--- title: Charmhub | Deploy OpenClaw using Charmhub - The Open Operator Collection description: Deploy the latest version of OpenClaw on any cloud. url: https://charmhub.io/openclaw/configurations --- # OpenClaw [Shih-Yuan Lee (FourDollars)](https://charmhub.io/publisher/fourdollars "View all packages from Shih-Yuan Lee (FourDollars)") * [Shih-Yuan Lee (FourDollars)](https://charmhub.io/publisher/fourdollars "View all packages from Shih-Yuan Lee (FourDollars)") Platform: 24.04 stable 37 ``` juju deploy openclaw ``` [Learn to deploy on juju >](https://juju.is/docs/juju/manage-applications) * [ai-api-key](https://charmhub.io/openclaw/configurations#ai-api-key) * [ai-base-url](https://charmhub.io/openclaw/configurations#ai-base-url) * [ai-context-window](https://charmhub.io/openclaw/configurations#ai-context-window) * [ai-model](https://charmhub.io/openclaw/configurations#ai-model) * [ai-provider](https://charmhub.io/openclaw/configurations#ai-provider) * [ai-providers-order](https://charmhub.io/openclaw/configurations#ai-providers-order) * [ai0-api-key](https://charmhub.io/openclaw/configurations#ai0-api-key) * [ai0-base-url](https://charmhub.io/openclaw/configurations#ai0-base-url) * [ai0-context-window](https://charmhub.io/openclaw/configurations#ai0-context-window) * [ai0-model](https://charmhub.io/openclaw/configurations#ai0-model) * [ai0-provider](https://charmhub.io/openclaw/configurations#ai0-provider) * [ai1-api-key](https://charmhub.io/openclaw/configurations#ai1-api-key) * [ai1-base-url](https://charmhub.io/openclaw/configurations#ai1-base-url) * [ai1-context-window](https://charmhub.io/openclaw/configurations#ai1-context-window) * [ai1-model](https://charmhub.io/openclaw/configurations#ai1-model) * [ai1-provider](https://charmhub.io/openclaw/configurations#ai1-provider) * [ai2-api-key](https://charmhub.io/openclaw/configurations#ai2-api-key) * [ai2-base-url](https://charmhub.io/openclaw/configurations#ai2-base-url) * [ai2-context-window](https://charmhub.io/openclaw/configurations#ai2-context-window) * [ai2-model](https://charmhub.io/openclaw/configurations#ai2-model) * [ai2-provider](https://charmhub.io/openclaw/configurations#ai2-provider) * [ai3-api-key](https://charmhub.io/openclaw/configurations#ai3-api-key) * [ai3-base-url](https://charmhub.io/openclaw/configurations#ai3-base-url) * [ai3-context-window](https://charmhub.io/openclaw/configurations#ai3-context-window) * [ai3-model](https://charmhub.io/openclaw/configurations#ai3-model) * [ai3-provider](https://charmhub.io/openclaw/configurations#ai3-provider) * [ai4-api-key](https://charmhub.io/openclaw/configurations#ai4-api-key) * [ai4-base-url](https://charmhub.io/openclaw/configurations#ai4-base-url) * [ai4-context-window](https://charmhub.io/openclaw/configurations#ai4-context-window) * [ai4-model](https://charmhub.io/openclaw/configurations#ai4-model) * [ai4-provider](https://charmhub.io/openclaw/configurations#ai4-provider) * [ai5-api-key](https://charmhub.io/openclaw/configurations#ai5-api-key) * [ai5-base-url](https://charmhub.io/openclaw/configurations#ai5-base-url) * [ai5-context-window](https://charmhub.io/openclaw/configurations#ai5-context-window) * [ai5-model](https://charmhub.io/openclaw/configurations#ai5-model) * [ai5-provider](https://charmhub.io/openclaw/configurations#ai5-provider) * [ai6-api-key](https://charmhub.io/openclaw/configurations#ai6-api-key) * [ai6-base-url](https://charmhub.io/openclaw/configurations#ai6-base-url) * [ai6-context-window](https://charmhub.io/openclaw/configurations#ai6-context-window) * [ai6-model](https://charmhub.io/openclaw/configurations#ai6-model) * [ai6-provider](https://charmhub.io/openclaw/configurations#ai6-provider) * [ai7-api-key](https://charmhub.io/openclaw/configurations#ai7-api-key) * [ai7-base-url](https://charmhub.io/openclaw/configurations#ai7-base-url) * [ai7-context-window](https://charmhub.io/openclaw/configurations#ai7-context-window) * [ai7-model](https://charmhub.io/openclaw/configurations#ai7-model) * [ai7-provider](https://charmhub.io/openclaw/configurations#ai7-provider) * [ai8-api-key](https://charmhub.io/openclaw/configurations#ai8-api-key) * [ai8-base-url](https://charmhub.io/openclaw/configurations#ai8-base-url) * [ai8-context-window](https://charmhub.io/openclaw/configurations#ai8-context-window) * [ai8-model](https://charmhub.io/openclaw/configurations#ai8-model) * [ai8-provider](https://charmhub.io/openclaw/configurations#ai8-provider) * [ai9-api-key](https://charmhub.io/openclaw/configurations#ai9-api-key) * [ai9-base-url](https://charmhub.io/openclaw/configurations#ai9-base-url) * [ai9-context-window](https://charmhub.io/openclaw/configurations#ai9-context-window) * [ai9-model](https://charmhub.io/openclaw/configurations#ai9-model) * [ai9-provider](https://charmhub.io/openclaw/configurations#ai9-provider) * [auto-update](https://charmhub.io/openclaw/configurations#auto-update) * [control-ui-allowed-origins](https://charmhub.io/openclaw/configurations#control-ui-allowed-origins) * [discord-bot-token](https://charmhub.io/openclaw/configurations#discord-bot-token) * [dm-policy](https://charmhub.io/openclaw/configurations#dm-policy) * [dm-scope](https://charmhub.io/openclaw/configurations#dm-scope) * [gateway-bind](https://charmhub.io/openclaw/configurations#gateway-bind) * [gateway-port](https://charmhub.io/openclaw/configurations#gateway-port) * [install-method](https://charmhub.io/openclaw/configurations#install-method) * [install-pkgs](https://charmhub.io/openclaw/configurations#install-pkgs) * [line-channel-access-token](https://charmhub.io/openclaw/configurations#line-channel-access-token) * [line-channel-secret](https://charmhub.io/openclaw/configurations#line-channel-secret) * [log-level](https://charmhub.io/openclaw/configurations#log-level) * [manual](https://charmhub.io/openclaw/configurations#manual) * [node-version](https://charmhub.io/openclaw/configurations#node-version) * [sandbox-mode](https://charmhub.io/openclaw/configurations#sandbox-mode) * [slack-app-token](https://charmhub.io/openclaw/configurations#slack-app-token) * [slack-bot-token](https://charmhub.io/openclaw/configurations#slack-bot-token) * [telegram-bot-token](https://charmhub.io/openclaw/configurations#telegram-bot-token) * [version](https://charmhub.io/openclaw/configurations#version) [Learn about configurations >](https://juju.is/docs/juju/configuration#heading--application-configuration) * ai-api-key | string API key for the selected AI provider. Required for most providers: + anthropic: Anthropic API key + openai: OpenAI API key + google: Google Gemini API key + opencode: OpenCode API key + github-copilot: GitHub personal access token + openrouter: OpenRouter API key + xai: xAI API key + groq: Groq API key + cerebras: Cerebras API key + mistral: Mistral API key + zai: Z.AI API key + vercel-ai-gateway: Vercel AI Gateway API key Not required for: ollama (local), bedrock (AWS credentials), openai-codex (OAuth) Note: API keys are stored securely in OpenClaw's sqlite auth store (agent/openclaw-agent.sqlite), not in environment variables. * ai-base-url | string Custom API base URL for OpenAI-compatible providers. Use this to connect to local AI services like LM Studio, vLLM, FastChat, etc. Examples: + LM Studio: http://localhost:1234/v1 + vLLM: http://localhost:8000/v1 + Text Generation WebUI: http://localhost:5000/v1 Leave empty to use default provider endpoints. * ai-context-window | int Override the context window size (in tokens) for the primary AI model. Set to a positive integer (e.g. 8192) to cap memory usage on low-VRAM GPUs. Use case: When using Ollama via the openai provider (ai-provider=openai, ai-base-url=http://.../v1), OpenClaw cannot auto-discover the model's context window. Setting this prevents OpenClaw from defaulting to a huge context that causes out-of-memory crashes on constrained hardware. Only effective when ai-provider is NOT 'ollama' (i.e. OpenAI-compatible mode). In native ollama mode, OpenClaw auto-discovers and enforces the model's own context window, so this setting has no effect. 0 = use OpenClaw's default (no override). * ai-model | string AI model(s) to use. Supports: + Single model: claude-opus-4-5 + Multiple models (comma-separated): gemini-3-flash-preview,gemini-3-pro-preview,gemini-2.5-pro When multiple models are provided: + First model becomes the primary (system default) + Remaining models are added as fallbacks + All models use the configured ai-provider Models are stored as provider/model format (e.g., anthropic/claude-opus-4-5). For models from different providers, use separate slots (ai0-provider/ai0-model, etc.) with each provider's API key. Examples: + Single: claude-opus-4-5 + Multiple same provider: gpt-4,gpt-3.5-turbo,gpt-4o-mini + GitHub Copilot aggregator: gemini-3-flash-preview,claude-haiku-4.5,gpt-4 * ai-provider | string Primary AI model provider. Supported providers: + anthropic: Anthropic Claude models + openai: OpenAI GPT models + openai-codex: OpenAI Codex (requires OAuth) + google: Google Gemini models + opencode: OpenCode Zen models + github-copilot: GitHub Copilot/Models API + openrouter: OpenRouter aggregator + xai: xAI models + groq: Groq models + cerebras: Cerebras models + mistral: Mistral AI models + zai: Z.AI (GLM) models + vercel-ai-gateway: Vercel AI Gateway + ollama: Local Ollama models (no API key needed) + bedrock: AWS Bedrock (uses AWS credentials) * ai-providers-order | string Comma-separated list of AI model slots to prioritize (e.g. "3,2,1,"). Empty string represents the primary ai-model slot. By default (empty), the order is: ai-model, ai0-model, ai1-model, ..., ai9-model. Slots not mentioned in the list will follow the natural order after the prioritized slots. Example: "3,2,1," will result in the following order: ai3-model, ai2-model, ai1-model, ai-model, ai0-model, ai4-model, ai5-model, ..., ai9-model. * ai0-api-key | string API key for AI model slot 0 * ai0-base-url | string Custom API base URL for AI model slot 0 (for OpenAI-compatible local services) * ai0-context-window | int Override the context window size (in tokens) for AI model slot 0. See ai-context-window for full details. 0 = no override. * ai0-model | string AI model(s) for slot 0. Supports single or comma-separated models. All models in this slot use ai0-provider. Example: gpt-4,gpt-3.5-turbo,gpt-4o-mini * ai0-provider | string AI provider for model slot 0. See ai-provider for supported providers. * ai1-api-key | string API key for AI model slot 1 * ai1-base-url | string Custom API base URL for AI model slot 1 (for OpenAI-compatible local services) * ai1-context-window | int Override the context window size (in tokens) for AI model slot 1. See ai-context-window for full details. 0 = no override. * ai1-model | string AI model(s) for slot 1 (supports comma-separated) * ai1-provider | string AI provider for model slot 1. See ai-provider for supported providers. * ai2-api-key | string API key for AI model slot 2 * ai2-base-url | string Custom API base URL for AI model slot 2 (for OpenAI-compatible local services) * ai2-context-window | int Override the context window size (in tokens) for AI model slot 2. See ai-context-window for full details. 0 = no override. * ai2-model | string AI model(s) for slot 2 (supports comma-separated) * ai2-provider | string AI provider for model slot 2. See ai-provider for supported providers. * ai3-api-key | string API key for AI model slot 3 * ai3-base-url | string Custom API base URL for AI model slot 3 (for OpenAI-compatible local services) * ai3-context-window | int Override the context window size (in tokens) for AI model slot 3. See ai-context-window for full details. 0 = no override. * ai3-model | string AI model(s) for slot 3 (supports comma-separated) * ai3-provider | string AI provider for model slot 3. See ai-provider for supported providers. * ai4-api-key | string API key for AI model slot 4 * ai4-base-url | string Custom API base URL for AI model slot 4 (for OpenAI-compatible local services) * ai4-context-window | int Override the context window size (in tokens) for AI model slot 4. See ai-context-window for full details. 0 = no override. * ai4-model | string AI model(s) for slot 4 (supports comma-separated) * ai4-provider | string AI provider for model slot 4. See ai-provider for supported providers. * ai5-api-key | string API key for AI model slot 5 * ai5-base-url | string Custom API base URL for AI model slot 5 (for OpenAI-compatible local services) * ai5-context-window | int Override the context window size (in tokens) for AI model slot 5. See ai-context-window for full details. 0 = no override. * ai5-model | string AI model(s) for slot 5 (supports comma-separated) * ai5-provider | string AI provider for model slot 5. See ai-provider for supported providers. * ai6-api-key | string API key for AI model slot 6 * ai6-base-url | string Custom API base URL for AI model slot 6 (for OpenAI-compatible local services) * ai6-context-window | int Override the context window size (in tokens) for AI model slot 6. See ai-context-window for full details. 0 = no override. * ai6-model | string AI model(s) for slot 6 (supports comma-separated) * ai6-provider | string AI provider for model slot 6. See ai-provider for supported providers. * ai7-api-key | string API key for AI model slot 7 * ai7-base-url | string Custom API base URL for AI model slot 7 (for OpenAI-compatible local services) * ai7-context-window | int Override the context window size (in tokens) for AI model slot 7. See ai-context-window for full details. 0 = no override. * ai7-model | string AI model(s) for slot 7 (supports comma-separated) * ai7-provider | string AI provider for model slot 7. See ai-provider for supported providers. * ai8-api-key | string API key for AI model slot 8 * ai8-base-url | string Custom API base URL for AI model slot 8 (for OpenAI-compatible local services) * ai8-context-window | int Override the context window size (in tokens) for AI model slot 8. See ai-context-window for full details. 0 = no override. * ai8-model | string AI model(s) for slot 8 (supports comma-separated) * ai8-provider | string AI provider for model slot 8. See ai-provider for supported providers. * ai9-api-key | string API key for AI model slot 9 * ai9-base-url | string Custom API base URL for AI model slot 9 (for OpenAI-compatible local services) * ai9-context-window | int Override the context window size (in tokens) for AI model slot 9. See ai-context-window for full details. 0 = no override. * ai9-model | string AI model(s) for slot 9 (supports comma-separated) * ai9-provider | string AI provider for model slot 9. See ai-provider for supported providers. * auto-update | boolean Automatically update OpenClaw to latest stable version on upgrade-charm * control-ui-allowed-origins | string Comma-separated list of full origins allowed to access the OpenClaw Control UI from non-loopback addresses (e.g. "http://10.0.0.5:18789,https://openclaw.example.com"). Each entry must be a complete origin: scheme + host + optional port, no trailing slash. Required when gateway-bind is not loopback and you want to use the Control UI remotely. Loopback origins (127.0.0.1, localhost) are always auto-approved and do not need to be listed. Maps to gateway.controlUi.allowedOrigins in openclaw.json. * discord-bot-token | string Discord bot token from Discord Developer Portal. Leave empty to disable Discord messaging. * dm-policy | string Default: pairing DM access policy: 'pairing' (require pairing code), 'open' (auto-respond), or 'closed' (reject all DMs) * dm-scope | string Default: main DM session scope for isolating direct message conversations: + 'main' (default): All DMs share the main session for continuity across devices/channels + 'per-peer': Isolate sessions by sender ID across channels + 'per-channel-peer': Isolate by channel + sender (recommended for multi-user inboxes) + 'per-account-channel-peer': Isolate by account + channel + sender (recommended for multi-account inboxes) Security Warning: If your agent receives DMs from multiple people, use 'per-channel-peer' or 'per-account-channel-peer' to prevent conversation context leakage between users. * gateway-bind | string Default: loopback Gateway bind mode: 'loopback' (127.0.0.1 only), 'lan' (all interfaces), or specific IP address. IMPORTANT: Multi-unit deployments REQUIRE 'lan' mode for Node connectivity. The charm will block deployment if loopback mode is used with multiple units. * gateway-port | int Default: 18789 Port for the OpenClaw Gateway WebSocket/HTTP server * install-method | string Default: npm Installation method: 'npm' (global npm install), 'pnpm' (uses npm), 'bun' (global bun install), or 'source' (build from git source) * install-pkgs | string Comma-separated list of packages to install. Supported values: 'chrome', 'chromium', 'firefox', 'tailscale', 'homebrew'. Example: "chrome,tailscale,homebrew". Can be changed post-deployment via 'juju config'. * line-channel-access-token | string LINE Messaging API channel access token from LINE Developers Console. Leave empty to disable LINE messaging. * line-channel-secret | string LINE Messaging API channel secret from LINE Developers Console. Required when line-channel-access-token is configured. * log-level | string Default: info Log level (debug, info, warn, error) * manual | boolean Manual configuration mode. When enabled (manual=true): + Charm will NOT auto-generate openclaw.json or node.json + User is responsible for creating and managing OpenClaw configuration + Charm only installs OpenClaw and manages systemd services + Peer relations still work for multi-unit deployments + Environment file (.openclaw/environment) is still created for systemd When disabled (manual=false, default): + Charm auto-generates configuration from Juju config options + AI providers, channels, and settings are managed by the charm + Configuration updates on 'juju config' changes * node-version | string Default: 24 Node.js major version to install (minimum 22 required) * sandbox-mode | string Default: non-main Sandbox mode for non-main sessions: 'all' (sandbox everything), 'non-main' (sandbox groups/channels), or 'none' (no sandboxing) * slack-app-token | string Slack app token (xapp-...) from Slack App settings. Required when slack-bot-token is configured. * slack-bot-token | string Slack bot token (xoxb-...) from Slack App settings. Leave empty to disable Slack messaging. * telegram-bot-token | string Telegram bot token from @BotFather (e.g., 123456:ABC-DEF1234ghIkl-zyx57W2v1u123ew11). Leave empty to disable Telegram messaging. * version | string Default: latest OpenClaw version to install (e.g., 'latest', '2026.1.29', or git commit)