RedPlanetHQ/core

Your Personal AI OS

What it solves

CORE is a self-hosted "AI OS" designed to act as a persistent, always-on personal assistant. It solves the problem of fragmented AI interactions by consolidating memory, task management, and tool access across multiple platforms (like Slack, WhatsApp, and GitHub) into a single, unified AI agent that understands your preferences and context over time.

How it works

CORE uses a temporal knowledge graph to index data from emails, meetings, and messaging apps, creating a persistent memory of your work. It operates through a "Scratchpad" for task entry and can be reached via voice, chat, or messaging apps. For execution, it can delegate tasks to specialized coding agents (like Claude Code or Codex), drive a built-in isolated browser, or run terminal commands via a gateway. It integrates with over 50 apps using the Model Context Protocol (MCP).

Who it’s for

It is built for power users, developers, and individuals who want a self-hosted, privacy-focused AI assistant that can proactively manage tasks, write code, and integrate deeply with their professional toolstack.

Highlights

  • Temporal Memory: Indexes context from multiple sources into a knowledge graph for consistent context across tasks.
  • Multi-Interface Access: Interact via voice, a daily scratchpad, or messaging apps like Telegram and WhatsApp.
  • Coding Agent Delegation: Can spin up Claude Code or Codex sessions to open PRs and run code on your machine or in Docker.
  • Broad Integration: One-click connectors for 50+ apps including Jira, Linear, and Notion via MCP.
  • Human-in-the-loop: Structured task planning requires human approval before execution.

Related

  • Project
    peterfei/ai-agent-team

    A virtual AI development team with specialized roles (PM, Backend, Frontend, etc.) and a persistent memory system for managing complex software projects.

  • Project
    jaylfc/taOS

    taOS is an open‑source, self‑hosted AI platform that provides a browser‑based desktop, a distributed compute cluster, and a local memory service (taOSmd) for AI agents. It runs on any hardware (PCs, SBCs, phones), lets you install and manage agents from 17 frameworks, and keeps all conversations, files and knowledge graphs on your own machines, with cloud models optional.

  • Project
    pmbstyle/Alice

    An open-source AI desktop companion that integrates voice interaction, system-level computer control, and long-term memory to assist with daily tasks and creative work.

  • Project
    skalesapp/skales

    A local-first AI agent application that performs autonomous multi-step work across files, browsers, and calendars on desktop and mobile.

  • Project
    spinabot/brigade

    A self-hosted AI agent ecosystem that manages a crew of coordinated agents with shared long-term memory, accessible via terminal and multiple messaging channels.