chore: sync content to repo (#9826)

Co-authored-by: kamranahmedse <4921183+kamranahmedse@users.noreply.github.com>
2026-09-24 15:00:31 +08:00 · 2026-04-06 18:03:42 +02:00
parent 59042092e6
commit baad2d2900
55 changed files with 377 additions and 0 deletions
@@ -0,0 +1,3 @@
+# Adding Daemon
+
+A daemon is a background process that runs continuously without needing a terminal window open. Configuring Open Claw as a daemon ensures it starts automatically and keeps running even after you log out or restart your machine.
@@ -0,0 +1,7 @@
+# Adding First Channel
+
+After setting up your model provider, the next step is connecting a communication channel, in other words, the platform where you will actually talk to your agent. Telegram is recommended as the fastest channel to get started with.
+
+Visit the following resources to learn more:
+
+- [@official@Channels](https://docs.openclaw.ai/channels)
@@ -0,0 +1,7 @@
+# Agent Loop
+
+When Open Claw receives a message, it runs a full agent loop rather than returning a single response. The loop validates the message, resolves the model, assembles the system prompt from skills and context files, and then sends everything to the model for inference. If the model decides to call a tool, like running a command, reading a file, or searching the web, the loop executes it, feeds the result back to the model, and continues until no more tool calls are needed and a final reply is ready. If the session gets too long for the context window, compaction kicks in automatically before retrying.
+
+Visit the following resources to learn more:
+
+- [@article@Agent Loop](https://docs.openclaw.ai/concepts/agent-loop)
@@ -0,0 +1,7 @@
+# Agents
+
+An agent in Open Claw is a fully isolated unit with its own workspace folder containing its personality and configuration files, its own state directory that holds auth profiles and the model registry, and its own session store that keeps the full conversation history separate from every other agent. Because auth profiles are scoped per-agent, credentials for one agent are never automatically shared with another, which means you can run a personal agent on your WhatsApp number and a work agent on a separate account on the same Gateway without any risk of their sessions, memories, or API keys crossing over.
+
+Visit the following resources to learn more:
+
+- [@official@Agent Runtime](https://docs.openclaw.ai/concepts/agent)
@@ -0,0 +1,8 @@
+# AGENTS.md
+
+AGENTS.md describes the agents available in your workspace, their roles, and how they relate to each other. It is used when running multiple agents to clarify who does what.
+
+Visit the following resources to learn more:
+
+- [@official@Default AGENTS.md](https://docs.openclaw.ai/reference/AGENTS.default#default-agents-md)
+- [@official@AGENTS.md Template](https://docs.openclaw.ai/reference/templates/AGENTS)
@@ -0,0 +1,7 @@
+# Anthropic
+
+Anthropic is the company behind the Claude family of models. Connecting Open Claw to Anthropic lets you use Claude as your agent's underlying model, which is well-suited for reasoning, writing, and tool use.
+
+Visit the following resources to learn more:
+
+- [@official@Anthropic Provider](https://docs.openclaw.ai/providers/anthropic)
@@ -0,0 +1,8 @@
+# Auth & Model Providers
+
+This section covers how to connect Open Claw to AI model providers like Anthropic, OpenAI, Gemini, or Ollama by entering your API credentials. The model provider is what powers the agent's intelligence.
+
+Visit the following resources to learn more:
+
+- [@official@Provider Directory](https://docs.openclaw.ai/providers)
+- [@official@Provider Quickstart](https://docs.openclaw.ai/providers/models)
@@ -0,0 +1,7 @@
+# Azure
+
+Azure is Microsoft's cloud platform offering a wide range of infrastructure options. It is a valid choice for hosting Open Claw, particularly for users already in the Microsoft ecosystem.
+
+Visit the following resources to learn more:
+
+- [@official@Azure Hosting](https://docs.openclaw.ai/install/azure)
@@ -0,0 +1,7 @@
+# Channels
+
+Channels are the messaging platforms through which users interact with Open Claw, and each one connects to the single Gateway process that routes incoming messages to the right agent and sends replies back. Every channel runs simultaneously on the same Gateway, so you can be connected to Telegram, WhatsApp, Discord, and Slack all at once without running separate processes. Text is supported across all channels, but richer features like reactions, media, message editing, and group behavior vary depending on what each platform's API supports
+
+Visit the following resources to learn more:
+
+- [@official@Chat Channels](https://docs.openclaw.ai/channels)
@@ -0,0 +1,8 @@
+# Context Window
+
+The context window is the amount of conversation history, instructions, and tool results the AI model can see at once when generating a response. Open Claw manages this carefully through a context engine and compaction system so long-running agents don't exceed the model's limits.
+
+Visit the following resources to learn more:
+
+- [@official@Context](https://docs.openclaw.ai/concepts/context)
+- [@official@Context Engine](https://docs.openclaw.ai/concepts/context-engine)
@@ -0,0 +1,8 @@
+# Dedicated Hardware
+
+Running Open Claw on dedicated hardware means using a physical device like a Raspberry Pi or Mac Mini that runs continuously in your home or office. This gives you full control and low ongoing costs with no monthly cloud fees.
+
+Visit the following resources to learn more:
+
+- [@official@Rasberry Pi](https://docs.openclaw.ai/install/raspberry-pi#raspberry-pi)
+- [@official@macOS VMs](https://docs.openclaw.ai/install/macos-vm#macos-vms)
@@ -0,0 +1,7 @@
+# DigitalOcean
+
+DigitalOcean is a cloud provider that offers simple, affordable virtual machines called Droplets. It is a popular choice for self-hosting Open Claw due to its straightforward pricing and easy setup process.
+
+Visit the following resources to learn more:
+
+- [@official@DigitalOcean Hosting](https://docs.openclaw.ai/install/digitalocean#digitalocean)
@@ -0,0 +1,7 @@
+# Discord
+
+Discord is a chat platform popular in gaming and developer communities. Open Claw connects to it via the Discord Bot API and Gateway, supporting servers, channels, and DMs.
+
+Visit the following resources to learn more:
+
+- [@official@Discord Channel](https://docs.openclaw.ai/channels/discord)
@@ -0,0 +1,7 @@
+# Docker / Isolated Install
+
+Docker lets you run Open Claw inside a container, an isolated environment that keeps it separate from the rest of your system. This makes installation cleaner, reduces conflicts with other software, and makes it easier to remove or update later.
+
+Visit the following resources to learn more:
+
+- [@official@Docker Install](https://docs.openclaw.ai/install/docker)
@@ -0,0 +1,7 @@
+# Gateway Settings
+
+Gateway settings control how the Open Claw server behaves, including the port it listens on, authentication tokens, and which interfaces it binds to. These settings are critical for both functionality and security.
+
+Visit the following resources to learn more:
+
+- [@official@Gateway Configuration](https://docs.openclaw.ai/gateway/configuration)
@@ -0,0 +1,7 @@
+# Gateway 
+
+The Gateway is the single always-on process that handles routing, the control plane, and all channel connections. It runs on a single multiplexed port that serves the WebSocket control and RPC interface, HTTP APIs, the Control UI, and hooks. By default, it binds to localhost and requires an auth token before accepting any connections.
+
+Visit the following resources to learn more:
+
+- [@official@Gateway Runbook](https://docs.openclaw.ai/gateway)
@@ -0,0 +1,7 @@
+# Gemini
+
+Gemini is Google's family of AI models. Open Claw supports Gemini as an alternative model provider, giving you access to Google's AI infrastructure for powering your agents.
+
+Visit the following resources to learn more:
+
+- [@article@Google (Gemini) Provider](https://docs.openclaw.ai/providers/google)
@@ -0,0 +1,7 @@
+# Hetzner
+
+Hetzner is a German cloud and hosting provider known for competitive pricing on VPS and dedicated servers, making it a cost-effective option for running Open Claw in Europe.
+
+Visit the following resources to learn more:
+
+- [@official@Hetzner Hosting](https://docs.openclaw.ai/install/hetzner)
@@ -0,0 +1,8 @@
+#How Open Claw Works
+
+Open Claw runs a single long-lived Gateway that owns all messaging surfaces and exposes a typed WebSocket API for control-plane clients like the macOS app, CLI, and web UI. When a message arrives, the Gateway routes it to the appropriate agent, which then runs through a full loop of context assembly, model inference, and tool execution before streaming a reply back.
+
+Visit the following resources to learn more:
+
+- [@official@OpenClaw Overview](https://docs.openclaw.ai/)
+- [@official@Gateway Architecture](https://docs.openclaw.ai/concepts/architecture)
@@ -0,0 +1,7 @@
+# iMessage
+
+iMessage is Apple's built-in messaging system. The recommended way to connect it to Open Claw is via BlueBubbles, a macOS server that provides a full-featured REST API for iMessage integration.
+
+Visit the following resources to learn more:
+
+- [@official@BlueBubbles Channel](https://docs.openclaw.ai/channels/bluebubbles)
@@ -0,0 +1,7 @@
+# Installation
+
+Installation covers the steps to get Open Claw onto your chosen environment. It requires a recent version of Node.js, an API key from your chosen model provider, and takes around five minutes. Always check the official documentation for the current Node.js version requirements before installing, as these may change between releases.
+
+Visit the following resources to learn more:
+
+- [@official@Installation](https://docs.openclaw.ai/install)
@@ -0,0 +1,7 @@
+# Introduction
+
+Open Claw is a self-hosted AI agent gateway that connects your messaging apps to AI models you control. You run a single Gateway process on your own machine or server, and it becomes the bridge between platforms like Telegram, WhatsApp, Discord, Slack, Signal, and more, and an always-available AI assistant. It is MIT-licensed, open source, and designed for developers and power users who want a personal AI they can message from anywhere without giving up control of their data.
+
+Visit the following resources to learn more:
+
+- [@official@Open Claw Docs](https://docs.openclaw.ai/)
@@ -0,0 +1,3 @@
+# Limitations
+
+Running Open Claw on dedicated hardware like a Raspberry Pi or Mac Mini gives you full control and no ongoing cloud fees, but the hardware itself is a constraint. Low-powered devices like a Raspberry Pi may struggle with memory-intensive tasks or multiple simultaneous agent sessions, and any hardware failure means your agent goes offline until you physically fix or replace the device. You are also still dependent on your home internet connection for external access, which may be unreliable, have changing IP addresses, or block incoming traffic by default.
@@ -0,0 +1,8 @@
+# Limitations
+
+Running Open Claw on a local machine means your agent is completely unreachable whenever your computer is off, asleep, or restarting. Most home internet connections also block unsolicited incoming traffic by default, which makes it difficult for external services to trigger your agent via webhooks. On top of that, your home IP address may change periodically depending on your internet provider, which can break any external connections you have configured. For anything beyond personal experimentation, a VPS or dedicated device is a more reliable choice.
+
+Visit the following resources to learn more:
+
+- [@official@Platforms](https://docs.openclaw.ai/platforms)
+- [@official@Remote Access](https://docs.openclaw.ai/gateway/remote)
@@ -0,0 +1,3 @@
+# Limitations
+
+Running Open Claw on a VPS or cloud server solves the uptime problem of a local machine but introduces its own constraints. You are paying a recurring monthly fee for the server, which adds up over time, especially if you need more resources to handle heavier workloads. Performance is also constrained by the size of the VPS you choose, and cheaper tiers may struggle with memory-intensive tasks or multiple simultaneous agent sessions. Finally, you are dependent on your cloud provider's availability, so any outages on their end will take your agent offline until they are resolved.
@@ -0,0 +1,7 @@
+# Local Machine
+
+Running Open Claw on your local machine means installing it directly on your personal computer. This is the quickest way to get started and is good for experimentation, though it comes with limitations around uptime and accessibility from outside your network.
+
+Visit the following resources to learn more:
+
+- [@official@Getting Started](https://docs.openclaw.ai/start/getting-started)
@@ -0,0 +1,7 @@
+# Mac Mini
+
+A Mac Mini is a compact desktop computer that works well as a home server for Open Claw. It is more powerful than a Raspberry Pi and runs macOS, which may simplify setup for Mac users.
+
+Visit the following resources to learn more:
+
+- [@official@macOS VMs Hosting](https://docs.openclaw.ai/install/macos-vm#macos-vms)
@@ -0,0 +1,8 @@
+# Memory System
+
+The memory system allows Open Claw agents to remember information across conversations. Instead of starting fresh every time, agents can store and retrieve facts, past interactions, or user preferences from structured memory files in the workspace. Open Claw also includes a compaction system that automatically summarizes older conversation history when a session grows too long, preserving the essential information while freeing up space for new exchanges.
+
+Visit the following resources to learn more:
+
+- [@official@Memory](https://docs.openclaw.ai/concepts/memory)
+- [@official@Compaction](https://docs.openclaw.ai/concepts/compaction)
@@ -0,0 +1,8 @@
+# MEMORY.md
+
+MEMORY.md is a persistent file where the agent stores important facts it has learned over time. It is regularly updated so the agent can recall relevant information in future conversations.
+
+Visit the following resources to learn more:
+
+- [@official@Memory Overview](https://docs.openclaw.ai/concepts/memory#memory-overview)
+- [@official@MEMORY.md - Your Long-Term Memory](https://docs.openclaw.ai/reference/templates/AGENTS#-memory-md-your-long-term-memory)
@@ -0,0 +1,7 @@
+# memory/YYYY-MM-DD.md
+
+These are dated memory log files that store a record of what happened on a specific day. They give the agent a chronological history that it can reference when needed, and are created automatically by the session-memory hook.
+
+Visit the following resources to learn more:
+
+- [@official@Memory Overview](https://docs.openclaw.ai/concepts/memory)
@@ -0,0 +1,7 @@
+# Ollama
+
+Ollama is a tool that lets you run open-source AI models locally on your own hardware, making it a natural fit for Open Claw setups where privacy, cost, or offline availability are a priority. It shines most in dedicated hardware setups like a Mac Mini or a capable home server, where you have enough RAM and processing power to run a model comfortably. However, low-powered devices like a Raspberry Pi will likely struggle with most models.
+
+Visit the following resources to learn more:
+
+- [@official@Ollama Provider](https://docs.openclaw.ai/providers/ollama)
@@ -0,0 +1,8 @@
+# Onboarding
+
+Onboarding is the guided first-run process that walks you through connecting your first AI model provider and communication channel so your agent is ready to receive and respond to messages. You can run it with `openclaw onboard`.
+
+Visit the following resources to learn more:
+
+- [@official@Onboarding Overview](https://docs.openclaw.ai/start/onboarding-overview)
+- [@official@Onboarding CLI](https://docs.openclaw.ai/start/wizard)
@@ -0,0 +1,8 @@
+# Open Claw vs Claude Code
+
+Claude Code is Anthropic's official CLI tool for AI-assisted coding, tightly integrated with Claude models and designed for developer workflows. Open Claw is a community-built alternative that runs independently, supports a wide range of AI providers beyond Anthropic, and extends beyond coding to general agent automation across messaging platforms.
+
+Visit the following resources to learn more:
+
+- [@official@Open Claw vs Claude Code](https://docs.openclaw.ai/help/faq#what-are-the-advantages-vs-claude-code-for-web-development)
+- [@video@OpenClaw vs Claude explained simply in 8 minutes](https://www.youtube.com/watch?v=b773XfpS7fw)
@@ -0,0 +1,7 @@
+# OpenAI
+
+OpenAI provides access to models like GPT-4o. Open Claw can use these models as the AI brain behind your agent by configuring your OpenAI API key in the model provider settings.
+
+Visit the following resources to learn more:
+
+- [@official@OpenAI Provider](https://docs.openclaw.ai/providers/openai)
@@ -0,0 +1,7 @@
+# Other Workspace Files
+
+Open Claw recognizes several other special markdown files that are automatically injected into the agent's context at startup. BOOT.md contains instructions that the agent runs once when the Gateway starts. TOOLS.md describes the tools available to the agent and how they should be used. IDENTITY.md is an alternative or complement to SOUL.md for defining the agent's persona. BOOTSTRAP.md is a general-purpose file for injecting additional context into every session. On top of these recognized filenames, you can also add any other markdown files to your workspace, such as project notes, reference documents, or custom instructions for specific tasks.
+
+Visit the following resources to learn more:
+
+- [@official@Agent Workspace](https://docs.openclaw.ai/concepts/agent-workspace)
@@ -0,0 +1,7 @@
+# Proactive Core
+
+The proactive core is what allows Open Claw agents to act on their own initiative rather than just responding to messages. Using heartbeats, cron jobs, and standing orders, the agent can run tasks on a schedule or trigger automatically based on conditions you define.
+
+Visit the following resources to learn more:
+
+- [@official@Automation & Tasks](https://docs.openclaw.ai/automation)
@@ -0,0 +1,7 @@
+# Railway
+
+Railway is a modern cloud deployment platform that simplifies hosting by handling much of the infrastructure configuration for you. It is a good option if you want a fast, low-friction cloud deployment.
+
+Visit the following resources to learn more:
+
+- [@official@Railway Hosting](https://docs.openclaw.ai/install/railway)
@@ -0,0 +1,7 @@
+# Raspberry Pi
+
+A Raspberry Pi is a small, low-cost single-board computer that can run Open Claw 24/7 with minimal power consumption. It is a popular self-hosting choice for hobbyists who want a home server.
+
+Visit the following resources to learn more:
+
+- [@official@Raspberry Pi Hosting](https://docs.openclaw.ai/install/raspberry-pi#raspberry-pi)
@@ -0,0 +1,3 @@
+# Risks
+
+Running Open Claw on a VPS exposes your Gateway to the public internet, which makes it a potential target if not properly secured. A misconfigured auth token, an exposed port, or a weak allowlist can give unauthorized users access to an agent that has tool access to your files, commands, and API keys. Since you are storing API credentials on a remote machine you do not physically control, a compromised server means those keys need to be rotated immediately.
@@ -0,0 +1,7 @@
+# Risks
+
+Running Open Claw locally or on shared hardware introduces certain risks like accidental exposure of API keys, lack of encryption, or the agent having access to sensitive local files. Understanding these helps you make informed decisions about your setup.
+
+Visit the following resources to learn more:
+
+- [@official@Security](https://docs.openclaw.ai/gateway/security)
@@ -0,0 +1,3 @@
+# Risks
+
+Dedicated hardware sitting in your home or office is physically accessible, which means anyone with access to the device could potentially tamper with it or extract credentials stored on it. If the device is connected to your home network without proper isolation, a compromised agent could have access to other devices on the same network. Power outages, hardware failures, and accidental resets can also cause data loss if your workspace and memory files are not backed up regularly.
@@ -0,0 +1,3 @@
+# Security Best Practices
+
+Treat dedicated hardware the same way you would a VPS: Bind the Gateway to localhost, set a strong auth token, and use Tailscale or an SSH tunnel for any remote access rather than exposing ports directly. Run Open Claw as a non-root user, keep the OS and Open Claw itself updated, and store all API keys in environment variables rather than config files. Keep the device physically secure, run `openclaw security audit --deep` after any configuration change, and make regular backups of your workspace and memory files so you can recover quickly if the hardware fails.
@@ -0,0 +1,8 @@
+# Security Best Practices
+
+When running Open Claw locally, bind the Gateway to localhost only so it is never exposed directly to the internet, set a strong, randomly generated auth token, and never hardcode API keys in config files — use environment variables instead. Run the process as a non-root user, keep your sender allowlist minimal, and enable device pairing so unknown devices cannot connect. Be cautious about prompt injection since the agent can read external content like emails and web pages. Run `openclaw security audit --deep` after any configuration change, keep Open Claw updated regularly, and rotate all credentials immediately if you suspect a breach.
+
+Visit the following resources to learn more:
+
+- [@official@Security](https://docs.openclaw.ai/gateway/security)
+- [@official@Threat Model](https://docs.openclaw.ai/security/THREAT-MODEL-ATLAS)
@@ -0,0 +1,9 @@
+# Security Best Practices
+
+On a VPS, never bind the Gateway to 0.0.0.0 — bind it to localhost and use a reverse proxy or Tailscale to control external access. Set a strong randomly generated auth token, use environment variables for all API keys, and run Open Claw as a non-root user. Keep your sender allowlist tight, enable device pairing, and start the agent in read-only mode before widening tool permissions deliberately. Keep both Open Claw and the OS updated regularly, run `openclaw security audit --deep` after any configuration change, and rotate all credentials immediately if anything looks suspicious.
+
+Visit the following resources to learn more:
+
+- [@official@Security](https://docs.openclaw.ai/gateway/security)
+- [@official@Tailscale](https://docs.openclaw.ai/gateway/tailscale)
+- [@official@Thread Model](https://docs.openclaw.ai/security/THREAT-MODEL-ATLAS)
@@ -0,0 +1,8 @@
+# Setting up Open Claw
+
+Setting up Open Claw involves installing the package via npm, running the onboarding wizard to connect your AI model provider and first communication channel, and optionally installing the Gateway as a background daemon so it starts automatically.
+
+Visit the following resources to learn more:
+
+- [@official@Getting Started](https://docs.openclaw.ai/start/getting-started)
+- [@official@Onboarding Overview](https://docs.openclaw.ai/start/onboarding-overview)
@@ -0,0 +1,7 @@
+# Signal
+
+Signal is an end-to-end encrypted messaging app. Open Claw connects to it via signal-cli, making it a strong option for users who prioritize privacy in their communications with the agent.
+
+Visit the following resources to learn more:
+
+- [@official@Signal Channel](https://docs.openclaw.ai/channels/signal)
@@ -0,0 +1,8 @@
+# Skills
+
+OpenClaw uses AgentSkills-compatible skill folders to teach the agent how to use tools. A skill is a markdown file injected into the system prompt that gives the agent context, constraints, and step-by-step guidance for using tools effectively. Skills live in your workspace, in shared folders, or ship inside plugins.
+
+Visit the following resources to learn more:
+
+- [@official@Skills](https://docs.openclaw.ai/tools/skills)
+- [@official@Agent Skills](https://agentskills.io/home)
@@ -0,0 +1,7 @@
+# Slack
+
+Slack is a team communication platform. Open Claw connects to it via the Bolt SDK as a workspace app, making it useful for team-based automation and internal tooling.
+
+Visit the following resources to learn more:
+
+- [@official@Slack Channel](https://docs.openclaw.ai/channels/slack)
@@ -0,0 +1,8 @@
+# SOUL.md
+
+SOUL.md is the file where you define the agent's personality, tone, and core behavioral guidelines. Think of it as the agent's character sheet. It shapes how it communicates and makes decisions across all conversations.
+
+Visit the following resources to learn more:
+
+- [@official@SOUL.md Personality Guide](https://docs.openclaw.ai/concepts/soul#soul-md-personality-guide)
+- [@official@SOUL.md Template](https://docs.openclaw.ai/reference/templates/SOUL#soul-md-template)
@@ -0,0 +1,7 @@
+# Telegram
+
+Telegram is a messaging app that supports bots via a straightforward API. It is one of the easiest channels to connect to Open Claw and is recommended as the first channel for new users.
+
+Visit the following resources to learn more:
+
+- [@official@Telegram Channel](https://docs.openclaw.ai/channels/telegram)
@@ -0,0 +1,7 @@
+# Use Cases
+
+Open Claw can be used for a wide range of tasks: you can connect it to your messaging apps to have it read and respond to messages on your behalf, set up scheduled jobs using cron and heartbeats to run recurring tasks like daily summaries or file cleanups without any human input, process incoming data from webhooks by extracting and acting on information automatically, manage and update files and documentation in your workspace, chain multiple actions together in a single agent loop to complete multi-step workflows from start to finish, and even run several specialized agents in parallel with routing rules and shared memory so each one handles a different domain while staying coordinated with the others.
+
+Visit the following resources to learn more:
+
+- [@official@Showcase - OpenClaw](https://docs.openclaw.ai/start/showcase)
@@ -0,0 +1,7 @@
+# USER.md
+
+USER.md contains information about you: your preferences, context, and anything you want the agent to know about you by default. The agent reads this to personalize its responses.
+
+Visit the following resources to learn more:
+
+- [@official@USER Template](https://docs.openclaw.ai/reference/templates/USER#user-md-about-your-human)
@@ -0,0 +1,7 @@
+# VPS/Cloud
+
+Running Open Claw on a VPS or cloud platform gives you a machine that is always online and accessible from anywhere. This is the most common production setup and is recommended over running on a local machine for anything beyond experimentation.
+
+Visit the following resources to learn more:
+
+- [@official@Remote Access](https://docs.openclaw.ai/gateway/remote#macos-persistent-ssh-tunnel-via-launchagent)
@@ -0,0 +1,7 @@
+# WhatsApp
+
+WhatsApp is the most popular channel in Open Claw. It connects via the Baileys library and requires a QR code pairing step to link your account to the Gateway.
+
+Visit the following resources to learn more:
+
+- [@official@WhatsApp Channel](https://docs.openclaw.ai/channels/whatsapp)
@@ -0,0 +1,7 @@
+# Workspace Settings
+
+Workspace settings define the environment your agent operates in, including its identity, behavioral guidelines, and what it knows about you. These are stored in a set of markdown configuration files in your project directory.
+
+Visit the following resources to learn more:
+
+- [@official@Agent Workspace](https://docs.openclaw.ai/concepts/agent-workspace)