A community-driven registry for Claude, Cursor, Windsurf, Cline & more. Not affiliated with Anthropic.
Are you the author? Sign in to claim
BACH v3.12.4-earth: local-first text-based OS for LLM agents with SQLite memory, 113+ handlers, 550+ tools, MCP servers,
The stream that unites everything.
Version: v3.12.4-earth
BACH is documented and shipped with translation surfaces for six languages:
🇬🇧 English | 🇩🇪 Deutsch | 🇪🇸 Español | 🇷🇺 Русский | 🇯🇵 日本語 | 🇨🇳 中文
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>/.
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.
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.
bach agent start/stop/list for direct agent controlbach agent doctor [name] [--json] validates Claude CLI availability, runtime dirs, skill files, and stale PID state before a launchbach agent pause/resume/checkpoint/steer/clear-steer [name] [--json] lets operators stage cooperative pause requests and guidance before or during a run, record explicit safe-checkpoint acknowledgements, mirror that state into OPERATOR_NOTES.md, preserve queued hints across the next bach agent start, inject them into the generated session CLAUDE.md, and expose nested operator_control snapshots plus queued_for_next_start for automation-safe pollingbach agent start now accepts --permission-mode, --allowed-tools, and --max-turns, and can preload the same defaults from agent SKILL frontmatter for per-agent guardrailsbach scheduler doctor [--json] plus bach scheduler session doctor [--json] validate automation scripts, PID state, DB/config/profile surfaces, and suggest recovery steps before background services are startedbach scheduler session pause/resume/steer/clear-steer [--json] lets operators gate or retarget the next profile-specific auto-session without editing daemon config by handbach scheduler pause/resume/steer/clear-steer [--json] now exposes the same operator control plane for due scheduler jobs, including global pause and queued run guidance without hand-editing control files; queued scheduler hints now also hydrate llmauto chains into their next safe-checkpoint prompt pathbach agent list/start/stop/pause/resume/checkpoint/steer/clear-steer/status --json, bach scheduler status/jobs/session status --json, and bach scheduler session pause/resume/steer/clear-steer --json, including queue state, queued_for_next_start, timestamps, checkpoint acknowledgements, and operator-note metadata for automation-safe pollingbach upgrade list <path> --json, bach upgrade status/check --json, and bach upgrade repair [--dry-run] [--version <tag>] expose automation-safe version, status, drift, repair hints, and recovery for broken distribution metadatabach path exposes canonical system/workspace/DB paths, validation, resolve helpers, and DB overrides in text or JSONskills 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 quarantinedbach plugins inspect previews activation, provider/model, setup, and capability metadata without importing plugin runtime codebach_api Core - task and memory now expose discoverable methods via dir(...), return Python objects for common reads/writes, and still keep raw(...) for legacy handler-style callsbach:// URL resolution# Clone the repository
git clone https://github.com/ellmos-ai/bach.git
cd bach
# Install dependencies and make `bach` CLI available
pip install -e .
# Pre-flight check
bach setup preflight
# Full install (MCP servers, hooks, secrets, user profile)
bach setup full-install
BACH provides two MCP servers for integration with Claude Code, Cursor, and other IDEs. Cross-platform tested on Windows, macOS (ARM64), and Linux:
# 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
# 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
Full GTD system with prioritization, deadlines, tags, and context tracking.
Structured memory system with Facts, Lessons, and automatic consolidation (6 memory types, 210+ DB tables).
11 Boss agents orchestrate 22 experts for complex tasks. The Agent CLI allows direct starting, stopping, and listing of agents via bach agent, and now also supports prelaunch steering queues, cooperative pause requests, and explicit safe-checkpoint acknowledgements via bach agent checkpoint. Queued hints are injected into the generated session CLAUDE.md at launch, OPERATOR_NOTES.md mirrors steering, pause, and checkpoint state, and live JSON status surfaces expose the nested operator_control snapshot for dashboards.
Illustration shows BACH's five original boss agents: ati, officeassistant, finance-assistant, health-assistant, personal-assistant. The current system ships 11 boss agents and 22 experts.
Central management of prompt templates with board collections and full versioning (bach prompt).
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.
SchedulerService for time-based jobs (chains, tasks, scripts) and event-driven workflows via the hook framework.
Multi-agent coordination with context generation, conflict detection, decay, and delta queries.
Chain steps as LLM prompts with bach:// URL resolution for dynamic context embedding.
All ellmos projects follow a water metaphor -- from a spring to a full stream:
| Tier | Project | Description | Repository |
|---|---|---|---|
| 1 | USMC | United Shared Memory Client -- the spring (shared memory only) | github.com/ellmos-ai/usmc |
| 2 | Rinnsal | The trickle -- USMC + llmauto (LLM orchestration), extremely compact | github.com/ellmos-ai/rinnsal |
| 3 | BACH | The stream that unites everything -- 113+ handlers, 1870+ skills, agents, GUI, bridge | github.com/ellmos-ai/bach |
How does BACH compare to OpenClaw, a popular open-source AI assistant?
| BACH | OpenClaw | |
|---|---|---|
| Focus | LLM Operating System -- deep autonomy, structured memory, multi-agent orchestration | Personal AI Assistant -- broad messaging gateway, voice, companion apps |
| Tools/Skills | 550+ tools, 1870+ skills, 59 workflows (local, curated) | Community-driven skill/plugin ecosystem; recent releases emphasize manifest-first plugin metadata and install safety |
| Memory | 6 memory types with decay, conflict detection, consolidation (210+ DB tables) | Session/runtime workspace with bootstrap files such as AGENTS.md, TOOLS.md, USER.md, and related context files |
| Agents | Boss-Expert orchestration (11 boss agents + 22 experts), SharedMemory Bus | Agent runtime with multi-session/channel operation |
| Messaging | Telegram, Email, WhatsApp (Bridge System) | 20+ platforms (WhatsApp, Telegram, Slack, Discord, Signal, Teams, Matrix...) |
| Interfaces | CLI, Python API, PySide6 GUI, Web GUI, Telegram Bot, Web Chat, System Tray | CLI, WebChat, macOS/iOS/Android apps, Voice |
| MCP | Own MCP servers (FileCommander, CodeCommander) | Native MCP Registry |
| Stack | Python 3.10+, SQLite | TypeScript, Node.js 22+ |
| License | MIT | MIT |
In short: BACH goes deep (structured memory, autonomous agents, scheduler, 210+ DB tables). OpenClaw goes wide (20+ messengers, native apps, voice, large community). Different philosophies, complementary strengths.
As of 2026-06-13, the OpenClaw repository still marks 2026.6.6 as the latest stable release on GitHub, published on June 12, 2026, while the newest visible prerelease on the official release feed is now 2026.6.7-beta.1, published on June 13, 2026 at 09:42. The most relevant new beta signals for BACH are tighter channel delivery, safer auth/context boundaries, stronger recovery across agent, memory, Codex, cron, and update paths, clearer doctor/update progress reporting, and more trustworthy QA/release evidence.
On the BACH side, the clean GUI i18n state from 2026-06-12 remains intact at 17,593 exported translations with 0 missing GUI entries, and the 2026-06-13 care pass shifted to workflow coverage: a shared skills/workflows/SOFTWARE.md now links software usecases 41-49 to a real workflow file instead of manual fallback, while wiki-author.md was updated to the current wiki/ and hub/_services/wiki/ paths. Verification re-ran bach usecase run 41 --dry-run, bach usecase run-all --dry-run, and a focused test_tuev_handler.py regression (1 passed), which moved the dry-run overview from 15 workflow-backed / 35 manual usecases to 24 / 26. Next high-leverage steps remain deeper active-run steering inside long-running scheduler internals, installer end-to-end coverage, GUI regression coverage, and closing the remaining manual workflow gaps such as reflection_status and the larger domain buckets.
MIT License - see LICENSE for details.
BACH ist ein textbasiertes Betriebssystem, das Large Language Models (LLMs) befähigt, eigenständig zu arbeiten, zu lernen und sich zu organisieren.
Die vollständige deutsche Dokumentation findest du hier: README.de.md
ellmos BACH v3.12.4-earth - Text-Based Operating System for LLMs
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.
Run Claude Code as an MCP server so any agent can delegate coding tasks to it
@microsoft✓ OfficialBrowser automation using accessibility snapshots instead of screenshots
MCP server integration for DaVinci Resolve Studio
A Jetbrains IDE IntelliJ plugin aimed to provide coding agents the ability to leverage intelliJ's indexing of the codeba