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

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

Image generation suite with fine-tuned game-asset, illustration, and photography models.

AI image generator built for designers — vector output, brand consistency, and style transfer in one app.

Text-to-image platform specialised in typography — generates legible text inside images better than most peers.

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.

OpenAI's text-to-image model with strong prompt adherence, available via ChatGPT and the OpenAI API.

Text-to-image generation service known for stylised, painterly outputs; accessed through Discord and a web app.

Multi-model chat front-end aggregating GPT, Claude, Gemini, and custom agents under one subscription.

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

Power-user chat client for GPT, Claude, and Gemini with prompts library, plugins, and conversation forking.

Desktop AI chat app that connects to Ollama, OpenAI, Anthropic, and any custom endpoint with one interface.

Desktop app to discover, download, and run local LLMs with a polished chat UI and OpenAI-compatible server.

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

Self-hostable web UI for Ollama and OpenAI-compatible endpoints — feels like ChatGPT, runs on your own server.

Privacy-focused chat front-end for GPT, Claude, Llama, and Mixtral with no logged identity.

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

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

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

Mistral AI's conversational interface for its Mistral and Codestral model families.

Hugging Face's free chat interface for open-weights models like Llama, Mixtral, and Qwen.

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

AI companion app for one-on-one chat, memory-aware relationships, and roleplay.

Inflection's empathetic AI companion focused on conversational support and warmth over task completion.

AI search engine tuned for developers — citation-rich answers, code blocks, and IDE integrations.

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

Quora's multi-model AI platform — switch between Claude, GPT, Gemini, and dozens of niche bots in one chat.

Roleplay platform for chatting with millions of user-created AI characters and personas.

AI answer engine that combines web search with LLM reasoning and inline source citations.

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

Anthropic's AI assistant with the Claude family of models (Opus, Sonnet, Haiku), Projects, and Computer Use.

OpenAI's flagship AI assistant — GPT-5 chat with web, voice, image generation, code interpreter, and custom GPTs.

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

AI assistants for teams with built-in knowledge connectors to Notion, Slack, Drive, and GitHub.

Research lab building reasoning agents for code and operations, with API access to its proprietary models.

LLM-powered browser automation that handles forms, captchas, and multi-page flows reliably.

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

Web-action agent API and Chrome extension that completes tasks like booking, shopping, and research.

Browserbase's library for building reliable AI agents on top of Playwright with structured actions.

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

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

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

Microsoft's framework for building agentic systems with conversable, customizable agent personas.

LangChain's graph-based framework for building stateful multi-agent applications.

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

Minimal task-driven autonomous agent in ~100 lines of Python — a foundational reference implementation.

Original autonomous-agent project that popularised the loop of plan, act, observe, reflect.

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

Platform to build, deploy, and manage AI agents and AI teams without writing code.

No-code AI employees that handle email, scheduling, lead routing, and customer support workflows.

Anthropic's API capability that lets Claude take screenshots, move the cursor, and use a real computer.

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

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

Code-search and AI assistant by Sourcegraph — semantic search across enterprise codebases plus inline coding help.

AI code-review bot that posts inline review comments on every pull request across GitHub, GitLab, and Bitbucket.

Browser-based IDE powered by WebContainers — runs full Node.js stacks instantly in a browser tab.

Visual builder for Flutter apps with AI assistance, code export, and Firebase/Supabase integrations.

Visual no-code platform for web and mobile apps with workflows, DB, and an AI assistant for app generation.

Replit's autonomous build agent that creates, debugs, and deploys apps inside the Replit workspace.

Vercel's AI app builder optimised for Next.js, shadcn/ui, and Vercel deployment.