From a spring to a stream — LLM operating systems that flow.
ellmos (XLLM-OS) is a family of text-based operating systems that empower Large Language Models to work autonomously, learn, and self-organize. For machine-readable ecosystem context, see llms.txt.
This index is complete for the public ellmos-ai repositories (38 repos, 1 archived). Archived repositories are marked explicitly. Last checked against GitHub: 2026-07-24.
| Area | Repositories |
|---|---|
| Organization profile | .github - org profile, community health files and llms.txt |
| Stack catalog | stacks - catalog and shared manifest schema for every stack in the ellmos-ai family |
| Operating systems | bach, rinnsal, ellmos - plus gardener as the minimal OS tier when run standalone; it is indexed under The .MEMORY Pillar below |
| Memory pillar | usmc, gardener, taskplan - curated session memory, organic cross-source index, and task tracking; see The .MEMORY Pillar |
| MCP servers | ellmos-codecommander-mcp, ellmos-filecommander-mcp, ellmos-clatcher-mcp, n8n-manager-mcp, ellmos-controlcenter-mcp, ellmos-homebase-mcp, ellmos-servercommander-mcp, ellmos-blender-use-mcp, open-compute-mcp |
| Agent modules and orchestration | clutch, connectors, MarbleRun, swarm-ai, n8n-workflow-manager, ellmos-stack, agent-ops-stack, skills, build-your-users-mind, open-compute, web-scraper - standalone web scraper (get/links/forms/headers/extract/screenshot) extracted from BACH, with an SSRF guard; anonymizer - local-first document pseudonymization with fail-closed NER; report-forge - domain-neutral core for anonymizable report pipelines |
| Domain tools | law-checker - source-grounded AI first-look legal assessments for German law (Erstorientierung, no substitute for a lawyer), statute registry and embodiment agents; worksheet-generator - generates structured, ICF-aware worksheets for pedagogical and therapeutic use, rendered to Markdown/HTML/DOCX; steuer-assistent - offline-first worksheet for German employee income-related expenses (Werbungskosten), with guided collection and plausibility checks and no cloud upload |
| Media and content workflows | ai-media-editor - local AI video, audio and podcast editing with local transcription, transcript-based cuts, Hyperframes motion graphics and agent-driven creative edits |
| Evaluation, templates and maintenance | ellmos-tests, project-docs-template - agent-ready project documentation template with START/STATE/TODO/DONE, workflows, lightweight tooling and LLM-friendly project memory; clirec - human-readable GUI demonstration recordings for CLI and agent workflows |
| Legacy archive | recludos-legacy - archived predecessor to BACH |
Two operating systems — different philosophies, same goal — plus a memory pillar either one can plug into:
 BACH The stream that unites everything Full LLM-OS: 113+ handlers, 1870+ skills, agents, GUI |
 Rinnsal The trickle Lightweight LLM infra: memory, tasks, connectors, chains, i18n. Zero dependencies. |
 gardener The zen garden Two roles, both current: the ellmos memory module (organic cross-source index) when composed into the pillar, and a minimal, LLM-native OS when run standalone: 1 table, 4 functions, FTS5 search. |
Which role applies is a deployment question, not a ranking: composed into the .MEMORY pillar below, gardener is its organic cross-source index; run on its own, it is the minimal OS tier. Both are fully supported.
ellmos memory isn't one repo — it's three focused modules that combine into the family's standard memory stack, importable as a dependency by any OS layer (BACH, Rinnsal) instead of each one rebuilding its own memory/task system:
| Module | Role |
|---|---|
| usmc | Curated session/core memory — the facade and entry point of the memory system. Push model: "what I consciously remember." |
| gardener | Memory supplier: organic growth via absorb/decay, plus a federated cross-source FTS5 index via observe() that cites results back to their source. Pull model: "index what's already there." |
| taskplan | Standalone SQLite task module — tasks stay separate from knowledge memory. Zero dependencies. |
The ellmos ecosystem consists of operating systems, the .MEMORY pillar, and pluggable modules that can be integrated into any OS — or used standalone.
| BACH | Rinnsal | gardener (memory pillar primary, OS secondary) | |
|---|---|---|---|
| Philosophy | Maximalist: everything integrated | Lightweight: zero dependencies | Minimalist: 1 table, 4 functions |
| Database | SQLite (145+ tables) | SQLite (structured) | SQLite (1 table everything + FTS5) |
| Memory | 5-type cognitive model | Facts/Notes/Lessons/Sessions | Unified (memo/lesson/recall + decay) |
| Tasks | Full GTD (priority, deadline, tags) | Priority + Status + Agent assignment | type='task' in everything |
| Tools | 550+ specialized tools | CLI commands | 6 bridge+skin tools (extensible) |
| Skills/Agents | 1870+ skills, 5 boss agents, 28 experts | None | None (the LLM is the agent) |
| Connectors | Telegram, Email, WhatsApp | Telegram, Discord, Home Assistant | Planned (v0.2+) |
| GUI | PySide6 Desktop + Web | CLI only | CLI only |
| Self-Extension | bach skills create |
No | No |
| Codebase | ~50,000+ lines | ~2,000 lines | ~1,600 lines |
| Best for | Power users, all-in-one | Developers wanting light infra | Minimalists, LLM-native experiments; standalone use of the .MEMORY pillar |
These modules and skills can be integrated into any OS or used standalone:
|
Modules (USMC, gardener and taskplan now live in the .MEMORY pillar above.)
|
Skills
|
| Project | Purpose |
|---|---|
| ai-media-editor | Local AI media-editing orchestrator for video, audio and podcasts: local STT with faster-whisper or WhisperX, Scribe-compatible transcript JSON, video-use transcript cuts, Hyperframes motion graphics and agent-guided creative edits. |
flowchart TD
subgraph OS["Choose Your OS Layer"]
BACH["BACH (full)<br/>1870+ skills · 5 boss agents"]
RIN["Rinnsal (light)<br/>Zero deps · Connectors · Chains · Events"]
end
subgraph MEM[".MEMORY Pillar"]
GAR["gardener — organic index (also: minimal OS)"]
USMC["usmc — curated memory"]
TASK["taskplan — tasks"]
end
subgraph MOD["Pluggable Modules"]
CLUTCH["clutch — model routing"]
MARBLE["MarbleRun — agent chains"]
SWARM["swarm-ai — parallel LLMs"]
OCOMP["open-compute — computer use"]
end
BACH --- MEM
RIN --- MEM
BACH --- MOD
RIN --- MOD
All projects: Python 3.10+ | SQLite | MIT License | Zero or minimal dependencies
Stacks are manifest-driven compositions (ellmos.stack.v2) — no code copies, just declared components. Two active public stacks anchor the family, catalogued in a third:
| Stack | Purpose | Core modules |
|---|---|---|
| stacks | Catalog and shared manifest schema for every stack in the ellmos-ai family | — |
| ellmos-stack | Self-hosted, local-first AI research base: Ollama, n8n, Rinnsal memory, Docker Compose automation | Rinnsal · KnowledgeDigest (file-bricks) · Ollama · n8n |
| agent-ops-stack | Coordination layer for CLI coding agents: ticket routing, file locking, cross-machine sync, decision-avatar, MCP control plane | ticket-master (dev-bricks) · lock-master (dev-bricks) · sync-master (dev-bricks) · build-your-users-mind · skills · ellmos-controlcenter-mcp · ellmos-homebase-mcp |
A number of these modules are deliberately both: standalone dev tools you can adopt individually, and stack components you get automatically by installing the stack. That also applies to llm-note (doc-bricks) — local-first notebooks for LLM agents, built as a pluggable module for stack composition.
 CodeCommander Code analysis & refactoring npm i -g ellmos-codecommander-mcp
|
 FileCommander File management & batch ops npm i -g ellmos-filecommander-mcp
|
 Clatcher Utility tools: file repair, format conversion, duplicate detection, batch operations npm i -g ellmos-clatcher-mcp
|
 n8n Manager n8n workflow automation npm i -g n8n-manager-mcp
|
 ControlCenter MCP profile dashboard, capability bundles & policy audits npm i -g ellmos-controlcenter-mcp
|
 Homebase Local LLM memory, knowledge, state & orchestration npm i -g ellmos-homebase-mcp
|
 ServerCommander Server health checks, log analysis, deploy dry-runs & mail status npm i -g ellmos-servercommander-mcp
|
 Blender Use Headless Blender asset QA: background runs & FBX reimport checks npm i -g ellmos-blender-use-mcp
|
 open-compute-mcp Computer-use: screenshot, safety-gated actions & Windows UIA targeting npx open-compute-mcp
|
 recludOS Archived predecessor to BACH Historical reference |
These projects live in sibling organizations but are particularly relevant to the ellmos multi-agent ecosystem:
| Project | Org | Description |
|---|---|---|
| ticket-master | dev-bricks | Cross-platform, multi-provider ticket router / triage console — files structured tickets and routes them to the right AI provider or sub-agent |
| lock-master | dev-bricks | Portable multi-agent file-lock system — LOCK*.txt-based project/component locking with scopes, expiry, stale-cleanup and a fast overview cache; especially relevant for multi-agent coordination |
| sync-master | dev-bricks | Serverless cross-machine sync yard for multi-agent setups — slot-per-host write ownership, a gated daily sync ritual, message channels and a bootstrap runbook; the transport layer that keeps several machines and their agents in step |
| companion-for-agy | dev-bricks | PTY-based wrapper that captures agy (Gemini CLI) responses via ANSI color extraction — lets Claude Code, Codex and CI pipelines read Gemini output reliably |
| llm-note | doc-bricks | Local-first notes and notebook inboxes for LLM agents — extracted from BACH Notizblock/Denkarium patterns with SQLite, plain-text notebooks and six locales |
| knowledgedigest | file-bricks | Local-first knowledge base with LLM preprocessing — ingest, structure and query documents without cloud dependencies; core module of ellmos-stack |
Full documentation | License: MIT
