Agentary

Nexa AI provides a powerful platform for running state-of-the-art AI models directly on any device. Its solutions, including the Nexa SDK for developers and the Hyperlink app for consumers, prioritize privacy, offline reliability, and cost-effectiveness by enabling local AI inference on CPUs, GPUs, and NPUs, eliminating the need for cloud processing.

Screenpipe is an open-source AI SDK that captures your computer's screen and audio 24/7, creating a local, private digital memory. It powers a rich ecosystem of AI agents that can search, summarize, and automate tasks based on your complete digital context, turning your computer usage into a powerful, personalized AI.

AnythingLLM is an open-source, all-in-one AI application that runs locally on your desktop or can be self-hosted. It allows you to create a private knowledge base from any document, chat with your data, and utilize powerful AI agents while ensuring complete data privacy and control.

Anything World is an AI-powered platform that revolutionizes 3D content creation with automated rigging and animation. It provides game-ready SDKs for Unity and Unreal Engine, enabling developers and artists to rapidly generate and control animated 3D models and entire virtual worlds using simple text or voice commands.

Velt is an AI-powered SDK for developers to rapidly integrate rich collaboration features like comments, co-editing, and live presence into any web application. It saves months of development time, boosts user engagement, and allows teams to ship features 5x faster.

Nexa AI provides a powerful platform for running state-of-the-art AI models directly on any device. Its solutions, including the Nexa SDK for developers and the Hyperlink app for consumers, prioritize privacy, offline reliability, and cost-effectiveness by enabling local AI inference on CPUs, GPUs, and NPUs, eliminating the need for cloud processing.

AnythingLLM is an open-source, all-in-one AI application that runs locally on your desktop or can be self-hosted. It allows you to create a private knowledge base from any document, chat with your data, and utilize powerful AI agents while ensuring complete data privacy and control.

Metorial is an integration platform for AI agents, enabling developers to quickly build, deploy, and monitor powerful agentic AI applications. It provides seamless connections to hundreds of tools, data sources, and APIs via its serverless Model Context Protocol (MCP) platform, offering robust SDKs, observability, and enterprise-grade security for scalable AI solutions.

A privacy-focused AI chatbot that runs a large language model (Vicuna-13B) entirely in your browser using WebGPU. No data is sent to a server, ensuring complete confidentiality of your conversations.

Screenpipe is an open-source AI SDK that captures your computer's screen and audio 24/7, creating a local, private digital memory. It powers a rich ecosystem of AI agents that can search, summarize, and automate tasks based on your complete digital context, turning your computer usage into a powerful, personalized AI.

Browser MCP connects AI applications like Claude or Cursor directly to your web browser. This enables you to automate repetitive tasks, conduct end-to-end software testing, and scrape web data using AI commands. It operates locally for maximum speed and privacy, leveraging your existing browser sessions to bypass logins and avoid bot detection.

LocalAI is a free, open-source desktop application that allows you to run AI models privately and offline on your computer. It simplifies AI experimentation without needing a GPU, offering features like model management, integrity verification, and a local inference server.

Novice is a local-first AI assistant that runs powerful language models like Llama 3.2 and Phi directly on your computer. It transforms your documents into a private, offline knowledge base, allowing you to analyze, summarize, and query information with complete data privacy. Every answer is backed by clear citations from your sources, ensuring accuracy and trust.

Ollama is a powerful open-source framework for running large language models (LLMs) like Llama 3, Mistral, and Gemma locally on your own hardware. Available for macOS, Windows, and Linux, it simplifies the setup and management of open-source models, enabling private, offline, and cost-effective AI development and usage.

Arcade is an AI tool-calling platform for developers, enabling AI agents to securely perform actions on behalf of users. It connects AI to services like Gmail, Slack, and APIs through pre-built connectors and a custom SDK, handling complex authentication (OAuth) automatically. This allows developers to build assistants that go beyond chat to execute real-world tasks.

OpenVoiceOS is a community-driven, open-source voice AI platform for creating custom, private, and secure voice-controlled interfaces. It runs on various hardware like Raspberry Pi and Linux desktops, offering a flexible, plugin-based architecture for developers and DIY enthusiasts.

reMind is an open-source, privacy-first AI tool that acts as your personal memory. It captures your digital activity locally, allowing you to search and recall anything you've seen or done on your computer using natural language. It runs entirely on your machine for maximum security.

Perfect Memory AI is a privacy-focused productivity assistant that acts as your second brain. It records your screen activity and meetings, making everything you've seen or heard fully searchable. With a powerful AI assistant, it helps you recall information, summarize research, and prepare for meetings, all while keeping your data securely on your local device.

Offeline is a powerful, privacy-first AI chat application that runs open-source Large Language Models (LLMs) locally on your hardware. It supports both browser and native desktop use, ensuring your data never leaves your machine. Enjoy offline capabilities, web search integration, document analysis, and voice support.