Open directory of products, games, agents, MCP servers, and apps built with AI. Submitted by makers, screenshotted automatically, indexed for humans and language models.

Collaboration platform for prompt engineering, evaluation, and deployment of LLM features.

Open-source, Rust-based vector database optimised for high-recall similarity search.

Free playground for the Gemini API with multimodal prompting, function calling, and JSON mode.

Dashboard for the Anthropic API — prompt workbench, model selection, and usage analytics.

Hub for ML models, datasets, and demos — the GitHub of open-source machine learning.

TypeScript toolkit for building AI apps with streaming, tools, and provider-agnostic interfaces.

Podcast post-production with AI — transcripts, show notes, SEO titles, and social clips.

Khan Academy's AI tutor — guided learning across math, writing, and science for students.

Hand-drawn-style whiteboard with AI-generated diagrams from text prompts.

Voice cloning platform with real-time speech-to-speech, deepfake detection, and enterprise security controls.

Auto-captions, B-roll, sound effects, and emoji animations for short-form social videos.

Loom's AI layer adds auto-titles, summaries, chaptered timestamps, and filler-word removal to screen recordings.

Royalty-free AI music streams and stem generation aimed at creators, livestreams, and ambient soundscapes.

Voice cloning and text-to-speech with naturalistic delivery in 30+ languages; powers many AI audio apps.

Photo-to-speaking-avatar generator — drop a photo and a script, get a talking-head video out.

Visual automation platform with AI modules for OpenAI, Anthropic, and self-hosted LLMs.

Automation platform connecting 6,000+ apps, now with built-in AI actions and an agent builder.

Turns scripts, articles, and webinars into shareable short videos with AI voiceover and visual selection.

OpenAI's text-to-video model with extended clip length and storyboarding tools, accessed via the Sora web app.

Generative video model with a chat-style interface and strong character consistency across shots.

AI video studio with text-to-video, video-to-video, motion brush, and a timeline-based editor for filmmakers.

Figma's built-in AI for layer naming, prototyping, asset generation, and design suggestions.

Infinite whiteboard with experimental AI features that turn sketches into working apps.

AI fields and assistants inside Airtable bases for categorization, summarisation, and translation.

Stem separation service that extracts vocals, drums, bass, and instruments from any audio file.

Noise-cancellation and meeting-transcript AI that runs on top of any video call.

AI podcast studio — generate hosts, voices, music beds, and full episodes from a brief.

Fireflies.ai's extension that joins meeting tabs and records, transcribes, and summarises calls.

Microsoft's consumer AI assistant — Copilot in Windows, Edge sidebar, and across Microsoft 365.

All-in-one AI assistant browser extension — chat, summarise, rewrite, translate, and answer on any site.

Asana's AI layer for status updates, smart goals, and risk detection across projects.

AI agent for productivity that turns chat into multi-step browser and app actions.

AI-native email client with agents that answer questions across your inbox and write replies in your voice.

Calendar + task manager that uses AI to re-plan your day around new commitments and deadlines.

Self-organising notes app with AI search, summarisation, and auto-linking between related thoughts.

Meeting transcription and AI summaries — joins Zoom, Google Meet, and Teams to capture and summarise calls.

Ideogram's freeform editing surface with infinite zoom, layered text generation, and selective edits.

Single-click background removal API and web tool that defined the category, by Kaleido AI.

Long-running web UI for Stable Diffusion, the original community-favourite local image-gen interface.

Real-time image and video generation with a live canvas, AI upscaling, and motion presets.

Open-weights diffusion model family by Black Forest Labs with photorealistic outputs and strong text rendering.

Open-weights text-to-image model by Stability AI, runnable locally on consumer GPUs and via dozens of third-party UIs.

Open-source desktop AI chat client that supports OpenAI, Anthropic, Gemini, and local models via Ollama.

Local LLM runner — pull and run Llama, Qwen, Mistral, DeepSeek, and other open models with one command.

Make websites accessible to AI agents — Python library that wraps Playwright into LLM-friendly actions.

Web-based autonomous agent — give it a goal, watch it self-plan and execute with web browsing and code.

voice to text and second brain

Autonomous general agent that browses the web, runs code, and ships deliverables on long-horizon tasks.

Personalised AI companion with long-term memory, voice calls, and customizable persona.

Web-based autonomous agent UI — give it a goal, approve each step or let it run unattended.

Google's multimodal AI assistant — text, image, audio, and video reasoning across Google Workspace.

Open-source framework for orchestrating role-playing multi-agent teams in Python.

OpenAI's agent mode (formerly Operator) — runs in a managed browser to complete multi-step web tasks.

DeepSeek's web chat for DeepSeek-V3 and reasoning models, with open-weights releases.

Rabbit's AI operating system and r1 device with the Large Action Model that learns to use apps.

AI search and chat with a focus on agentic research workflows and citation-backed answers.

xAI's chatbot integrated into X with realtime knowledge, image generation, and an irreverent persona.

Lightweight Python framework for building agents with memory, knowledge, and tool-use, formerly Phidata.

Hugging Face's minimal library for code-writing agents — agents respond in Python, not JSON.

Mac command bar with built-in AI — chat, write, translate, and run scripts from any app.