Loading...
Loading...
Foundry Local: Run AI models locally on your device. It is listed under Development & Code on AI Registry as a free tool.
The tools below are approved listings in the same category, ordered by how closely their tags match Foundry Local. This is an automatic list. We have not written a researched verdict for Foundry Local yet, so treat it as a shortlist and check each vendor's pricing page before switching.
Built from each tool's listing. Vendors can update their own listing after claiming it.
GammaCV is a WebGL accelerated Computer Vision library for browser
GammaCV is a computer vision library for the browser, accelerated with WebGL so that image processing and feature extraction run on the GPU rather than the CPU. It follows a data flow paradigm similar to TensorFlow, where operations are assembled into a graph that is then compiled and run, which lets a developer chain ...
Go AI SDK, the Go way.
GoAI is an open source Go SDK for building AI applications, in the spirit of the TypeScript AI SDK but written for Go. It offers one unified API over more than 25 model providers, including OpenAI, Anthropic, Google Gemini, AWS Bedrock, Azure, Vertex, Mistral, xAI, Groq, Cohere, DeepSeek, Ollama and OpenRouter, so you ...
NativeMind: Your fully private, open-source, on-device AI assistant
NativeMind is a browser extension that puts an AI assistant inside the browser while keeping every prompt on the user's own machine. It connects to local models served through Ollama, including gpt oss, DeepSeek, Qwen, Llama, Gemma and Mistral, and the vendor states that no data, prompts or page content are sent to clo...
AI video generation SDK — JSX for videos.
The varg SDK is a TypeScript toolkit for rendering video declaratively, aimed at AI agents. The developer, or an agent such as Claude Code, writes JSX that describes what the video should contain, using components like Clip, Image and Speech, and the SDK renders an MP4. Despite the JSX syntax it does not depend on Reac...
Run a 105 GB AI model on a Mac that can't hold it.
Slotstream is an open source inference engine for running a very large language model on a Mac with limited memory. According to the vendor, it runs a 105 GB model on Macs with 16 to 64 GB of memory by loading parts of the model from the SSD as needed. It is written in native Swift on Apple's MLX and Metal and is tuned...
10x - Up to 20x faster AI coding with multi-step Superpowers.
10x is a terminal based AI coding agent that reads a whole codebase to plan, generate and verify code changes. It runs in the shell rather than as an IDE plugin, with full file system access for reading, writing and editing files, glob and grep search, and the ability to run commands, scripts and build tools while show...