Privacy-first AI 5
Open-source browser AI components for private, offline applications
LocalMode UI is an open-source, MIT-licensed toolkit and shadcn-style registry for building privacy-first AI interfaces that run entirely in the browser. It provides more than 100 copy-owned React components and 36 installable blocks for chat, RAG, vector search, vision, audio, agents, privacy, and developer tools. Models run locally through WebGPU or a WebAssembly fallback, so applications can work without servers or API keys and keep user data on the device.
A privacy-first, sustainable British AI assistant powered by the Locai L1 model.
GB1 is a private, planet-friendly AI assistant developed in the UK by Locai Labs. Built as a sovereign alternative to big tech AI, it runs on 100% renewable UK energy and is powered by the Locai L1 Large foundational model. It prioritizes user privacy by never training on user chats, ensuring end-to-end encryption, and maintaining all data residency within the UK. The platform allows users to create Spaces for projects, interact via web or mobile, and participate in a democratic roadmap where the community votes on future features.
AI browser extension for intelligent automation, free, open source, no migration.
AIPex is a powerful AI browser extension designed to transform your existing browser into an AI browser, offering a free and open-source alternative to tools like ChatGPT Atlas. It eliminates the need for browser migration, allowing users to add AI capabilities in seconds using natural language commands. AIPex provides intelligent browser assistance with advanced AI features, complete privacy protection, and empowers users with AI-powered browser automation for various tasks.
Sovereign AI foundry for running private, autonomous AI agent teams on your own devices.
Karma AI Factory is a sovereign AI foundry that allows users to turn their personal devices into a private compute pool to run hundreds of autonomous AI agents. Unlike traditional chatbots, KarmaBox orchestrates an entire 'AI Superbrain' that can handle complex workflows, research, and automation in parallel. It supports various models including Claude, Gemini, and local LLMs like Llama and Qwen, ensuring full data sovereignty by processing information on the user's own device without cloud lock-in. It is designed for 'super-individuals' looking for infinite leverage through persistent, private, and agentic AI.
Open-source LLM router for OpenClaw that optimizes model routing to save up to 70% costs.
Manifest is an open-source LLM (Large Language Model) router specifically built for OpenClaw. It optimizes AI expenditures by intercepting queries and routing them to the most cost-effective model based on the complexity of the task, potentially saving users up to 70% on token costs. The system analyzes queries locally in less than 2ms to ensure minimal latency. It prioritizes privacy by performing query scoring on the user's machine and using a blind proxy architecture for its cloud version. Additionally, it allows users to track costs, set usage limits, and export data using the OpenTelemetry standard.
