Rose22/openlumara

AI agent framework, written from scratch (not based on openclaw), focused on stripping it down to the bare necessities, optimizing token count, reducing security risks. modular so you can enable only exactly what you need.

What it solves

OpenLumara is a lightweight, local-first AI agent framework designed to reduce token consumption and overhead. It provides a modular system for managing personal tasks, notes, and routines, making it particularly useful for individuals with executive dysfunction (such as ADHD or autism) who need a structured AI assistant.

How it works

The framework is written in Python and connects to any OpenAI API-compatible backend, including local providers like llamacpp, ollama, and koboldcpp. It uses a modular architecture where features—such as memory, scheduling, and shell access—can be toggled on or off to minimize the system prompt size. It supports multiple communication channels including a WebUI, CLI, Telegram, Discord, and Matrix.

Who it’s for

  • Local AI enthusiasts: Users who want a private, self-hosted agent that is fast and token-efficient.
  • Developers: Those looking for a modular framework that is easy to extend via Python classes for new modules or channels.
  • Personal productivity seekers: People managing life tasks, habits, and routines through an AI interface.

Highlights

  • Extreme Token Efficiency: Optimized system prompts (as low as 4000 tokens) and tools to monitor real-time token usage.
  • Modular Design: Almost every core component (memory, scheduler, time-awareness) can be disabled to reduce overhead.
  • Sandboxed Shell: A toggleable module that runs commands inside a Docker or Podman container for security.
  • Multi-Channel Support: Native integration with WebUI, CLI, Telegram, Discord, and Matrix.
  • Integrated Scheduler: A custom-built system for scheduling AI tasks.
  • Memory System: Uses MessagePack format for compact and fast data storage.

Related

  • Project
    tinyhumansai/openhuman

    An open-source, local-first AI orchestrator that builds a persistent personal memory graph from your data and manages fleets of agents via visual, durable workflows.

  • Project
    open-jarvis/OpenJarvis

    A framework for local-first personal AI agents that allows users to run intelligence on their own devices, reducing reliance on cloud APIs.

  • Project
    opensquilla/opensquilla

    A token-efficient microkernel AI agent that uses a local model router to minimize costs by sending tasks to the cheapest capable LLM.

  • Project
    amaiya/onprem

    A privacy-focused Python toolkit for document intelligence that enables local-by-default LLM execution for sensitive data, with optional cloud integration.

  • Project
    luoguoxiong/aipack

    A lightweight personal AI assistant framework featuring a custom Agent runtime, hybrid long-term memory, and multi-level context compression.