ChatGPT
Frontier cloud assistant: chat, documents, coding and agents. Free tier plus paid plans and API.
Visit site ↗AI Tools Directory
11 AI tools and services — filter by category, platform, price and whether they run locally or in the cloud. Not sure where to start? Use one of the finders below.
Finders
Task Finder
Pick a task — text to image, text to video, speech to text — and get matching tools.
Model Finder
Filter open models by type, size and license.
VRAM Calculator
Estimate the VRAM a model needs at a given quantization and context length.
Runner Picker
Choose the right LLM runner for your OS and experience level.
AI Stack Builder
Pick VRAM, OS and use case — get a recommended GPU, model and app.
Local vs Cloud
Estimate when your own hardware beats API costs.
All tools
11 of 11 tools
ComfyUI
Node-based local image generation: SDXL, Flux, LoRAs and the largest workflow ecosystem in AI art.
Visit site ↗Cursor
AI-native code editor with agent mode and codebase awareness. Cloud models or local via Ollama.
Visit site ↗LlamaIndex
The Python framework for RAG: load documents, chunk, embed, retrieve and generate — with local model support.
Visit site ↗LM Studio
Desktop app for local LLMs with model browser, chat UI and a local server. Best for non-developers and Mac users.
Visit site ↗Midjourney
Cloud-only image generation with the best-in-class aesthetic quality. Subscription, no API.
Visit site ↗Ollama
Run local LLMs with one command; local OpenAI-compatible API for chat, RAG and coding assistance.
Visit site ↗OpenAI Whisper
Open-source speech-to-text: near-frontier transcription accuracy, runs fully locally on a CPU or GPU.
Visit site ↗Piper
Fast, lightweight local text-to-speech: runs on a Raspberry Pi, ideal for offline voice output.
Visit site ↗Runway
Cloud video generation: text-to-video and image-to-video with an editing suite. The accessible entry point to AI video.
Visit site ↗Stable Diffusion WebUI (Automatic1111)
The classic local SD interface: familiar UI, massive extension library, quick to set up for SDXL.
Visit site ↗