openclaw-configEdit and validate OpenClaw Gateway config (openclaw.json / JSON5). Use when adding/changing config keys (gateway.*, agents.*, models.*, channels.*, tools.*, skills.*, plugins.*, $include) or diagnosing openclaw doctor/config validation errors, to avoid schema mismatches that prevent the Gateway from starting or weaken security policies.
Install via ClawdBot CLI:
clawdbot install caopulan/openclaw-configSafely edit ~/.openclaw/openclaw.json (or the path set by OPENCLAW_CONFIG_PATH) using a schema-first workflow. Validate before and after changes to avoid invalid keys/types that can break startup or change security behavior.
OPENCLAW_CONFIG_PATH > OPENCLAW_STATE_DIR/openclaw.json > ~/.openclaw/openclaw.jsonopenclaw gateway call config.schema --params '{}' to fetch a JSON Schema matching the running version.openclaw/openclaw source-of-truth, primarily:src/config/zod-schema.ts (OpenClawSchema root keys like gateway/skills/plugins)src/config/zod-schema.*.ts (submodules: channels/providers/models/agents/tools)docs/gateway/configuration.md (repo docs + examples)openclaw config get|set|unset (dot path or bracket notation).config.patch (merge patch) or config.apply (replaces the entire config; use carefully).$include (see below).openclaw doctor, then fix issues using the reported path + message.openclaw doctor --fix/--yes without explicit user consent (it writes to config/state files)..strict()): unknown keys usually fail validation and the Gateway will refuse to start.channels is .passthrough(): extension channels (matrix/zalo/nostr, etc.) can add custom keys, but most provider configs remain strict.env is .catchall(z.string()): you can put string env vars directly under env, and you can also use env.vars.openclaw.json.$include is resolved before schema validation and lets you split config across JSON5 files:
"$include": "./base.json5" or "$include": ["./a.json5", "./b.json5"]$include, sibling keys override included values.openclaw config set agents.defaults.workspace '"~/.openclaw/workspace"' --json
openclaw doctor
openclaw config set gateway.port 18789 --json
openclaw doctor
// ~/.openclaw/openclaw.json
{
"$include": ["./gateway.json5", "./channels/telegram.json5"],
}
Schema constraint: whendmPolicy="open",allowFrommust include"*".
openclaw config set channels.telegram.dmPolicy '"open"' --json
openclaw config set channels.telegram.allowFrom '["*"]' --json
openclaw doctor
# Option A: write to config
openclaw config set channels.discord.token '"YOUR_DISCORD_BOT_TOKEN"' --json
# Option B: env var fallback (still recommend a channels.discord section exists)
# export DISCORD_BOT_TOKEN="..."
openclaw doctor
openclaw config set tools.web.search.enabled true --json
openclaw config set tools.web.search.provider '"brave"' --json
# Recommended: provide the key via env var (or write tools.web.search.apiKey)
# export BRAVE_API_KEY="..."
openclaw doctor
Load these when you need a field index or source locations:
references/openclaw-config-fields.md (root key index + key field lists with sources)references/schema-sources.md (how to locate schema + constraints in openclaw repo)scripts/openclaw-config-check.sh (print config path + run doctor)Generated Mar 1, 2026
A startup deploys an AI chatbot across multiple messaging channels like Telegram and Discord, requiring secure configuration of API keys and channel-specific policies. This skill ensures proper setup of channels, agents, and tools to avoid startup failures and maintain security.
A large corporation integrates OpenClaw Gateway into its IT infrastructure, needing to manage complex configurations with modular includes for different departments. The skill helps validate schema changes and split configs to prevent downtime and enforce strict security policies.
A development team builds custom AI agents and tools, using this skill to edit and validate config files for testing and production environments. It aids in setting up workspaces, models, and plugins while avoiding schema mismatches that could break deployments.
A university research lab configures OpenClaw for experiments with various AI models and channels, requiring frequent updates to config keys. The skill provides a safe workflow to apply changes, validate with doctor, and use includes for modular experiment setups.
A customer service company automates support via AI agents on platforms like Discord and Telegram, using this skill to configure DM policies and tool integrations. It ensures secure token management and validation to maintain operational reliability and data protection.
Offer a managed OpenClaw Gateway service with config management as a core feature, charging monthly fees for secure, validated deployments. Revenue comes from tiered plans based on usage, support, and customization options for businesses.
Provide expert consulting to help clients configure and optimize their OpenClaw setups, focusing on schema validation and modular configs to reduce errors. Revenue is generated through project-based fees and ongoing maintenance contracts.
Develop training courses and certifications for using OpenClaw Config skill effectively, targeting developers and IT professionals. Revenue streams include course fees, certification exams, and corporate training packages.
💬 Integration Tip
Always run openclaw doctor after config changes to catch validation errors early, and use $include for modular setups to simplify management and reduce risks.
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞
Use the ClawdHub CLI to search, install, update, and publish agent skills from clawdhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawdhub CLI.
Clawdbot documentation expert with decision tree navigation, search scripts, doc fetching, version tracking, and config snippets for all Clawdbot features
Interact with Moltbook social network for AI agents. Post, reply, browse, and analyze engagement. Use when the user wants to engage with Moltbook, check their feed, reply to posts, or track their activity on the agent social network.
OpenClaw CLI wrapper — gateway, channels, models, agents, nodes, browser, memory, security, automation.
MoltGuard — runtime security plugin for OpenClaw agents by OpenGuardrails. Helps users install, register, activate, and check the status of MoltGuard. Use wh...