Ellmos — AI skill for Claude Code

ellmos -- Extra Large Language Model Operating Systems

*From a spring to a stream -- LLM operating systems that flow.*

**English** | [Deutsch](README_de.md)

      

**ellmos** (XLLM-OS) is a local-first family of text-based operating systems for Large Language Models: agent memory, task state, MCP tools, skills, connector bridges, model routing, and multi-agent orchestration in small SQLite-backed projects. It is designed for people who want an AI operating layer they can inspect, run locally, and extend without a hosted platform.

[!NOTE] **Machine-Readable Index**: For AI agents, LLM tool callers, and automated indexing engines, a full context directory and system breakdown is available in [`llms.txt`](llms.txt).

**Quick links:** [Organization](https://github.com/ellmos-ai) | [BACH](https://github.com/ellmos-ai/bach) | [Rinnsal](https://github.com/ellmos-ai/rinnsal) | [gardener](https://github.com/ellmos-ai/gardener) | [llms.txt](llms.txt)

Start Here

[!TIP] **🗺️ See it instead of reading it:** the interactive [module circuit map](https://ellmos-ai.github.io) shows all functional areas of the ecosystem, how they work together, and every public module — with a [skill library](https://ellmos-ai.github.io/skills.html) and a [stack composer](https://ellmos-ai.github.io/stack-composer.html) alongside.

| If you are