ellmos BACH - Text-Based Operating System for LLMs

The stream that unites everything.

Version: v3.8.0-sugar-of-babel

Overview

BACH is a text-based operating system that empowers Large Language Models (LLMs) to work autonomously, learn, and self-organize. Part of the ellmos family (Extra Large Language Model Operating Systems), BACH provides comprehensive infrastructure for task management, knowledge management, automation, and LLM orchestration.

Key Features

• 109+ Handlers - Full CLI and API coverage of all system functions
• 373+ Tools - Extensive tool library for file processing, analysis, and automation
• 932+ Skills - Reusable workflows and templates
• 54 Protocol Workflows - Pre-built process workflows
• Knowledge Store - Lessons, Facts, and Multi-Level Memory System
• Agent CLI - bach agent start/stop/list for direct agent control
• Prompt System - Central prompt management with board system and versioning
• Install Security Gate - Static pre-load scans block obvious code-injection patterns during skills install/plugins load; MCP setup validates allowlisted packages/configs fail-closed, plugin setup contracts now require explicit shell/desktop/MCP checks, and blocked local imports are quarantined
• Manifest-first Plugins - bach plugins inspect previews activation, provider/model, setup, and capability metadata without importing plugin runtime code
• SharedMemory Bus - Multi-agent coordination with conflict detection and decay
• USMC Bridge - United Shared Memory Communication for cross-agent communication
• llmauto Chains - Claude prompts as chain steps with bach:// URL resolution
• Chat Service - Multi-backend Telegram bot (5 backends), Control API, Web Dashboard, cross-platform System Tray

Installation

# Clone the repository
git clone https://github.com/ellmos-ai/bach.git
cd bach

# Install dependencies
pip install -r requirements.txt

# Optional: make `bach` and `from bach_api import ...` work directly from the repo root
pip install -e .

# Initialize BACH
python system/setup.py

MCP Servers (Claude Code Integration)

BACH provides two MCP servers for integration with Claude Code, Cursor, and other IDEs:

# Install and configure MCP servers (recommended)
python system/bach.py setup mcp

# Or manually via npm:
npm install -g ellmos-codecommander-mcp ellmos-filecommander-mcp

• ellmos-codecommander-mcp - Code analysis and refactoring tools
• ellmos-filecommander-mcp - File management and batch operations

Quick Start

# Start BACH
python bach.py --startup

# Create a task
python bach.py task add "Analyze project structure"

# Manage agents
python bach.py agent list
python bach.py agent start bueroassistent

# Manage prompts
python bach.py prompt list
python bach.py prompt add "My Prompt" --content "..."

# Check scheduler status
python bach.py scheduler status

# Shut down BACH
python bach.py --shutdown

Core Components

1. Task Management

Full GTD system with prioritization, deadlines, tags, and context tracking.

2. Knowledge System

Structured memory system with Facts, Lessons, and automatic consolidation (5 memory types).

3. Agent Framework

Boss agents orchestrate experts for complex tasks. The Agent CLI allows direct starting, stopping, and listing of agents via bach agent.

The 5 Boss Agents: ati, officeassistant, finance-assistant, health-assistant, personal-assistant

4. Prompt System

Central management of prompt templates with board collections and full versioning (bach prompt).

5. Chat Service & Bridge System

Multi-backend Telegram bot with pluggable LLM backends (Ollama, Claude CLI, Codex CLI, Claude API, OpenAI API), HTTP Control API with web dashboard, and cross-platform system tray. Connector framework for additional services (Email, WhatsApp, etc.) and USMC Bridge for cross-agent communication.

6. Automation

SchedulerService for time-based jobs (chains, tasks, scripts) and event-driven workflows via the hook framework.

7. SharedMemory

Multi-agent coordination with context generation, conflict detection, decay, and delta queries.

8. llmauto Integration

Chain steps as LLM prompts with bach:// URL resolution for dynamic context embedding.

The ellmos Family

All ellmos projects follow a water metaphor -- from a spring to a full stream:

Documentation

• Quickstart Guide - Get your first workflow running in 5 minutes
• User Manual - Complete handbook
• Skills Catalog - All available skills
• Agents Catalog - All available agents and experts
• Workflows - 54 protocol workflows
• SKILL.md - LLM operating instructions (for Claude, Gemini, Ollama)

See Also: OpenClaw

How does BACH compare to OpenClaw, the popular open-source AI assistant (about 369k GitHub stars observed on 2026-05-07)?

In short: BACH goes deep (structured memory, autonomous agents, scheduler, 145+ DB tables). OpenClaw goes wide (20+ messengers, native apps, voice, massive community). Different philosophies, complementary strengths.

Competitive Watch (2026-05-07)

As of May 7, 2026, OpenClaw's latest stable GitHub release is 2026.5.5, published on May 6, 2026. For BACH, the relevant takeaways from the recent 2026.4.x to 2026.5.5 release line are still not the broader channel surface, but control-plane hardening: workspace-scoped plugin metadata snapshot reuse on hot paths, install hints for missing official external plugins, collision-safe session-memory capture around repeated resets/new sessions, and stricter fail-closed config/setup behavior.

BACH should keep selectively adopting the parts that fit its operating-system model: manifest-first metadata, fail-closed setup checks, broader install scanning for skills/MCP/plugins, privacy-preserving secret/reference handling, active-run steering at safe checkpoints, memory/wiki provenance views, and low-cardinality telemetry. BACH now also validates malformed existing Claude config JSON before hook or MCP setup writes, which moves the setup-check track forward without pulling in OpenClaw's wider channel/runtime surface.

License

MIT License - see LICENSE for details.

Support

• Issues: GitHub Issues
• Discussions: GitHub Discussions

Deutsche Version

BACH ist ein textbasiertes Betriebssystem, das Large Language Models (LLMs) befaehigt, eigenstaendig zu arbeiten, zu lernen und sich zu organisieren.

Die vollstaendige deutsche Dokumentation findest du hier: README.de.md

ellmos BACH v3.8.0-sugar-of-babel - Text-Based Operating System for LLMs

Haftung / Liability

Dieses Projekt ist eine unentgeltliche Open-Source-Schenkung im Sinne der §§ 516 ff. BGB. Die Haftung des Urhebers ist gemäß § 521 BGB auf Vorsatz und grobe Fahrlässigkeit beschränkt. Ergänzend gelten die Haftungsausschlüsse aus GPL-3.0 / MIT / Apache-2.0 §§ 15–16 (je nach gewählter Lizenz).

Nutzung auf eigenes Risiko. Keine Wartungszusage, keine Verfügbarkeitsgarantie, keine Gewähr für Fehlerfreiheit oder Eignung für einen bestimmten Zweck.

This project is an unpaid open-source donation. Liability is limited to intent and gross negligence (§ 521 German Civil Code). Use at your own risk. No warranty, no maintenance guarantee, no fitness-for-purpose assumed.