AI Projects & Tools

OpenAI's conversational AI assistant — chat, code, image generation and voice in one product. The best-known consumer AI chatbot, also available through a developer API.

Anthropic's AI assistant known for strong reasoning, long-context understanding and nuanced writing. Available as a consumer chat app, API models and Claude Code for the terminal.

Google's multimodal AI assistant embedded across Search, Gmail, Docs and Android. Runs on Gemini models with a 1M-token context window and strong Google ecosystem integration.

An AI image generator famous for artistic, high-quality results. Create images from text prompts on Discord, web and mobile, with strong style control and upscaling.

AI pair programmer that autocompletes code and answers questions inside your editor. Built on OpenAI models, it learns from your context and is available for every major IDE.

An AI-native code editor forked from VS Code. Chat with your codebase, auto-generate edits across files, and use agent mode to implement features end to end.

An AI answer engine that combines LLM reasoning with real-time web search, citing sources for every claim. A fast alternative to traditional search for research and questions.

AI voice platform with state-of-the-art text-to-speech, voice cloning and dubbing in 70+ languages. Used for audiobooks, videos, games and voice agents.

AI tools for creative workflows — text-to-video, image generation and video editing with models like Gen-3 Alpha. Used by filmmakers and artists for VFX and motion design.

Run large language models locally with one command. A friendly CLI and API for Llama, Mistral, Qwen, Gemma and hundreds of open models on your own machine.

A desktop app to discover, download and run local LLMs through a friendly GUI. Chat with open models, run a local OpenAI-compatible server, or use GPU acceleration.

The open-weights image generation model family from Stability AI. Runs locally with no GPU required for small models, and powers countless apps, extensions and fine-tunes.

A node-based interface for Stable Diffusion and other diffusion models. Powerful graph workflows give you fine-grained control over generation pipelines — from simple prompts to complex multi-stage compositions.

OpenAI's open-source speech recognition model that transcribes audio in 99 languages with near-human accuracy. Runs locally via CLI, Python or the OpenAI API.

The collaboration platform for machine learning — 1M+ models, datasets, Spaces apps and the Transformers library. The home of open-source AI.

A framework for building applications powered by LLMs — chains, agents, tools, memory and retrieval. The most popular toolkit for production LLM apps, with Python and JS versions.

A fast and easy LLM serving engine with PagedAttention for high throughput inference. Serves open models with an OpenAI-compatible API, used widely in production deployments.

A French AI lab offering open-weights models (Mistral 7B, Mixtral) and powerful API models (Mistral Large). Known for efficiency and strong multilingual performance.

The open-source deep learning framework behind most modern AI research and production models. Dynamic computation graphs, GPU acceleration and the torch ecosystem.

Google's end-to-end machine learning platform for building, training and deploying models. Keras API, production serving with TF Serving, and mobile/edge support via Lite.

A self-hosted, feature-rich AI interface for Ollama and OpenAI-compatible APIs. Chat with local models in a polished web UI with RAG, tool calling and multi-user support.

Project management for human + agent teams — an open-source platform that turns coding agents into real teammates. Assign tasks, track progress and compound skills across your agent workforce.

The context file system for AI agents — a self-evolving context database that unifies agent memory, knowledge RAG and skills so agents keep context across sessions.

The runtime coding agents run on — holds real terminals open on your laptop, desktop or a rented box so agent work survives the lid closing, reachable from anything with a keyboard.

The missing design vocabulary for agents — strips the slop from AI-generated interfaces, gives agents precise commands to steer visual work, and iterates design variants live in your product.