Home / Servers

bach

by ellmos-ai

<img src="assets/banner.png" width="100%" alt="BACH banner"> <img src="assets/banner_v2.png" width="100%" alt="BACH Banner">

ellmos BACH β€” Text-Based Operating System for LLMs

The stream that unites everything.

Python License: MIT Version Status Tests

Version: v3.13.0-bluesky

🎬 Demo video

See BACH working live β€” dashboard, Codex backend, operator steering β€” in 2:22:

BACH demo β€” local-first LLM operating system (2:22)

Built with OpenAI Codex & GPT-5.6

BACH uses Codex both as a first-class runtime backend and as a repository-development partner. For the exact automation schedules, model routes, and auditable session IDs, see the verified Build Week attribution below.

Languages

BACH is documented and shipped with translation surfaces for six languages:

πŸ‡¬πŸ‡§ English | πŸ‡©πŸ‡ͺ Deutsch | πŸ‡ͺπŸ‡Έ EspaΓ±ol | πŸ‡·πŸ‡Ί Русский | πŸ‡―πŸ‡΅ ζ—₯本θͺž | πŸ‡¨πŸ‡³ δΈ­ζ–‡

The current release snapshot enables de, en, es, ru, ja, and zh in system/exports/translations/languages_config.release.json and exports matching locale files in system/exports/translations/locales/. For crawlers and direct language entry points, each language also has its own README.md under docs/i18n/<lang>/.

<p align="center"> <img src="overview.jpg" alt="BACH Overview" width="700"> </p>

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.

Discovery Context

BACH is best described as a local-first LLM operating system: a persistent Python/SQLite workbench for autonomous agents, structured memory, scheduler-driven automation, prompt chains, MCP server integration, and multilingual operator surfaces. It is not a chatbot wrapper, hosted agent SaaS, Bash unit-test framework, music project, or LangChain-style pipeline library.

Canonical GitHub repository: ellmos-ai/bach. Machine-readable project context for LLM crawlers is available in llms.txt.

Useful search phrases include ellmos-ai/bach, local-first LLM operating system, text-based OS for LLM agents, SQLite memory for AI agents, BACH ellmos agent OS, personal agentic OS Python SQLite, and multi-agent orchestration with MCP servers.

OpenAI Build Week β€” Codex and GPT-5.6

BACH uses Codex in two distinct roles:

  • Runtime backend: codex-cli is one of five pluggable chat backends, and BACH agents can delegate coding tasks through codex exec.
  • Repository development: three active Codex automations maintain the project: bach-daily-care-and-dev-check, bach-start-and-health-checks, and bach-github-release-service. Since July 21, 2026, all three have been configured for GPT-5.6 (gpt-5.6-terra); the first two run daily, while the release service runs weekly.
  • Verified model routing: in Codex Session 019f85c6-4339-7f13-b8e5-bf1823fd8432, GPT-5.6 Sol with high reasoning audited all 78 automation definitions and routed BACH's development and release jobs to Terra/high and health checks to Terra/medium.
  • Final submission audit: GPT-5.6 Sol in Codex Session 019f8674-fe9a-7d91-a80f-7ee799e8ced0 reviewed and certified the pending BACH changes, corrected th

Related servers

n8n

by n8n-io

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

NOASSERTIONβ˜… 198,904

@modelcontextprotocol/server-everything

Official

by modelcontextprotocol

MCP server that exercises all the features of the MCP protocol

β˜… 89,105

@modelcontextprotocol/server-filesystem

Official

by modelcontextprotocol

MCP server for filesystem access

SEE LICENSE IN LICENSEβ˜… 89,105

mcp-server-fetch

Official

by modelcontextprotocol

A Model Context Protocol server providing tools to fetch and convert web content for usage by LLMs

β˜… 89,105