3.9k+ AI tools. Sorted by what actually ships.
Built something? Get it in front of builders.
List your tool for free, or promote it to the top of the directory.
ModelHub is a native macOS menu-bar app that brings all your local LLMs into one place. Discover, download, and manage models from HuggingFace, LM Studio, Ollama, MLX, and llama.cpp without leaving your menu bar. Downloads land in the standard HuggingFace cache with the official layout, so models fetched through ModelHub are byte-identical to ones fetched with huggingface-cli.
ModelRed is an AI security and red teaming platform that helps organizations identify vulnerabilities in LLMs, agents, RAG pipelines, and custom AI systems. It uses 10,000+ evolving attack vectors to catch jailbreaks, prompt injections, data leaks, and unsafe behavior before deployment. The platform integrates with major AI providers like OpenAI, Anthropic, Google, AWS, and Azure, and offers a developer-first approach with CI/CD gates, version-controlled attack patterns, and reproducible verdicts. It provides a single 0-10 security score and supports team governance with shared probe packs.
Vidix is a macOS app that uses AI to automate tasks and enhance productivity. Select text in any app, press a shortcut, and get AI-generated responses without copy-pasting or context switching. Features include a workflow canvas, palette for quick actions, copy editor, image assistant, and support for multiple AI providers like OpenAI, Anthropic, Gemini, and Ollama. Privacy-focused with local processing and no third-party storage.
Morph is a Python framework and hosting platform for building and deploying AI-powered data apps with code. It provides built-in authentication, data connectors (BigQuery, Snowflake, PostgreSQL, Salesforce, Intercom, Linear), CI/CD, RBAC, and a secure deployment environment. Users can create interactive dashboards and AI workflows using Python, Markdown, and React components, then share them via URL with team access controls.
Perfect Memory AI is a personalized productivity assistant that runs in the background on your PC, using OCR to read your screen and transcribe meetings. It creates a searchable memory of everything you've seen, said, or heard, allowing you to search across all applications, get standup summaries, and prepare for meetings. All data stays encrypted on your device.
.png){kind=small}
Thunder Compute provides one-click GPU servers at 80% less cost than AWS. Developers can spin up dedicated cloud GPUs (RTX A6000, A100, H100) in seconds directly from VS Code, CLI, or web console. Features include expandable disk, customizable vCPUs and RAM, 7-10 Gbps networking, and pre-built templates for AI workflows like Comfy UI and Ollama. Pricing starts at $0.35/GPU/hr for RTX A6000, $0.78/GPU/hr for A100, and $1.38/GPU/hr for H100.
Cline is an autonomous coding agent that operates directly within your IDE (VS Code). It can create and edit files, execute terminal commands, use a headless browser, and extend its capabilities via the Model Context Protocol (MCP). All actions require user permission, providing a safe human-in-the-loop experience. It supports multiple AI models including Claude, GPT, Gemini, and local models via Ollama/LM Studio.
RLAMA is a complete AI platform for creating RAG systems and intelligent agents. It allows users to build, deploy, and manage AI-powered solutions with local models, from document Q&A to autonomous agent crews. The platform supports multiple document formats, advanced semantic chunking, and local processing for privacy. It also enables the creation of specialized AI agents and multi-agent crews for complex automation tasks.
The best AI tools in your inbox. 7am. Free.
Local Deep Researcher is a fully local web research assistant that uses any LLM hosted by Ollama or LMStudio. Given a topic, it generates a web search query, gathers results, summarizes findings, reflects on knowledge gaps, and repeats for a configurable number of cycles. It outputs a final markdown summary with citations. The tool runs entirely locally, ensuring privacy and no API costs.
Bolt.diy is the official open source version of Bolt.new, allowing users to prompt, run, edit, and deploy full-stack web applications using any LLM they choose. It supports 19+ AI providers including OpenAI, Anthropic, Ollama, OpenRouter, Gemini, LMStudio, Mistral, xAI, HuggingFace, DeepSeek, Groq, Cohere, Together, Perplexity, Moonshot, Hyperbolic, GitHub Models, and Amazon Bedrock. Features include AI-powered full-stack development, image attachment, integrated terminal, code revert, ZIP download, Docker support, direct deployment to Netlify/Vercel/GitHub Pages, Electron desktop app, data visualization, Git integration, MCP support, search, file locking, diff view, Supabase integration, and Expo app creation. It is community-driven and extensible via the Vercel AI SDK.
PhxTemplates offers visually-stunning, easy-to-customize Elixir Phoenix website templates and boilerplates built with Stripe, OpenAI, EmailJS, Mailgun, and more. Each template is a well-structured Phoenix project optimized for performance, SEO, and quick deployment. Templates include SaaS-ready features like payment integration, email sending, admin dashboards, and AI capabilities. The collection includes portfolio, blog, and SaaS templates, as well as a featured project 'Chat Buddy MCP'—an AI-powered database interface with natural language SQL and GPU support.
Alex is an AI-powered coding assistant for Xcode that helps iOS and Swift developers automate project builds, fix bugs, add Swift packages, run apps in Simulator, and more. It features autocomplete, inline code replacements, chat with selected code, image-to-code generation, codebase search, web search, and terminal command execution. Alex prioritizes privacy by running local models and not relaying code through its servers.