Mac menu-bar OCR: drag over any part of the screen and the text in it lands on your clipboard, from videos, PDFs, images or apps.
Find the AI tool for the job
Search 1237 hand-checked apps, skills and MCP servers — no account needed.
Explore apps
The newest, the most saved, and what everyone is trying right now.
Desktop PDF editor built around ABBYY's AI-based OCR: turn scans into editable Word, Excel or searchable PDF in 198 recognition languages.
Open-source, self-hosted AI gateway and Python SDK: one OpenAI-compatible API for 100+ providers, with spend tracking, budgets and guardrails.
AI gateway and LLMOps platform: one API to 1,600+ models with fallbacks, caching, guardrails, cost tracking and prompt management.
Royalty-free background music and sound effects from text prompts, made with Maestro, a model trained on licensed music that pays artists.
AI 3D model generator with unlimited text- and image-to-3D on paid plans, plus rigging, retexturing and editable templates.
AI 3D model generator from Deemos that turns text prompts or one or more images into textured, near production-ready 3D assets.
AI daily planner that merges all your calendars and task managers, proposes a time-blocked day you approve, and handles booking links.
Gamma is your AI design partner for effortless presentations, websites, social media posts, and more—so you can focus on what you do best.
Ad-supported coding agent suite — CLI, parallel desktop workspaces, cloud IDE and a prompt-to-deploy web builder, with no subscription or API key.
Turn anything into clear, structured knowledge points. Learn them fast and review them at the right time.
Free, local, open-source AI app builder ✨ v0 / lovable / Bolt alternative
Microsoft's AI assistant for chat, images, voice and files, now one app for personal and work accounts on web, desktop and mobile.
Krea AI is a web-based platform offering a suite of AI-powered creative tools.
v0 converts natural language descriptions into code and UI. Build landing pages, full-stack apps, and more.
Create stunning original music in seconds using AI. Make your own masterpieces, share with friends, and discover music from artists worldwide.
Anthropic's agentic coding tool — a terminal-native agent that reads your codebase, edits files, runs tests, and opens PRs.
Anthropic's desktop agent for non-coding knowledge work: point it at a folder, describe the outcome, and it does the multi-step work itself.
Open-source personal AI assistant that runs on your own machine and answers from WhatsApp, Telegram, Slack, iMessage and 25 other chat apps.
Open-source AI workspace you deploy into your own Cloudflare account: agent chat wired to company context, sandboxed app building, and policy guardrails.
The open-source AI hub: over a million models, hundreds of thousands of datasets, and hosted demo Spaces.
OpenAI's video generation model and social app — text, image, or cameo prompts into short, sound-synced clips.
Point your phone at any product label and get a 0-100 score judged against your own allergies, diet and skin — buy it, or skip it.
Cursor's Git forge for the agentic era — host repos, review pull requests and let coding agents work in the same place.
Skills
Reusable skill templates that make your AI assistant better at one job.
Find where a photo was taken: EXIF, OCR, OpenStreetMap, skyline and satellite matching, with coordinates, error radius and evidence images.
AMD's official meta-skill: permanently reroutes an agent's image generation, text-to-speech and speech-to-text to a local Lemonade Server instead of a paid cloud API.
CodeQL, Semgrep and SARIF static-analysis toolkit from Trail of Bits: taint tracking, fast pattern scans and merged, deduplicated security findings for coding agents.
Microsoft's official Playwright skill — drives a real browser from the command line using accessibility snapshots and element refs, and plans, generates and heals Playwright tests.
Google's official Stitch skill for generating and editing UI screens from text or images — with a mandatory prompt-enhancement pipeline before every call.
Google's official agent skill for writing production Maps Platform code — grounded in freshly fetched docs, with a demo key path that needs no billing account.
Railway's official agent skill: create projects, provision databases and buckets, deploy, manage variables and domains, and read build failures back — from the CLI, API or MCP server.
Diagnoses wrong gradients in differentiable NVIDIA Warp programs by measuring first — comparing autodiff against finite differences on a shrunk reproduction before proposing any fix.
MCP servers
Connect your assistant to the tools and data it needs.
The whole Cloudflare API — 2,500+ endpoints — behind two tools. The agent writes JavaScript instead of picking from a tool list, cutting the context cost by about 99.9%.
Google's official MCP server for the Home ecosystem — let an agent list your homes and devices, read live trait state, run actions and query event history over OAuth.
Canva's official remote MCP server — generate and edit designs, search your library, manage assets and brand kits, and export to PDF, PNG, PPTX or MP4.
Query SigNoz metrics, traces, logs, alerts and dashboards in natural language — and create alerts, dashboards and saved views back, with deep links into the UI.
Official MCP server for the Mux video API, built on a code-execution scheme: the agent writes TypeScript against the SDK and runs it in a Deno sandbox.
Red Hat's zero-dependency C++23 code-context engine — ranked call graphs and blast-radius analysis, indexing a repo in under half a second with no server and no database.
Builds a searchable markdown graph of your repo so coding agents stop re-exploring it on every task — reported 42% fewer tokens and 46% fewer tool calls.
Expo's official remote MCP server — searches Expo docs, installs compatible SDK packages, triggers and monitors EAS builds, and drives iOS/Android simulators.