# How to Set Up a Local Development Workflow for OpenClaw Agents A solid local development environment helps you build and debug OpenClaw agents before deployment. This guide covers the full setup, from Docker configuration to installing skills via ClawHub, and shows you how to mock external APIs for safe testing. Source: https://fast.io/resources/openclaw-local-development/ Last reviewed: 2026-02-17 ## Prerequisites for a Local OpenClaw Environment OpenClaw runs locally, so the execution environment lives on your machine. This gives you speed and privacy, but you need a specific foundation. Before writing your first skill, you need a few core components. **Docker** is required because OpenClaw executes agent actions within sandboxed containers. This prevents accidental system damage. Isolation matters when testing new skills that might delete files or execute shell commands. Make sure Docker Desktop is running before starting the OpenClaw gateway. You also need **Node.js 22 or higher**. The OpenClaw Gateway and CLI tools rely on modern Node.js features. Once these are ready, initialize your environment: ```bash # Install the OpenClaw CLI globally npm install -g openclaw-cli # Start the onboarding wizard openclaw onboard ``` The onboarding process sets up your primary agent profile, configures your LLM provider (Anthropic or OpenAI work best for development), and creates the local directory structure for your agent's memory and skills. ## Managing Skills with ClawHub Skills are the functions your agent uses to interact with the world. You can write custom skills in TypeScript or connect to external MCP servers. For file management and persistent storage, connect OpenClaw to Fastio's remote MCP server at `https://mcp.fast.io/mcp` using a scoped API key. Fastio requires no local skill installation, giving your agent access to a consolidated MCP toolset to read, write, search, and share files in the cloud. These tools handle authentication and cloud file operations out of the box, eliminating boilerplate code for storage and permissions. **Pro Tip**: Always inspect your agent's tool definitions and schemas before running local workflows. Understanding the input parameters and response shapes helps you debug why an agent might misuse a tool during testing. ## Mocking External APIs for Safe Testing Testing interactions with live external services is hard. You don't want your agent sending real emails to clients or deleting production database records while you debug logic. Mocking is essential for a stable workflow. Instead of connecting to live APIs immediately, point your local environment to mock endpoints. For file operations, use Fastio's **realtime activity feed or WebSocket events feed** to react to external triggers. Create a "Test" workspace in Fastio and poll the activity feed or listen on the WebSocket feed whenever a file is uploaded. This lets you trigger your agent's file processing logic by dropping a dummy file into the folder, without needing a full production pipeline. If your agent uses the Fastio MCP server, you can toggle **Intelligence** on and off for your test workspace. This helps you verify how your agent handles both raw file access (Intelligence OFF) and semantic search results once Intelligence is enabled without changing your code. ## Debugging Agent Memory and State OpenClaw stores conversation history and long-term memory as plain Markdown and YAML files on your local disk. This makes debugging easier than cloud-only agents where state is a black box. If your agent gets stuck in a loop or hallucinates a fact, check the `memory/` directory in your OpenClaw installation. You can edit these files to reset the agent's state or inject context for a test case. For example, if you are testing a "project handoff" workflow, you can manually insert a memory entry stating that "Project X is complete" and see if the agent suggests transferring workspace ownership to the client. Direct manipulation of memory is a powerful way to test edge cases. ## Using Persistent Cloud Storage Local development is great, but your agent needs a place to store artifacts that persist beyond your local machine. Fastio provides a 14-day **Business Trial** (credit card required) that serves as your agent's persistent storage backend. By mounting a Fastio workspace, your local agent gains: * **Persistence**: Files survive even if you wipe your local Docker container. * **Search**: Built-in RAG once Intelligence is enabled on the workspace means your agent can query documents with citations without loading entire files into context. * **Collaboration**: You can log in to the Fastio web UI to inspect exactly what files your agent has created or modified. This mix of local execution and cloud storage combines the speed of local dev loops with the reliability of cloud persistence. ### Handling Authentication Locally Avoid hardcoding API keys in your agent's config files. Use environment variables or OpenClaw's built-in secrets management to inject keys for Fastio, OpenAI, and other services at runtime. This prevents accidental commits of secrets to your git repository. ## Frequently asked questions ### How do I update OpenClaw skills? You can update skills using the ClawHub CLI. Run `clawhub update ` to fetch the latest version of a specific skill, or `clawhub update --all` to update all installed skills. Always check the changelog for breaking changes before updating in a production environment. ### Can I run OpenClaw without Docker? Technically yes, but it is highly discouraged. Running agents directly on your host machine exposes your system to risks if the agent executes a destructive command. Docker provides a necessary safety layer for local development. ### How do I debug OpenClaw network requests? Since OpenClaw runs locally, you can inspect network traffic using standard tools. The Gateway process logs API calls to the console. For more detailed inspection, you can route traffic through a proxy or use the verbose logging mode in the CLI. ### What is the cost of Fastio for agent development? Fastio offers a 14-day Business Trial (credit card required), and plans scale with usage-based credits from Starter ($29/mo, 1 TB) to Business ($99/mo, 10 TB) and Growth ($299/mo, 50 TB). See /pricing/. ## About Fast.io Fast.io provides shared workspaces where people and AI agents work on the same files, with built-in semantic search and citation-backed chat over what they hold. Agents reach it through a remote MCP server at https://mcp.fast.io/mcp, a REST API at https://api.fast.io/current/, and a command line client published on npm as @vividengine/fastio-cli.