Claude Skill
Rose22/openlumara
OpenLumara is a lightweight AI agent framework written from scratch, focusing on minimal token usage, modular design, and reduced security risks. Enable only what you need.
Overview
Repository
Install this Skill
git clone https://github.com/Rose22/openlumaraRegistry
Summary
OpenLumara is a lightweight AI agent framework written from scratch (not based on OpenClaw), designed to strip down to bare essentials, optimize token usage, and reduce security risks. Its modular architecture lets you enable only the components you need.
AI代理框架，从零开始编写（不基于openclaw），专注于精简至核心功能，优化令牌数量，降低安全风险。采用模块化设计，可仅启用所需部分。
Key features
- Written from scratch, not based on OpenClaw
- Minimalist design for reduced token count
- Modular architecture for selective feature enablement
- Enhanced security by reducing attack surface
Use cases
- Building lightweight AI assistants
- Deploying token-efficient agent workflows
- Creating secure, minimal-risk AI automation
- Customizing agent behavior with modular components
README excerpt
# OpenLumara OpenLumara is a modular, token-efficient AI agent framework written from scratch in Python. Unlike many other AI agents out there, this one is **local-first**, lightweight, modular, and very fast. The system prompt can be extremely small, as little as around 4000 tokens with normal use. This makes it very well-suited for local use, but it also results in drastically reduced token use when used with public API's. It pairs well with `llamacpp` and `koboldcpp`. Currently supports: WebUI (for use in your browser), CLI (terminal interface), Telegram, Discord, Matrix (with encryption support!). More coming. > [!TIP] > OpenLumara is especially well-suited to life management: todos, notes, morning routines, habit tracking, and so on. It's what i personally use it for the most, so it's well tailored for those needs. If you have any sort of executive dysfunction such as ADHD, autism, or any other form of executive dysfunction, OpenLumara can be a great tool! AI Disclaimer: OpenLumara's core framework (everything in the core/ folder) was designed and coded by hand, but i used AI to ask it how to further improve things, and how to fix certain bugs. Here and there I asked the AI how to do certain things in Python, but no code was inserted without me personally auditing it and modifying it. Certain non-core parts, such as many of the channels, were mostly generated by AI but manually audited and edited by me. This is not a vibe-coded project, but it IS an AI-assisted project. Here are some screenshots and videos of the Web UI: https://github.com/user-attachments/assets/c6bde601-022b-44c4-80b7-16ed6c7f74eb <img width="1203" height="765" alt="Screenshot_20260501_130111" src="https://github.com/user-attachments/assets/1924a3f6-06a7-495f-b4ee-320fd4f89037" /> <img w
Topics
No topics yet.