Terminal-based AI coding assistant with native UI, LSP support, shareable session links, multi-model integration, multi-session management, and open source licensing.

Terminal-based AI coding assistant with native UI, LSP support, shareable session links, multi-model integration, multi-session management, and open source licensing.

A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.




Customizable client for chatting with local private models, open source AIs, and remote LLMs via OpenRouter or custom backend, enabling private, secure AI access.





Empowering LLM researchers and hobbyists with seamless control over self-hosted models. Connect remotely, customize prompts, manage chats, and fine-tune configurations. All in one intuitive app.




JetBrains Air is the Agentic Development Environment where Codex, Claude Agent, Gemini CLI, and Junie execute independent task loops without interfering with each other.




Chat with AI models, generate images, convert books into audiobooks, and run text-to-speech – all locally on your device. No cloud. No compromises.




Mocolamma is an Ollama management application for macOS and iOS / iPadOS that connects to Ollama servers to manage models and perform chat tests using models stored on the Ollama server.




The Assistant by Kagi combines the top large language models (LLMs) with optional results from Kagi Search, making it the perfect companion for creative, research, and programming tasks.




Have a truly private AI conversation with powerful models and compare results. Brainstorm, create, and analyze without compromising your data.




Mine StableDiffusion is a native, offline-first AI art generation app that brings the power of Stable Diffusion models to your fingertips. Built with modern Kotlin Multiplatform technology and powered by the blazing-fast stable-diffusion.




Free, local, open-source GUI app, Cowork for Gemini CLI, Claude Code, Codex, Qwen Code, Goose Cli, Auggie, and more — Enhanced Chat UI, WebUI, Multi-Agent & Multi-LLM, MCP Integration.




AI edge infrastructure for macOS. Run local or cloud models, share tools across apps via MCP, and power AI workflows with a native, always-on runtime.

Run multiple Claude Codes as individual agents in parallel, each with an isolated workspace, supporting code reviews, agent status tracking, and local repository cloning.

1-bit Bonsai 8B implements a proprietary 1-bit model design across the entire network: embeddings, attention layers, MLP layers, and the LM head are all 1-bit. There are no higher-precision escape hatches. It is a true 1-bit model, end to end, across 8.2 billion parameters.





Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack.

Alice is a smart desktop AI assistant application built with Vue.js, Vite, and Electron. Advanced memory system, function calling, MCP support, optional fully local use, and more.

An AI API platform offering 200+ AI models with a single and secure API endpoint, enabling developers and businesses to integrate all major AI models into applications and existing systems/.

Test AI models yourself, privately, with a standardized benchmark, and get both technical scores AND practical recommendations.

Unified AI chatbot interface for accessing multiple leading models, uploading personal docs, running in-depth searches, ensuring privacy, and pay-as-you-go usage.


Onyx (formerly Danswer) is the AI platform connected to your company's docs, apps, and people. Onyx provides a feature rich Chat interface and plugs into any LLM of your choice. Keep knowledge and access controls sync-ed across over 40 connectors like Google Drive, Slack...
Find Your Brand in AI - Track your brand visibility across all major AI models. Monitor mentions, analyze responses, and stay ahead in the AI-driven world.




sllm provides access to a range of large language models at the cheapest possible price, in the most configurably relevant way, all securely and privately hosted on dedicated GPU infrastructure. No markup beyond cost. No tracking. Just the models you need.

PipesHub is the workplace AI platform for enterprises to improve how businesses operate and help employees and AI agents work more efficiently. In most companies, important work data is spread across multiple apps like Google Workspace, Microsoft 365, Slack, Jira, Confluence...
