MMCPMarkets
LA

lennonkc/ai-tools-map

Developer tools
86 stars 품질 70 트렌드 70
Repository Install

- AutoGen - A multi-agent application framework currently in maintenance mode; new Microsoft projects are directed to Agent Framework.

개요

- AutoGen - A multi-agent application framework currently in maintenance mode; new Microsoft projects are directed to Agent Framework.

README

AI ToolMap ✨ [2026-08-17]

Agents

Agent Frameworks

Workflow Agents

MCP

Agent Interoperability Protocols

Skills

Knowledge

GUI Agents

  • Browser Operator

    • open-source
    • source-available
      • Suna
        • Source-available AI management system with browser automation, file management, crawling, and API integrations; licensed under Elastic License 2.0.
      • Agent QA
        • Source-available QA harness for natural-language web and mobile tests, with MCP integration, execution memory, and self-healing flows; FSL 1.1 with an Apache-2.0 future grant after two years.
    • 3rd
    • AI Browser
      • Dia
        • An AI-focused browser that organizes work context across tabs, meetings, documents, and connected tools.
      • Fellou
        • An agentic browser for multi-step research and cross-application workflows.

  • Computer Operator

    • 3rd
    • open-source
      • autoMate
        • Circle a region on the screen and let the AI operate within that area.
      • UFO³
        • Microsoft’s open-source Windows desktop automation framework for multi-application tasks.

  • Computer Vision

    • open-source
      • OmniParser
        • Parses UI screenshots into structured elements for vision-based computer-use agents.
      • Supervision
        • Reusable computer-vision utilities for datasets, detections, annotations, and video processing.
    • source-available
      • screenpipe
        • Local screen and audio capture with OCR/transcription indexing for agent context and memory.

  • Use Cases

    • Non-API tasks
      • Platforms that do not provide suitable APIs
      • Cases where API data is incomplete or inaccurate
      • Reasons
        • Cost
          • APIs are often developed and maintained separately from a product’s core interface, increasing implementation cost.
        • Complexity
          • Public APIs may not expose every operation or data field available in the product UI.
    • Highly repetitive tasks

Good Examples

Tools

Deep Research

Workflow Builder

  • open-source
    • Langflow
      • A visual framework for building and deploying AI agents and workflows.
    • iii
      • An event-driven runtime for composing services and workflows from reusable workers.
    • Tars
    • Activepieces
    • bisheng
  • source-available / fair-code
    • n8n
      • Workflow automation platform with extensive app integrations and AI workflow support.
    • Dify
      • Platform for building and operating LLM applications and agentic workflows.
  • 3rd

Media

  • News Center

    • Folo
      • An information aggregator that combines articles, videos, and updates from followed sources into one timeline.
    • meridian
      • Collects and analyzes news from many sources to produce personalized daily briefings.
    • NewsNow
    • LingoWhale
      • Tracks information sources and generates AI summaries.

  • Writing

  • Voice & Video & Images

    • TTS
      • MiniMax Audio
      • Dia
        • Multi-speaker dialogue generation with non-verbal expressions such as laughter, sighing, and coughing.
      • Spark-TTS
        • Open-source text-to-speech system for controllable, natural speech generation.
    • Video
      • Veo 3 ⭐
        • Video generation with native dialogue, sound effects, and ambient audio.
      • HunyuanVideo
        • A systematic framework for a large video-generation model.
      • FramePack
        • Image- and prompt-driven video diffusion designed to run on supported consumer NVIDIA hardware.
      • KrillinAI
        • Video subtitle generation, translation, and automatic dubbing.
      • Deep-Live-Cam
        • Real-time face swapping for video streams.
      • MoneyPrinterTurbo
        • Automates short-video creation from scripts, stock media, voice-over, and subtitles.
      • Video to Text
        • BiliNote
          • Converts supported video content into structured notes.
        • Video2Blog
          • YouTube video to text.
      • Video download
        • datatool.vip
        • cobalt
          • Web interface and API for saving openly accessible media from supported services.
        • yt-dlp
          • Command-line downloader supporting thousands of media sites.
    • Images
      • Nano Banana ⭐
        • Image generation and editing that combines visual synthesis with model reasoning.
      • Midjourney V7 ⭐
        • Strong lighting, artistic composition, and style consistency.
      • FLUX
        • Black Forest Labs image-generation and editing model family with open-weight and API-delivered variants.
      • Stable Diffusion, LoRA, ControlNet
        • Ecosystem for custom characters, styles, and precise pose or composition control.
      • ComfyUI
        • Node-based interface and execution engine for generative AI workflows.

  • Podcast

    • Podcastfy
      • Open-source Python tool that transforms multimodal content into multilingual AI-generated audio conversations.

  • WeChat

    • chatlog
    • WeClone
      • Fine-tunes conversational models from exported chat history to reproduce a personal writing style.

Coding

Vibe Coding ⭐

Docs

  • helpful tools to read GitHub repositories
  • DevDocs
    • API documentation browser with centralized search and offline access.
  • awesome-selfhosted ⭐
    • A curated collection of free and open-source software products.

Design & Front-end

  • A2UI
    • Open standard and libraries for agent-generated declarative UI.
  • OpenUI
    • Conversational interface for building front-end UI.
  • Onlook
    • Open-source, AI-first visual builder and editor for React.
  • GrapesJS
    • Open-source web builder framework with drag-and-drop editing.
  • Galileo AI
  • Anime.js
    • JavaScript animation engine for the web.
  • Akaza UI
    • Unstyled, accessible headless UI components for Vue 3.
  • Logo Design
  • Desktop & mobile app
    • Tauri
      • Framework for building small, fast desktop and mobile applications with a web front end.
    • PakePlus
      • Packages websites as desktop and mobile applications.
  • Git
    • GitMCP
      • Converts a GitHub repository into an MCP endpoint for documentation and code retrieval.

Back-end

  • servers
    • ctop
      • Command-line monitoring interface for containers.
    • kubectl-ai
      • Uses natural-language instructions to help operate Kubernetes clusters.
    • Nginx Proxy Manager
      • Web interface for managing Nginx proxy hosts and certificates.
    • JumpServer
      • Open-source privileged access management platform.
  • database / app platform
  • developer tools
    • public-apis
      • Collaborative collection of public APIs.
    • Meilisearch
      • Application-focused search engine with typo tolerance and fast search-as-you-type.
    • Bruno
      • Open-source API client and testing tool.
  • Caddy
  • Gatsby
  • Strapi
    • Open-source headless CMS for customizable content APIs and administration.
  • SQLPage
    • Builds data-driven websites directly from SQL queries.

Network

  • NPS
    • Intranet proxy supporting TCP, UDP, HTTP(S), SOCKS5, and related protocols.

Data

  • Scraping
  • AI Conversational Database
  • BI / Database Management
    • open-source
      • Metabase ⭐
        • Approachable business intelligence with AI-assisted querying and visualization.
      • DataEase
        • Chinese-friendly BI platform with AI integrations.
      • Wren AI
        • Semantic layer and text-to-SQL engine for embedded conversational analytics.
      • DBeaver
        • Cross-platform database client.
      • Prisma
        • Type-safe ORM and database toolkit for TypeScript.
      • Apache Superset
        • Open-source data exploration and visualization platform.
      • Teable
        • PostgreSQL-based business data platform with spreadsheet-style collaboration and automation.
  • Files and OCR
    • LangExtract
      • Extracts structured information from unstructured text with source grounding.
    • Docs
      • ConvertX ⭐
        • Self-hosted file conversion service.
      • PPT
        • MultiAgentPPT
          • Uses multiple conversational agents to generate presentations.
      • PDF
        • BabelDOC
          • Translates PDFs while preserving layout.
        • no-ocr
          • Processes PDF pages without OCR and supports visual question answering over charts and images.
        • Docling
          • Document parsing and conversion with PDF/Office support, OCR, layout, and table processing for AI and RAG content.
        • MinerU
          • Converts complex PDFs into structured Markdown and JSON for downstream AI workflows.
    • OCR
  • Finance / Quantitative Trading
    • ai_quant_trade
    • QUANTAXIS
      • Quantitative research and trading framework with task scheduling and distributed deployment.
    • Backtrader
      • Python backtesting and trading framework.
    • Qlib
      • AI-oriented quantitative investment platform for research and production.
    • FinGenius
      • Multi-agent financial research and investment analysis.
    • OpenBB ⭐
      • Open financial-data platform for analysts, quantitative research, and AI agents.
    • TradingAgents-CN
      • Chinese-enhanced multi-agent LLM financial trading framework.

RAG & Knowledge Management

  • Google NotebookLM ⭐
  • Open Notebook
    • Self-hosted research and knowledge-management tool with source ingestion, retrieval, citations, and configurable AI models.
  • Second Me
  • SurfSense
    • Self-hostable research assistant that aggregates personal and team sources into a searchable knowledge base.
  • RAGFlow
    • Open-source RAG engine combining document understanding, retrieval, and agent workflows.

What’s More Than Text

  • Mermaid
    • Text-based diagrams, charts, flowcharts, and sequence diagrams.
  • Markmap
    • Markdown to mind map.
  • Vega
    • Declarative grammar for interactive visualizations.
  • Slidev
    • Markdown-based presentation framework for developers.
  • GPT-Vis
    • Framework-agnostic, AI-native visualization library for LLM applications.
  • Next AI Draw.io
    • Creates and edits draw.io diagrams through natural language.
  • D2
    • Declarative diagram scripting language with automatic layout.

Knowledge

Learning Path

View this README on GitHub

추천 도구

다른 키워드를 입력하거나 필터를 제거해 보세요.

설치

npx skillfish add lennonkc/ai-tools-map