coding assistants perform concrete .NET development tasks—building, debugging, upgrading, testing, UI work, and even ML integration—across Copilot, Claude, Cursor, and OpenAI Codex. Includes a public metrics dashboard and ready‑made agentic workflows.

awesome-jev is a curated list of public projects and practices built on Jev, TypeSafe AI's model for typed decisions (choice, score, boolean) with confidence. It organizes entries by application domain, requires public, citable, genuinely Jev-based examples, and explicitly warns that inclusion is not endorsement — no quality or security review is done.

这是一个深度学习笔记合集，涵盖CV、NLP、大模型和Agent，配套视频教程、数据集、交流群及就业指导服务。

A Python SDK that provides a unified API gateway to access professional data across legal, enterprise, academic, and logistics domains for AI agents.

A collection of AI agents and plugins for legal professionals that automates workflows across commercial, corporate, privacy, and litigation practices.

A collection of AI agent skills that automatically generate interactive, single-file HTML animations for technical presentations, system diagrams, and product UI demos.

Read Frog is an open‑source browser extension that adds AI‑powered translation, explanation, text‑to‑speech, subtitle translation, custom AI actions, and flashcard/spaced‑repetition tools to any web page, supporting 20+ LLM providers and free translators.

A plug‑in library that adds Cloudflare‑specific “Agent Skills” to AI coding assistants (Claude Code, Codex, Cursor, VS Code, etc.). Each skill teaches the agent how to work with a Cloudflare product—Workers, Wrangler, Durable Objects, Turnstile, Cloudflare One, and more—by providing up‑to‑date docs, CLI commands, and API calls via Cloudflare’s remote MCP server. Install via the native plugin marketplace of the target agent or manually copy the skill folders.

Whaleness is a native mobile client for DeepSeek Harness that enables real-time AI agent interaction, workspace management, and file previews across Android and iOS devices using Kotlin Multiplatform.

ModSearch is a free‑first plug‑in that gives LLM chat apps (DeepSeek, Claude Code, Codex, etc.) live web, page‑fetch, and X (Twitter) search capabilities. It routes requests through engines like Firecrawl (key‑less default), Antigravity CLI, Tavily, Exa, Grok Build, or a local fetcher, with automatic fail‑over and key rotation. Installable via a single command, it works out of the box and returns structured, sourced answers.

hunk is a terminal‑based, interactive diff viewer that adds a UI layer (sidebar, split/unified panes, mouse support) on top of Git/Jujutsu/Sapling diffs. It includes built‑in support for inline AI/agent annotations and an extensible TypeScript plugin system, making it a useful front‑end for AI‑assisted code review.

An open-source, self-hosted platform for annotating images, video, audio, and 3D data to create high-quality datasets for AI training.

FlashInfer is a GPU‑kernel library (with a Python package) that provides ultra‑fast, low‑precision attention, GEMM, MoE, and sampling operations for LLM inference. It automatically selects the best backend (FlashAttention‑2/3, cuDNN, CUTLASS, TensorRT‑LLM) for a wide range of NVIDIA GPUs, from Turing up to Blackwell, and is already used by popular inference servers like vLLM and TensorRT‑LLM.

eve is a Vercel‑backed, filesystem‑first framework for building, running, and deploying durable AI agents. Agents are defined by a clear folder layout (prompts, typed tools, skills, channels, schedules) and can be scaffolded with `npx eve init`. The CLI handles model selection, local dev (`npm run dev`), and Vercel deployment with web‑chat integration.

SlopMonster is a Python‑only command‑line checker that spots five common AI‑writing patterns (buzz‑words, certain sentence structures, dense punctuation, promotional three‑item lists, and unverified numeric claims) in English text. It gives a 0‑5 score, integrates with LLMs for a two‑pass edit, and can be run in CI to block AI‑flavored copy.

pdf‑inspector is a Rust‑based library (with Python, Node, and WASM bindings) that rapidly classifies PDFs, extracts position‑aware text, and converts it to clean Markdown. It can route only the pages that need OCR to a local model, saving time and cost. Benchmarks show it faster and more accurate than similar tools on a 200‑PDF test set.

Magic Context is a CortexKit plugin that gives coding‑agent LLMs a self‑managing, long‑term memory. It captures knowledge from chat history, consolidates it overnight, and recalls relevant facts on demand, eliminating the usual context‑compaction pauses and letting a single session run for weeks.

XHS-Downloader is a tool that extracts and downloads posts, images, videos, and live photos from Xiaohongshu (RedNote) by pasting links. It offers multiple interfaces: a GUI, a terminal UI, a command-line mode, an API server, and a browser userscript, and can run locally or via Docker.

Agent Client Protocol (ACP) is a language‑agnostic JSON‑RPC standard that lets code editors talk to generative‑AI coding agents. The repository provides the Rust schema crate, versioned JSON‑Schema files, and links to official SDKs (Kotlin, Java, Python, Rust, TypeScript). It defines a stable protocol version (1) negotiated at runtime, enabling editors and agents to interoperate without custom adapters.

短剧工作台 | 无限时长视频的 MiniMax H3 工作流 | ComfyUI 本地短剧与长视频生成插件

Hermes Desktop is an Electron‑based GUI that installs, configures, and lets you chat with the Hermes Agent LLM assistant. It supports local or remote back‑ends, dozens of LLM providers, a streaming chat UI with slash commands, profile & session management, tool integrations, scheduling, and many messaging‑gateway bots.

An enterprise-grade multi-agent orchestration framework that provides pre-built architectures for coordinating multiple AI agents in sequential, concurrent, and hierarchical workflows.

Rapid-MLX is an open-source LLM inference server for Apple Silicon Macs, built on Apple's MLX framework. It serves open-weight models (like Qwen) via OpenAI- and Anthropic-compatible APIs, tuned for fast, reliable tool calling by coding agents — with claims of up to 4× faster decoding than Apple's reference server, plus continuous batching, persistent prefix caching, a CLI, a desktop app, and image-generation support.

HolmesGPT is an open‑source AI SRE agent that automatically investigates production incidents. It connects to >30 observability and cloud‑native data sources (Kubernetes, Prometheus, Datadog, AWS, Azure, etc.), streams large datasets safely, reasons with any LLM, and writes findings back to alerts, tickets or Slack. Operator mode runs continuously in Kubernetes to detect problems proactively. The project is Apache‑2.0, CNCF‑sandbox, and can be installed via CLI, Docker, or Helm.

Effective HTML provides prompt‑templates (“skills”) that let LLMs generate self‑contained, responsive HTML wireframes, prototypes, diagrams, and design briefs, installable via `npx skills` or Claude/Codex plugins.

Mooncake is a high-performance infrastructure project that provides a disaggregated, KV cache-centric architecture to improve the efficiency, scalability, and latency of large-scale LLM inference and training.

A tool for removing image backgrounds using pre-trained AI models, available as a CLI, Python library, or HTTP server.

Rescript is an open-source, transcript-based media editor: drop in video/audio, get a local transcript with word timestamps and speaker labels, then edit by deleting text — the media follows. All processing happens on-device. Runs in the browser or as a desktop app (macOS/Windows/Linux). It supports filler/silence removal, timeline split/trim, multiple export formats, and NLE/DAW timeline export. Licensed under PolyForm Noncommercial (prior versions remain MIT).

Ix is a system intelligence tool that parses codebases into a persistent graph of symbols and relationships, allowing humans and AI agents to query structure instead of searching text.

Claude Code skill that generates a product‑launch video from a website URL using deterministic HTML animation, music‑driven timing, and AI‑directed storytelling.

TabPFN is a transformer-based foundation model for tabular data that enables rapid, high-accuracy classification and regression without the need for complex data preprocessing or hyperparameter tuning.

lieflat‑gongwen is a data‑driven “skill” for Chinese AI agents that lets them generate official government‑style documents (work plans, research reports, party‑building material) by matching statistical style fingerprints extracted from a 1 M‑character corpus. It detects the document type, applies numeric style constraints, builds a skeleton, fills the text with an LLM, and runs a Python self‑check to ensure the output stays within the measured ranges. The repo includes the rule set, example drafts, and a non‑commercial license.

COLMAP is an open‑source Structure‑from‑Motion and Multi‑View Stereo pipeline that automatically turns collections of photos into 3‑D models. It offers a GUI, command‑line tools, Python bindings, GPU‑accelerated feature extraction, and cross‑platform binaries, making it a go‑to foundation for research and applications in computer vision, robotics, AR/VR, and any workflow that needs camera poses and dense scene geometry.

A Rust‑based demo that programmatically renders a short video of a virtual camera tracking every glyph an AI‑agent types in a terminal‑style UI. It uses the fframes library, a custom SkSL shader for realistic lens effects, and Python‑generated sound, all driven by deterministic JSON data.

An open-source metadata management platform that turns enterprise data into trusted context for humans and AI agents through discovery, governance, and observability.

Kuna is a Rust‑written binary decompiler designed for LLM agents. It’s fast (top of DecBench), offers CLI, web‑assembly, and Ghidra integrations, and provides an extensible, phase‑based pipeline with tunable options. The project aims for autonomous, agent‑driven refinement of decompilation quality.

InsightFace is an open‑source 2D/3D face analysis library offering detection, recognition, alignment, video redaction, person‑level matching, and a self‑hosted server with REST API. Implemented in PyTorch/MXNet, it provides pretrained models, automatic hardware backend selection, and tools for large‑scale face search.

Emdash is a cross‑platform desktop app that runs multiple AI coding agents (Claude Code, Codex, Copilot, etc.) in parallel, each in its own Git worktree. It integrates issue trackers, supports remote SSH projects, and keeps all state locally, offering a unified UI for reviewing diffs and merging AI‑generated code.

KVMem is an inference management tool that enables long-context LLM execution by tiering KV cache data across GPU VRAM, system RAM, and SSDs, allowing models to handle massive conversation histories on consumer hardware.

A Python‑only server that exposes 39 market‑data, technical‑analysis, screener and back‑testing tools via the Model Context Protocol (MCP). AI assistants (Claude, ChatGPT, Cursor, Copilot, etc.) can call these tools with natural language prompts and receive live data, indicator tables, or interactive charts inside the chat. Self‑hosted for free (MIT license) or available as a hosted SaaS (TradingMCP) for $9 / mo.

An open‑source guide and starter kit that turns an Obsidian vault into a personal “second brain” automatically curated by a Claude Code LLM agent. It provides a vault template, 18 LLM‑driven skills, 72 slash commands, scheduled sub‑agents, and detailed docs covering setup, ingestion, graph handling, and maintenance.

StemDeck is a local, open-source application that uses AI to split songs into individual instrument stems for practice and study without uploading your audio to the cloud.

An MCP server that integrates Firecrawl's web scraping and search capabilities into AI agents, enabling them to search, scrape, and interact with the live web for real-time context.