melandlabs/openloomi

OpenLoomi is an open-source AI coworker. It connects your work tools, understands what you’re working on, and tells you what needs your attention, why it matters, and what to do next. It’s your open-source Attention Agent.

What it solves

OpenLoomi addresses the problem of fragmented work context across multiple applications. It prevents users from dropping commitments and losing track of decisions by acting as an "attention agent" that surfaces only the most critical actions and reminders, reducing the need to manually dig through various communication and documentation tools.

How it works

It operates as an always-on desktop companion that monitors your screen and connects to various platforms via connectors. It builds a holistic context graph using short, mid, and long-term memory to track people, projects, and decisions. The system can proactively surface reminders (like morning to-dos or evening recaps) as small bubbles on the desktop and integrates with messaging apps (Telegram, WhatsApp, iMessage, etc.) to provide AI assistance directly within chats. It is designed to be local-first with AES-256 encryption for privacy.

Who it’s for

It is designed for professionals and developers who use a wide array of tools and want a centralized AI coworker to manage their work state and context. It is also suitable for users of other agent frameworks (such as Claude Code, Codex, or Hermes) who want to add a shared layer of memory and proactive attention management to their existing agents.

Highlights

  • Attention Agent: A resident desktop companion that surfaces pre-decided reminders and daily digests without interrupting focus.
  • Holistic Context Memory: An evolving memory system that tracks work history and decisions across months and multiple tools.
  • Platform Connectors: Background sync loops that pull data from commits, issues, emails, and docs, plus direct integration with messaging apps.
  • Agent Neutrality: Can be used as a standalone app or plugged into other agent runtimes as a set of skills and plugins.
  • Local-First Security: Features local storage and AES-256 encryption to ensure data does not leave the machine.

Related

  • Project
    beilusaiying/always-accompany

    A multi-purpose AI agent framework focused on context and attention mechanisms, providing layered memory and dynamic retrieval for long-term companionship, coding, and work.

  • Project
    MemTensor/memmy-agent

    A personal memory infrastructure that allows different AI agents to share a structured memory of user preferences and project history, ensuring task continuity across tools.

  • Project
    netease-youdao/LobsterAI

    A desktop AI agent that automates office workflows by interacting with local files, terminal commands, and browser workflows through a dedicated runtime engine.

  • Project
    getomnico/omni

    An open-source, self-hosted AI agent for companies that integrates with workplace tools to gather context, analyze data, and execute tasks across systems.

  • Project
    TencentCloud/TencentDB-Agent-Memory

    A centralized memory server and management hub that allows AI agents to share and reuse distilled experience, skills, and project knowledge across sessions and frameworks.