Repository History
4 repositories tagged with ai-assistant
Mercury Agent: A Soul-Driven AI with Hardened Permissions and Multi-Channel Access
Mercury Agent is a sophisticated, soul-driven AI agent designed for continuous 24/7 operation, offering robust permission-hardened tools, intelligent token budgeting, and versatile multi-channel access. It remembers what matters, asks for permission before acting, and runs seamlessly from the CLI, Telegram, or a web dashboard. With 31 built-in tools, Kanban boards, and a SQLite-backed Second Brain memory, Mercury provides a comprehensive and secure AI assistant experience.
Ruflo: The Agent Meta-Harness for Intelligent AI Swarms
Ruflo, formerly Claude Flow, is an advanced agent meta-harness designed to deploy intelligent multi-player swarms and coordinate autonomous AI workflows. It enhances AI models like Claude Code and Codex with adaptive memory, self-learning intelligence, RAG integration, and robust enterprise security features. This powerful framework enables agents to self-organize, learn from tasks, and securely collaborate across different machines.
Page Assist: Integrate Local AI Models Directly into Your Web Browser
Page Assist is an open-source browser extension that integrates your local AI models directly into your web browsing experience. It provides a sidebar and a dedicated web UI, allowing users to interact with their AI model, including chatting with the content of any webpage. This tool supports various Chromium-based browsers and Firefox, emphasizing privacy by keeping all data local.
DeepChat: A Powerful Open-Source Multi-Model AI Chat Platform
DeepChat is a robust, open-source AI chat platform designed to provide a unified interface for interacting with various large language models, both cloud-based and local. It offers advanced features like search augmentation, tool calling, and multimodal conversations, making AI capabilities more accessible and efficient across Windows, macOS, and Linux. This platform simplifies the management and use of diverse AI models within a single, privacy-focused application.