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.
Three operating systems -- different philosophies, same goal:
 BACH The stream that unites everything Full LLM-OS: 109+ handlers, 932+ skills, agents, GUI |
 Rinnsal The trickle Lightweight LLM infra: memory, tasks, connectors, chains. Zero dependencies. |
 gardener The zen garden LLM-native OS: 1 table, 4 functions, FTS5 search. Everything is searchable. |
The ellmos ecosystem consists of three OS layers and pluggable modules that can be integrated into any OS -- or used standalone.
| BACH | Rinnsal | gardener | |
|---|---|---|---|
| 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 | 373+ specialized tools | CLI commands | 6 bridge+skin tools (extensible) |
| Skills/Agents | 932 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 |
These modules can be integrated into any OS or used standalone:
| Module | Purpose | Key Feature |
|---|---|---|
| USMC | Cross-agent shared memory | Confidence-based conflict resolution, change tracking |
| clutch | Provider-neutral model routing | Auto-learning which model fits which task, budget zones |
| MarbleRun | Chain orchestration | Autonomous multi-round agent loops with context handoff |
| swarm-ai | Parallel LLM coordination | 5 patterns: Epstein, Hierarchy, Stigmergy, Consensus, Specialist |
┌─────────────────────────────────────────────────┐
│ Choose Your OS Layer │
│ │
│ BACH (full) Rinnsal (light) gardener (min) │
│ ┌─────────┐ ┌────────────┐ ┌──────────┐ │
│ │ 932 │ │ Zero deps │ │ 1 table │ │
│ │ skills │ │ Connectors │ │ 4 funcs │ │
│ │ 5 boss │ │ Chains │ │ FTS5 │ │
│ │ agents │ │ Events │ │ = search │ │
│ └────┬────┘ └─────┬──────┘ └─────┬────┘ │
│ └──────────────┼─────────────────┘ │
│ │ │
│ ┌──────────────┼──────────────┐ │
│ │ Pluggable Modules │ │
│ │ │ │
│ │ USMC ── shared memory │ │
│ │ clutch ── model routing │ │
│ │ MarbleRun ── agent chains │ │
│ │ swarm-ai ── parallel LLMs │ │
│ └─────────────────────────────┘ │
└─────────────────────────────────────────────────┘
All projects: Python 3.10+ | SQLite | MIT License | Zero or minimal dependencies
 skills Pluggable Skill Library Reusable agent skills that slot into any ellmos OS. Development, research, education, infrastructure -- pick what you need. |
 CodeCommander Code analysis & refactoring npm i -g bach-codecommander-mcp
|
 FileCommander File management & batch ops npm i -g bach-filecommander-mcp
|
 n8n Manager n8n workflow automation npm i -g n8n-manager-mcp
|
| Project | Description |
|---|---|
| USMC | Cross-agent shared memory with confidence-based conflict resolution |
| clutch | Provider-neutral model routing with auto-learning and budget zones |
| MarbleRun | Autonomous multi-round agent chains for Claude Code |
| swarm-ai | 5 parallel LLM coordination patterns (Stigmergy, Consensus, ...) |
| n8n Workflow Manager | Standalone GUI for n8n workflow creation |
| ellmos-stack | Self-hosted AI stack (Docker, Ollama, n8n) |
| skills | Pluggable skill library (dev, research, education, infrastructure) |
 recludOS Archived predecessor to BACH Historical reference |
Full documentation | License: MIT