Herramientas de automatización con IA

AI agent that generates detailed research reports from a single query. Searches multiple sources, synthesizes findings, and cites references.

One-click prompt to upgrade your AI agent memory system to Karpathy LLM Wiki pattern. Send to Claude Code / Cursor / Windsurf — auto audits, compiles fragments, resolves contradictions, builds structured wiki.

Ready-to-use Claude Code configurations: 600+ agents, 200+ commands, 55+ MCPs, and project templates. Install any template with one command.

Curated .cursorrules files for 30+ tech stacks. Drop into your project root so Cursor AI follows your coding standards automatically.

Open agent skills ecosystem from Vercel. Install packaged SKILL.md instruction sets into Claude Code, Cursor, Codex, and 30+ AI agents with one command. 13,000+ GitHub stars.

Convert any URL to clean markdown for AI consumption. Free API at r.jina.ai strips ads, navigation, and clutter. Used by AI agents for web research and RAG.

Convert any URL to clean, LLM-friendly markdown with a simple prefix. Just prepend r.jina.ai/ to any URL. Handles JS-rendered pages, PDFs, and images. 10K+ stars.

Add a context meter, AI asset discovery, and session info to your Claude Code status bar. Scans 300+ installed assets (skills, agents, MCP, plugins) and surfaces the most relevant ones as you type. Zero token cost, 100% local.

High-performance port of OpenAI Whisper in C/C++. No Python, no GPU required. Runs on CPU, Apple Silicon, CUDA, and even Raspberry Pi. Real-time transcription.

First open-source agentic video production system. 11 pipelines, 52 tools, 400+ agent skills. Describe a video in plain language, AI handles scripting to final render. AGPLv3, 910+ stars.

Audiobookshelf is an open-source audiobook and podcast server with progress sync, chapter navigation, mobile apps, and multi-user support — a self-hosted Audible alternative.

内容审稿官。评估口播稿/视频脚本的质量，给出具体诊断和改稿建议，并提供改写版本。当用户说"帮我看看这篇稿子"、"review一下"、"这个内容怎么样"时触发。

Self-hosted AI code completion and chat assistant. Privacy-first alternative to GitHub Copilot. Supports 20+ models, repo-aware context, and IDE integrations. 33K+ stars.

Piped is a self-hosted alternative YouTube frontend that proxies video streams through your server, removing ads and tracking while providing a fast, modern viewing experience.

LibreTranslate is a self-hostable translation API powered by open-source Argos Translate models. No API keys, no rate limits, no data sent to third parties — a drop-in replacement for Google Translate when privacy matters.

MCP server that lets Claude Code use Gemini, OpenAI, Grok, and Ollama as a unified AI dev team. Features model routing, CLI-to-CLI bridge, and conversation continuity across 7+ providers.

Add persistent, personalized memory to AI agents and assistants. Mem0 stores user preferences, past interactions, and learned context across sessions.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or appli...

Curated video AI tools: Remotion (programmatic video), Manim (math animation), MoviePy (editing), Whisper (speech-to-text), ElevenLabs (voiceover). Build automated video pipelines.

Community fork of Bolt.new. Prompt, edit, and deploy full-stack web apps with any LLM provider. 19K+ GitHub stars.

Free open-source resume builder with AI integration. Supports Claude, GPT, Gemini for content generation. Drag-and-drop, PDF export, self-hostable, privacy-first. MIT, 36,000+ stars.

Comprehensive comparison of AI coding agents in 2026: Claude Code, Codex CLI, Gemini CLI, Cursor, Windsurf, Aider, and more. Features, pricing, model support, and use case recommendations.

CLI that reads ~/.claude logs and breaks down Claude Code token spend by day, session, and project — pluggable into your statusline.

High-performance code intelligence MCP server. Indexes repos in milliseconds via tree-sitter AST, supports 66 languages, sub-ms graph queries. MIT, 1,300+ stars.

OpenAI official coding agent CLI. Supports Agent Skills, custom prompts, and IDE integration. Open-source alternative to Cursor.

Official Remotion Agent Skill for Claude Code and Codex. 30+ rules covering animations, transitions, captions, FFmpeg, audio visualization, voiceover, 3D, and more.

Modern open-source CRM with AI features. Custom objects, kanban views, email sync, workflow automation. NestJS + React + PostgreSQL. AGPL-3.0, 43,700+ stars.

Cherry Studio Knowledge Base ingests PDFs, Office docs, Markdown into a local vector index. Query offline, BYOK any LLM. Data stays on your machine.

Python library for video editing: cutting, concatenating, adding titles, effects, and audio. Script-based video production for automation pipelines.

Production-tested CLAUDE.md template for Claude Code projects. Covers coding conventions, test requirements, git workflow, and project-specific AI instructions.

A single CLAUDE.md file that reduces Claude Code output verbosity by 63%. Includes 5 specialized profiles for coding, benchmarks, agents, and analysis workflows.

bottom (btm) is a customizable, cross-platform graphical system monitor for the terminal. It displays CPU, memory, network, disk, temperature, and process information with interactive charts — a modern alternative to top, htop, and btop.

Lapce is a high-performance code editor written in Rust with a native GUI. It features modal editing (Vim-like), remote development via SSH, built-in terminal, LSP support, and a plugin system powered by WASI — all with sub-millisecond rendering.

BookStack is a simple, self-hosted documentation platform organized by Shelves, Books, Chapters, and Pages. WYSIWYG/Markdown editor, LDAP, and powerful search.

AI-powered end-to-end short video pipeline: topic in, finished video out. Auto-generates script, materials, subtitles, and background music. 53,000+ stars.

Curated n8n workflow templates for data sync, notifications, CRM automation, and more. Import directly into your n8n instance.

CAMEL is a multi-agent framework for studying scaling laws of AI agents. 16.6K+ GitHub stars. Up to 1M agents, RAG, memory systems, data generation. Apache 2.0.

changedetection.io monitors websites for content changes and sends alerts. Track price drops, restock alerts, content updates, and page modifications automatically.

Open-source AI coding agent with 140K+ stars. TUI-first design, LSP integration, works with Claude, OpenAI, Google, or local models. Two built-in agents: build and plan. MIT license.

Build knowledge graphs from documents for smarter RAG. Local and global search over entity relationships. By Microsoft Research. 31K+ stars.

Connect Claude Code, Cursor, Gemini CLI, or VS Code to Google Stitch for AI-driven UI design. Create projects, generate screens from text, edit designs, manage design systems — all via MCP.

Open-source autonomous coding agent for software engineering tasks. Multi-provider LLM support. By ByteDance. 11K+ stars.

The largest open-source ChatGPT prompt library with 155K+ GitHub stars. Community-curated prompts for every role — developer, writer, translator, analyst, and more. Self-hostable.

LangChain framework for building resilient, stateful AI agents as graphs. Supports cycles, branching, persistence, human-in-the-loop, and streaming. 28K+ stars.

Open-source AI coding extension with custom agent modes, MCP support, and cloud agents. Fork of Cline with 22K+ stars.

Curated guide to the best models available on Ollama for coding, chat, and reasoning. Compare Llama, Mistral, Gemma, Phi, and Qwen models for local AI development.

Bubble Tea is a powerful little TUI framework for Go based on The Elm Architecture. Build terminal applications with composable components, events, and commands. Part of the Charm ecosystem (Lip Gloss, Gum, Wish, Huh). Powers lazygit, soft-serve, and many CLI tools.

Build dynamic knowledge graphs from AI agent conversations. Graphiti tracks entity changes over time, resolves contradictions, and provides temporal-aware queries.

Create and edit videos with code. MIT-licensed alternative to Remotion with API-driven rendering and dynamic inputs. Forked from Motion Canvas.

Autonomous AI coding agent that lives in VS Code. Cline creates files, runs commands, uses MCP servers, and handles multi-step tasks with Claude or GPT models.

Official prompting guide from Anthropic for Claude. System prompts, chain-of-thought, few-shot, XML tags, tool use, and advanced techniques.

GPT-4 system prompt that creates a personalized AI tutor. Adapts to your learning level, language, and style. Used by 30K+ learners.

思维蒸馏。把一大段零散想法快速理成结构化大纲，一步到位不来回对话。当用户丢来一堆乱七八糟的想法、语音转文字的braindump、或说"帮我理一下"时触发。

Fast, accurate PDF to Markdown + JSON converter. Handles tables, images, equations, code blocks, and multi-column layouts. GPU-accelerated. 33K+ GitHub stars.

Pushed via CLI: video-production-skill-push.md

NocoDB turns any SQL database into a smart spreadsheet with REST APIs. Open-source Airtable alternative with views, automations, and team collaboration.

Gradio-based web interface for Browser-Use AI agent. Automate web browsing with visual feedback, persistent sessions, and HD recording. Supports 6+ LLM providers. 15,800+ stars, MIT.

Build AI agents with persistent memory using MemGPT architecture. Letta manages context windows automatically with tiered memory for stateful LLM applications.

Comprehensive comparison of all AI coding agents in 2026. Covers Claude Code, Cursor, Codex, Gemini CLI, Cline, Roo Code, Windsurf, and Aider with feature matrices and recommendations.

Command-line tool for Lark/Feishu Open Platform with 200+ commands and 19 AI Agent Skills. Covers Messenger, Docs, Base, Sheets, Calendar, Mail, Tasks, and more.

Self-hosted search engine aggregating 70+ sources. No tracking, no ads. Perfect backend for AI search apps. 27K+ stars.

Actual is an open-source personal finance app with envelope budgeting, bank sync, multi-device sync, and local-first architecture — a YNAB alternative.

Surya is a document OCR toolkit with 19.5K+ GitHub stars. Text recognition in 90+ languages, layout analysis, table detection, reading order, and LaTeX OCR. Benchmarks favorably against cloud OCR serv

Connect Claude Code to Dida365/TickTick via MCP. OAuth auth, full CRUD for tasks and projects, batch operations. Works with Claude Code, Cursor, and other MCP-compatible tools.

Claude Code skill for PowerPoint. Create slide decks, add charts, format layouts, import content, and generate presentations from text.

Outline is a beautiful, real-time collaborative knowledge base and wiki. Markdown editor, nested documents, integrations with Slack and Figma, and full-text search.

Official OpenAI terminal coding agent. Reads your codebase, writes code, runs commands, and manages files from the command line. Multi-model support with sandbox execution. 20,000+ stars.

Cherry Studio Custom Models adds any OpenAI-compatible endpoint — proxy, local, or third-party. Mix Claude, GPT, Gemini, DeepSeek, Ollama side-by-side.

Layers swarm and hive-mind multi-agent orchestration on top of Claude Code with 64 specialized agents, SQLite memory, and parallel execution.

Claude Code 身体追踪 Skill：支持多用户自助 onboarding、飞书群聊饮食记录、AI 营养估算、飞书多维表格仪表盘同步、每日卡片推送。包含 body-track（日常记录）、body-track-dashboard（仪表盘同步）和 body_push.py（定时卡片推送脚本）。

Full-stack AI desktop app with RAG, agents, MCP support, and multi-model chat. AnythingLLM manages documents, embeddings, and vector stores in one private interface.

Add persistent, personalized memory to any AI agent. Learns user preferences, adapts context, reduces tokens. 51K+ stars, used by 100K+ devs.

Official Anthropic plugin that turns Claude Code into an autonomous loop. Adds /ralph-loop and /cancel-ralph for long-running self-improving task execution.

F5-TTS is a diffusion transformer TTS system with flow matching. 14.3K+ GitHub stars. Multi-speaker, voice chat, Gradio UI, CLI inference, 0.04 RTF on L20 GPU. MIT code.

Postiz is an open-source social media scheduling tool with AI content generation, multi-platform posting, team collaboration, and analytics — a Buffer/Hootsuite alternative.

Agent harness built on LangGraph by the LangChain team. Features planning tools, filesystem backend, and sub-agent spawning for complex multi-step tasks like codebase refactoring. 16,500+ stars.

All 17 official Agent Skills by Anthropic for Claude Code: document generation, dev tools, creative design, and enterprise workflows.

Open-source virtual whiteboard for hand-drawn style diagrams. Export to SVG/PNG, real-time collaboration, and AI integrations for generating diagrams from text descriptions. 90,000+ stars.

Claude Code agent for auditing Solidity smart contracts. Reentrancy, overflow, access control, gas optimization, and best practices.

The shared Agent Skills format used by Claude Code, OpenAI Codex, and Gemini CLI. Write skills once, use across all major AI coding tools.

Directory and management platform for MCP servers. Discover, install, and monitor Model Context Protocol servers for Claude Code, Cline, and other AI coding tools.

High-performance MCP server that indexes codebases into persistent knowledge graphs. Supports 66 languages, sub-millisecond queries, and claims 99% fewer tokens than raw file context. 1,100+ stars.

In-depth comparison of the three leading AI coding tools in 2026. Covers pricing, context window, MCP support, agent capabilities, and best use cases for each platform.

Glow is a terminal-based Markdown reader from Charmbracelet. Renders Markdown beautifully in the terminal with syntax highlighting, word wrapping, and theming. Also features a stash for bookmarking Markdown files.

Candle is a Rust-native ML framework focused on inference performance, small binaries, and serverless deployment. It runs Llama, Whisper, Stable Diffusion, and other PyTorch models in pure Rust — no Python required.

Convert PDFs, scans, and complex documents into clean Markdown or JSON for RAG and LLM pipelines. 57K+ GitHub stars.

Faster Whisper is a reimplementation of OpenAI Whisper using CTranslate2, up to 4x faster with less memory. 21.8K+ GitHub stars. GPU/CPU, 8-bit quantization, word timestamps, VAD. MIT licensed.

Python library by Microsoft that converts PDF, DOCX, PPTX, XLSX, images, audio, and HTML to clean Markdown. Perfect for feeding documents into LLM context windows. 8,000+ stars.

OpenSpec provides structured specifications that AI coding agents follow to produce consistent code. 36K+ stars. Works with Cursor, Claude Code, Copilot. MIT.

A spec-driven development system with 48.6k GitHub stars. Adds phase-based planning, multi-agent execution, verification gates, and state persistence to Claude Code, Cursor, Gemini CLI and 9 more runtimes. Install with one npx command.

Autonomous coding agent in VS Code. Creates/edits files, runs commands, browses the web, and uses MCP tools — with human approval at every step. 60K+ stars.

Fork of Cline with custom agent modes, boomerang orchestration, and multi-model routing. Create specialized AI agents for coding, review, and architecture tasks.

Logseq is a privacy-first, open-source platform for knowledge management and collaboration. Outliner-based with bidirectional links, block references, queries, and graph visualization. Local-first with optional sync. The open-source alternative to Roam Research.

Microsoft research tool for prompt compression. Reduce token usage up to 20x while maintaining LLM performance. Solves lost-in-the-middle for RAG. MIT, 6,000+ stars.

Open-source real-time voice AI by Kyutai. Full-duplex speech conversation with 200ms latency, emotion recognition, and on-device processing. Apache 2.0 licensed.

Deploy any LLM on any hardware — phones, browsers, GPUs, CPUs. Compiles models for native performance on iOS, Android, WebGPU, CUDA, Metal, and Vulkan. 22K+ stars.

Webstudio is an open-source Webflow alternative with a visual drag-and-drop editor, full CSS support, headless CMS integration, and self-hosting on Cloudflare.

Search, install, and manage MCP servers from Smithery's registry of 6,000+ servers. One command to connect any MCP server to Claude, Cursor, or other AI tools. AGPL-3.0.

Lark/Feishu CLI skill for knowledge base. Create and manage knowledge spaces, organize document nodes and shortcuts.

Docmost is an open-source Confluence and Notion alternative for team wikis and documentation, featuring real-time collaboration, rich editor, and permission management.

Lark/Feishu CLI skill for creating reusable custom skills. Wrap atomic APIs or orchestrate multi-step workflows.

Open-source AI developer agent by Block (Square). Goose automates coding tasks with extensible toolkits, session memory, and MCP server support in your terminal.

Open-source infinite canvas library for building whiteboard, diagramming, and design applications. React component with real-time collaboration. Used by AI tools for visual generation. 40,000+ stars.

Educational multi-agent framework by OpenAI. Ergonomic agent handoffs, tool calling, and context variables. Minimal abstraction over Chat Completions API. 21K+ stars.

Stirling PDF is the #1 open-source PDF tool on GitHub. Merge, split, convert, compress, OCR, sign, and edit PDFs — all self-hosted with no data leaving your server.

Generate speech in 1100+ languages with voice cloning. XTTS v2 streams with under 200ms latency. 44K+ GitHub stars.

Serena is a coding agent MCP server with semantic code retrieval and editing. 22K+ stars. Understands classes, functions, symbols for precise context-aware edits. MIT.

Open-source RAG engine with deep document understanding. Parses complex PDFs, tables, images. Agent-powered Q&A with citations. Multi-model. 77K+ stars.

KoboldCpp is a self-contained local LLM inference engine that runs GGUF models with GPU acceleration on consumer hardware, providing an OpenAI-compatible API and built-in web UI without requiring Python or complex setup.

Self-hosted tool that converts GitHub, GitLab, and Gitea repositories into AI-powered knowledge bases with Mermaid diagrams and conversational AI. MIT license, 3,000+ stars.

Official MCP server that gives AI agents safe, scoped access to your local filesystem. Read, write, search, and manage files and directories with configurable permissions. 4,000+ stars.

Gemini CLI extension for Google Stitch. AI-driven UI design, component generation, and design system management.

Build real-time knowledge graphs for AI agents by Zep. Temporal awareness, entity extraction, community detection, and hybrid search. Production-ready. 24K+ stars.

macOS 守护脚本：监控 TickTick 番茄钟状态，自动驱动 TickMato 浮窗

WezTerm is a GPU-accelerated cross-platform terminal emulator and multiplexer written in Rust. Configured entirely in Lua with built-in tabs, splits, SSH multiplexing, image display, and a rich set of terminal features.

Paperless-ngx is an open-source document management system that scans, OCRs, indexes, and archives all your physical and digital documents for full-text search.

收割对话中的洞察。回顾当前对话，提取有价值的认知突破、比喻、决策、情绪发现、方法论，存入 Obsidian 收集箱。当用户说"收割"、"沉淀一下"、"harvest"、对话快结束时触发。

Microsoft's Python tool to convert Office docs, PDFs, images, audio, and HTML to clean Markdown for LLM pipelines. Also available as MCP server.

Official prompting guides from OpenAI: GPT-5.2, Codex, Meta Prompting, and Realtime API guides. The definitive reference for OpenAI model optimization.

Starlight is a full-featured documentation framework built on Astro that generates fast, accessible, and SEO-friendly docs sites from Markdown and MDX with built-in navigation, search, and internationalization.

Ghostfolio is an open-source personal finance dashboard for tracking stocks, ETFs, crypto, and other investments with real-time market data and performance analytics.

Build advanced chatbots visually with 34+ blocks. Embed anywhere, collect results in real-time. OpenAI integration, custom themes, analytics. Self-hostable. 9,800+ stars.

Axum is a web application framework built on Tokio, Tower, and Hyper. Focuses on ergonomics and modularity with a macro-free routing API, seamless Tower middleware integration, and type-safe extractors. The official Tokio team web framework.

DeepEval is a pytest-like testing framework for LLM apps with 30+ metrics. 14.4K+ GitHub stars. RAG, agent, multimodal evaluation. Runs locally. MIT.

Open-source alternative to Twilio for building AI voice applications. Programmable voice with Answer, Say, Gather, Dial verbs. NodeJS SDK, OAuth2, Google Speech API. MIT, 7,800+ stars.

Compare top LLM gateway and proxy tools for routing AI requests. Covers LiteLLM, Bifrost, Portkey, and OpenRouter for cost optimization, failover, and multi-provider access.

Framework for building stateful, multi-actor AI agent applications as directed graphs. Supports cycles, branching, persistence, and human-in-the-loop patterns. By LangChain. 8,000+ stars.

Verba is an open-source RAG (Retrieval-Augmented Generation) chatbot from the Weaviate team. Drop in PDFs, web pages, or notes; pick a model (OpenAI, Ollama, Anthropic); and get a polished chat UI with semantic search built in.

Curated collection of 50+ production-ready AI application examples with full source code. RAG chatbots, AI agents, multi-model apps, and more. Each recipe is a complete, runnable project. 6,000+ stars.

A TypeScript-first framework for building cross-browser extensions with hot reload, auto-imports, and built-in support for Chrome, Firefox, Safari, and Edge from a single codebase.

Firefly III is an open-source personal finance manager for tracking expenses, budgets, and bank accounts. Self-hosted with full privacy, multi-currency, and powerful reporting.

Complete guide to Claude Code hooks for automating actions before and after tool calls. Set up linting, testing, notifications, and custom validation with shell commands.

Woodpecker is a lightweight, container-based CI/CD engine forked from Drone. Simple YAML pipelines, Docker-native execution, and multi-platform support.

A powerful open-source tool for large-scale geospatial data visualization built on deck.gl and Mapbox GL.

OpenAI's open-source speech recognition model. Transcribe audio/video to text with word-level timestamps in 99 languages. Essential for subtitle generation.

Fish Speech is a state-of-the-art open-source TTS system supporting 80+ languages. 29K+ GitHub stars. 4B dual-AR model, voice cloning, emotional control with 15K+ tags, real-time inference.

Phaser is a fun, free and fast 2D game framework for making HTML5 games for desktop and mobile web browsers. Canvas and WebGL rendering, physics systems (Arcade, Matter.js), sprite atlases, tilemaps, and animation built in.

Open-source TypeScript framework for building AI agents with built-in Memory, RAG, Guardrails, MCP, Voice, and Workflow support. Includes LLM observability console for debugging.

创作搭档。用户有零散的想法/观点，通过深度采访引导，帮助梳理成结构化的口播稿。当用户想聊一个话题、想把想法整理成内容、或说"我有个想法"时触发。

Hand-curated collection of 60+ papers, 50+ tools, benchmarks, and courses for prompt engineering and context engineering. Covers CoT, RAG, agents, security, and multimodal. Apache 2.0.

Python scraping library powered by LLMs. Describe what you want to extract in natural language, get structured data back. Handles dynamic pages. 23K+ stars.

Mihomo (formerly Clash.Meta) is a Go-based network proxy kernel supporting multiple protocols including SOCKS5, HTTP, Shadowsocks, VMess, VLESS, Trojan, and WireGuard. It features a powerful rule-based routing engine for transparent proxying and traffic management.

Apache ECharts is a powerful, interactive charting and data visualization library for browsers. 40+ chart types, canvas/SVG rendering, streaming data, and GPU acceleration. The enterprise choice used by Alibaba, Baidu, and countless dashboards.

A blazing-fast inference server for text embedding and reranking models. TEI serves any Sentence Transformers or cross-encoder model with optimized Rust and CUDA kernels, token-based dynamic batching, and an OpenAI-compatible API.

Ant Design is an enterprise-class UI design language and React component library created by Alibaba. 60+ production-ready components with comprehensive patterns, internationalization for 30+ languages, and a rich theme system. The go-to choice for admin dashboards.

超聚焦检测 prompt

KiCAD MCP Server lets MCP clients drive KiCAD for PCB automation; verified 997★ with KiCAD 9.0+ and a Node+Python build (`npm install` + `npm run build`).

Anthropic's open-source post-task cleanup agent that Boris Cherny runs after every Claude Code session. Refactors for clarity without changing behavior.

TGI is Hugging Face's production-grade LLM inference server. It powers HF Inference Endpoints with continuous batching, tensor parallelism, quantization, and OpenAI-compatible APIs — handling thousands of requests per second.

LangChain4j integrates 20+ LLM providers and 30+ vector stores into Java apps. 11.4K+ stars. Unified API, RAG, MCP, Spring Boot. Apache 2.0.

Docker Compose template by n8n that bootstraps a complete local AI environment with n8n workflow automation, Ollama LLMs, Qdrant vector database, and PostgreSQL. 14,500+ stars.

Monica is a self-hosted personal CRM that helps you nurture relationships with family and friends. Track birthdays, conversations, kids' names, gifts given, and the little details that sustain long-term relationships.

Official Model Context Protocol specification reference. Understand MCP architecture, message format, tool definitions, resource types, and transport protocols for building servers.

Kokoro is an 82M parameter text-to-speech model delivering quality comparable to larger models. 6.2K+ GitHub stars. Supports English, Spanish, French, Japanese, Chinese, and more. Apache 2.0.

Build AI agents with Alibaba Qwen models featuring tool calling, code execution, RAG, and browser control. Supports MCP protocol and custom tool development.

Run large language models locally on your machine. Supports Llama 3, Mistral, Gemma, Phi, and dozens more. One-command install, OpenAI-compatible API.

Sanitized public Chrome MCP bundle for Codex: persistent CDP proxy, real Chrome login-state control, background tabs, focus protection, multi-agent isolation, and cached chrome-devtools-mcp startup fallback.

EleutherAI's framework for reproducible evaluation of language models across hundreds of benchmarks, providing the standard evaluation backend used by the Open LLM Leaderboard and research papers.

40+ official Gemini CLI extensions by Google: coding, security, Google Cloud, databases, and partner integrations.

Open-source Chrome extension with multi-agent AI for web automation. Free alternative to OpenAI Operator. 12K+ stars.

Open-source workflow automation with 400+ integrations and built-in AI capabilities. Build AI agents, RAG pipelines, and automation workflows with a visual editor.

btop is a resource monitor that shows usage and stats for CPU, memory, disks, network, and processes. Beautiful TUI with mouse support, gradients, themes, and low memory footprint. The modern successor to htop and bashtop.

Official OpenAI plugin that adds Codex code review and task delegation inside Claude Code. Get adversarial reviews, rescue debugging, and multi-model collaboration.

Remotion skill rule: Rendering transparent videos in Remotion. Part of the official Remotion Agent Skill for programmatic video in React.

Curated collection of extracted system prompts from 32+ production AI tools including ChatGPT, Claude, Cursor, v0, Manus, Devin, Windsurf, and Perplexity. MIT license, 5,700+ stars.

draw.io is a free, browser-based diagramming application that supports flowcharts, UML, network diagrams, and more. Works offline as a desktop app on Windows, macOS, and Linux with no account required.

用IFS（内在家庭系统）的方式陪用户和内在的部分工作。当用户情绪困扰、想探索内在感受、说"我想做IFS"、或情绪明显需要被处理时触发。

Translate PDF scientific papers while preserving math formulas, charts, and layout. Supports Google, DeepL, OpenAI, Ollama. CLI, GUI, MCP, Docker, Zotero plugin.

MkDocs turns a folder of Markdown files into a fast static documentation site. With themes like Material for MkDocs, plugins, and search built in, it is the go-to choice for technical docs that need to stay close to the code.

MCP server that gives AI agents persistent memory using a local knowledge graph. Stores entities, relationships, and observations across sessions for Claude Code.

Install 130+ specialized Claude Code subagents across 10 categories: core dev, language experts, infra, security, data/AI, DevEx, and business. Plugin-based with 16.7K GitHub stars.

Autonomous AI that understands instructions, researches the web, plans, and writes code. Open-source Devin alternative. 19K+ stars.

语言炼金术。把内容/观点炼成比喻、双关、新词、金句、开头钩子、反直觉表达、场景化开头。当用户想给内容增色、找好的表达方式、或说"帮我炼一下"时触发。

Composio connects AI agents to 250+ tools (GitHub, Slack, Jira, DBs) with managed auth. 15K+ stars. Python/JS SDK, MCP support. AGPL-3.0.

Onyx (formerly Danswer) is a self-hosted AI chat with RAG, custom agents, and 40+ knowledge connectors. 20.4K+ stars. Enterprise search. MIT.

Build polished Windows desktop applications using Microsoft's latest native UI framework with Fluent Design, XAML, and the Windows App SDK.

An open-source TTS system that can clone any voice from just one minute of audio data, combining GPT-style language modeling with VITS synthesis for natural speech generation.

A Rust library for creating cross-platform desktop applications with web-based UIs by leveraging each operating system's native webview engine with minimal overhead.

Manage multiple MCP servers from one dashboard. Smart routing, hot-swap config, OAuth 2.0 auth. Deploy via Docker in one command. Apache-2.0, 2,000+ stars.

Tauri lets you build smaller, faster, and more secure desktop and mobile applications with any web frontend. Rust backend + OS native WebView (no bundled Chromium) produces ~3MB binaries compared to Electron 150MB.

Agent framework by Alibaba with function calling, code interpreter, RAG, and MCP support. Built for Qwen 3.0+. 15K+ stars.

Framework for building real-time voice AI agents. STT, LLM, TTS pipeline with sub-second latency. Supports OpenAI, Anthropic, Deepgram, ElevenLabs. 9.9K+ stars.

Jan is an open-source ChatGPT alternative that runs LLMs locally with full privacy. 41.4K+ GitHub stars. Desktop app for Windows/macOS/Linux, OpenAI-compatible API, MCP support. Apache 2.0.

Three.js is the most popular 3D library for JavaScript — WebGL/WebGPU rendering made accessible. Build 3D scenes, models, shaders, physics, VR/AR, and interactive experiences without touching low-level graphics APIs.

dnd-kit is a lightweight, modular, performant, and accessible drag-and-drop toolkit built for React with hooks, sensors, and collision detection algorithms.

A community-driven open-source AI agent framework that enables building autonomous agents capable of web browsing, coding, file manipulation, and multi-step task completion.

Stanford's LLM-powered system that researches any topic and writes a full Wikipedia-style article with citations. Simulates multi-perspective expert conversations.

Natural language interface that executes Python, JS, and shell commands on your computer. Local-first, model-agnostic. 63K+ stars.

A self-hosted API management and distribution system that aggregates multiple LLM providers behind a single OpenAI-compatible interface with load balancing, rate limiting, and token quota management.

Text Generation WebUI is a Gradio interface for running LLMs locally. 46.4K+ GitHub stars. Multiple backends, vision, training, image gen, OpenAI-compatible API. 100% offline.

LLM-powered video subtitle tool: Whisper transcription + AI correction + 99-language translation + styled subtitle export. 13,800+ stars.

Framework for building stateful, multi-step AI agent workflows as graphs. LangGraph enables cycles, branching, human-in-the-loop, and persistent state for complex agent systems.

Budibase is an open-source low-code platform for building internal tools, admin panels, dashboards, and workflow apps in minutes. Connect any database and deploy instantly.

Chat UI is Hugging Face's open-source web interface for conversational AI, powering HuggingChat and supporting any text-generation model via TGI, Ollama, or OpenAI-compatible APIs with features like web search, tool use, and multimodal input.

Hugging Face's diffusion model library. Run CogVideoX, AnimateDiff, Stable Video Diffusion, and 50+ video/image models with a unified API. 33,200+ stars.

Invidious lets you watch YouTube without ads, tracking, or a Google account. It proxies video content and strips all tracking — a self-hostable frontend for YouTube that respects your privacy.

Debug, test, and monitor LLM applications in production. LangSmith provides trace visualization, prompt playground, dataset evaluation, and regression testing for AI.

The most powerful modular AI image generation GUI with a node/graph editor. Supports Stable Diffusion, Flux, SDXL, ControlNet, and 1000+ custom nodes. 107K+ stars.

WhisperX provides 70x realtime speech recognition with word-level timestamps and speaker diarization. 21K+ GitHub stars. Batched inference, under 8GB VRAM. BSD-2-Clause.

Foam is a free, open-source personal knowledge management tool that runs inside VS Code. Inspired by Roam Research, it uses wikilinks, backlinks, and a graph visualization to help you organize interconnected notes in plain Markdown files.