MonoClaw Wiki

Schedule automated tasks with natural language, manage them with one cron tool, and attach one or more skills.

Spawn isolated child agents for parallel workstreams with delegate_task.

Durable SQLite-backed task board for coordinating multiple MonoClaw profiles.

Set a standing goal and let Mona keep working across turns until it's done. Our take on the Ralph loop.

Programmatic Python execution with RPC tool access — collapse multi-step workflows into a single turn.

Run custom code at key lifecycle points — log activity, send alerts, post to webhooks.

Generate agent trajectories at scale — parallel processing, checkpointing, and toolset distributions.

Overview of Mona's built-in tools — what's available, how toolsets work, and terminal backends.

On-demand knowledge documents — progressive disclosure, agent-managed skills, and the Skills Hub.

Background maintenance for agent-created skills — usage tracking, staleness, archival, and LLM-driven review.

How Mona remembers across sessions — MEMORY.md, USER.md, and session search.

External memory provider plugins — Honcho, OpenViking, Mem0, Hindsight, Holographic, RetainDB, ByteRover, Supermemory.

Project context files — .monoclaw.md, AGENTS.md, CLAUDE.md, global SOUL.md, and .cursorrules — automatically injected into every conversation.

Inline @-syntax for attaching files, folders, git diffs, and URLs directly into your messages.

Customize Mona's personality with a global SOUL.md, built-in personalities, and custom persona definitions.

Extend MonoClaw with custom tools, hooks, and integrations via the plugin system.

Plugins shipped with MonoClaw Runtime that run automatically via lifecycle hooks — disk-cleanup and friends.

Your first conversation with Mona — from zero to chatting in under 5 minutes.

How to update MonoClaw Runtime to the latest version or uninstall it.

Choose your learning path through the MonoClaw documentation based on your experience level and goals.

Practical advice to get the most out of MonoClaw — prompt tips, CLI shortcuts, context files, memory, cost optimization, and security.

Set up a local OpenAI-compatible LLM server on macOS with llama.cpp or MLX, including model selection, memory optimization, and real benchmarks on Apple Silicon.

Build an automated daily briefing bot that researches topics, summarizes findings, and delivers them to Telegram or Discord every morning.

Set up, configure, and optimize local LLMs using LM Studio on Apple Silicon Macs, tailored for M4 hardware and 16GB unified RAM.

Step-by-step guide to setting up a Telegram bot that your whole team can use for code help, research, system admin, and more.

Embed MonoClaw Runtime into your own Python scripts, web apps, or automation pipelines.

A practical guide to connecting MCP servers to MonoClaw, filtering their tools, and using them safely in real workflows.

A practical guide to setting up and using Mona voice mode across CLI, Telegram, Discord, and Discord voice channels.

How to use SOUL.md to shape Mona's default voice, what belongs there, and how it differs from AGENTS.md and /personality.

Step-by-step guide to building a complete MonoClaw plugin with tools, hooks, data files, and skills.

Real-world automation patterns using MonoClaw cron — monitoring, reports, pipelines, and multi-skill workflows.

Find, install, use, and create skills — on-demand knowledge that teaches Mona new workflows.

When and how to use subagent delegation — patterns for parallel research, code review, and multi-file work.

Build an automated AI code reviewer that monitors your repos, reviews pull requests, and delivers feedback — hands-free.

Connect MonoClaw Runtime to external tool servers via MCP — and control exactly which MCP tools Mona loads.

Use MonoClaw Runtime inside ACP-compatible editors such as VS Code, Zed, and JetBrains.

Use Claude, Nova, Llama, and DeepSeek via AWS Bedrock's native Converse API.

Use Mistral models directly via the Mistral AI API.

Real-time voice conversations with Mona — CLI, Telegram, Discord (DMs, text channels, and voice channels).

Web browsing and scraping capabilities for Mona.

Text-to-speech and voice message transcription across all platforms.

Set up MonoClaw Runtime as a Telegram bot.

Set up MonoClaw Runtime as a Discord bot.

Set up MonoClaw Runtime as a Slack bot using Socket Mode.

Set up MonoClaw Runtime as a WhatsApp bot via the built-in Baileys bridge.

Set up MonoClaw Runtime as a Signal messenger bot via signal-cli daemon.

Set up MonoClaw Runtime as an email assistant via IMAP/SMTP.

Set up MonoClaw Runtime as an SMS chatbot via Twilio.

Receive events from GitHub, GitLab, and other services to trigger MonoClaw agent runs.

Set up MonoClaw Runtime as a Matrix bot via mautrix.

Set up MonoClaw Runtime as a DingTalk bot.

Set up MonoClaw Runtime as a Feishu/Lark bot.

Authoritative reference for MonoClaw terminal commands and command families.

Complete reference for interactive CLI and messaging slash commands.

Complete reference of all environment variables used by MonoClaw Runtime.

Authoritative reference for MonoClaw built-in tools, grouped by toolset.

Reference for MonoClaw core, composite, platform, and dynamic toolsets.

Reference for MonoClaw MCP configuration keys, filtering semantics, and utility-tool policy.

MonoClaw's featured model catalog with context lengths, pricing, and recommendations.

Featured commercial skill modules vs the full MonoClaw Runtime skill library.

Frequently asked questions and solutions to common issues with MonoClaw Runtime.

Deploy Mona on Modal's serverless GPU infrastructure for scalable, on-demand agent execution.

AI-native persistent memory via Honcho — dialectic reasoning, multi-agent user modeling, and deep personalization.

High-quality text-to-speech using ElevenLabs voices for Mona.

Integrate Mona with Gmail, Calendar, Drive, Contacts, Sheets, and Docs via the Google Workspace skill.

Deploy Mona on Daytona's cloud development environments for ephemeral, isolated workspaces.

Deploy Mona and the MonoClaw dashboard to Vercel's serverless platform.

Interactive terminal support for local and remote shells via ptyprocess and pywinpty.

Run the MonoClaw dashboard as a local web application with FastAPI and uvicorn.

Fine-tune models with reinforcement learning using Atropos, Tinker, and Weights & Biases.

Web search and media generation tools bundled with MonoClaw — Exa, Firecrawl, Parallel Web, and Fal Client.

Configure MonoClaw Runtime — config.yaml, providers, models, API keys, and more.

Session persistence, resume, search, management, and per-platform session tracking.

Master the MonoClaw terminal interface — commands, keybindings, personalities, and more.

Launch the modern terminal UI for MonoClaw — mouse-friendly, rich overlays, and non-blocking input.

Choose your LLM provider and model, configure custom endpoints, and set up fallback routing.

Isolate configurations, sessions, and skills into separate profiles for work, personal, and team contexts.

Run multiple Mona agents safely on the same repository using git worktrees and isolated checkouts.

Run Mona in Docker and use Docker as a terminal backend for isolated command execution.

Security model, dangerous command approval, user authorization, container isolation, and production deployment best practices.

Filesystem safety nets for destructive operations using shadow git repos and automatic snapshots.