TaskFlow
DashboardFreewriteWhiteboardsProjectsCRMTasksNotificationsSettingsAgent TowerAPI Docs
OpenClaw Docs
?

User

Member

Caricamento in corso...

Home
Progetti
Task
Notifiche
CRM

    OpenClaw

    Documentation Mirror

    Documentation Overview

    Docs

    Auth credential semantics
    Scheduled tasks
    Hooks
    Automation & tasks
    Standing orders
    Task flow
    Background tasks
    BlueBubbles
    Broadcast groups
    Channel routing
    Discord
    Feishu
    Google Chat
    Group messages
    Groups
    iMessage
    Chat channels
    IRC
    LINE
    Channel location parsing
    Matrix
    Matrix migration
    Matrix push rules for quiet previews
    Mattermost
    Microsoft Teams
    Nextcloud Talk
    Nostr
    Pairing
    QA channel
    QQ bot
    Signal
    Slack
    Synology Chat
    Telegram
    Tlon
    Channel troubleshooting
    Twitch
    WeChat
    WhatsApp
    Yuanbao
    Zalo
    Zalo personal
    CI pipeline
    ACP
    Agent
    Agents
    Approvals
    Backup
    Browser
    Channels
    Clawbot
    `openclaw commitments`
    Completion
    Config
    Configure
    Cron
    Daemon
    Dashboard
    Devices
    Directory
    DNS
    Docs
    Doctor
    Flows (redirect)
    Gateway
    Health
    Hooks
    CLI reference
    Inference CLI
    Logs
    MCP
    Memory
    Message
    Migrate
    Models
    Node
    Nodes
    Onboard
    Pairing
    Plugins
    Proxy
    QR
    Reset
    Sandbox CLI
    Secrets
    Security
    Sessions
    Setup
    Skills
    Status
    System
    `openclaw tasks`
    TUI
    Uninstall
    Update
    Voicecall
    Webhooks
    Wiki
    Active memory
    Agent runtime
    Agent loop
    Agent runtimes
    Agent workspace
    Gateway architecture
    Channel docking
    Inferred commitments
    Compaction
    Context
    Context engine
    Delegate architecture
    Dreaming
    Experimental features
    Features
    Markdown formatting
    Memory overview
    Builtin memory engine
    Honcho memory
    QMD memory engine
    Memory search
    Messages
    Model failover
    Model providers
    Models CLI
    Multi-agent routing
    OAuth
    OpenClaw App SDK
    Presence
    QA overview
    Matrix QA
    Command queue
    Steering queue
    Retry policy
    Session management
    Session pruning
    Session tools
    SOUL.md personality guide
    Streaming and chunking
    System prompt
    Timezones
    TypeBox
    Typing indicators
    Usage tracking
    Date and time
    Node + tsx crash
    Diagnostics flags
    Authentication
    Background exec and process tool
    Bonjour discovery
    Bridge protocol
    CLI backends
    Configuration — agents
    Configuration — channels
    Configuration — tools and custom providers
    Configuration
    Configuration examples
    Configuration reference
    Diagnostics export
    Discovery and transports
    Doctor
    Gateway lock
    Health checks
    Heartbeat
    Gateway runbook
    Local models
    Gateway logging
    Multiple gateways
    Network model
    OpenAI chat completions
    OpenResponses API
    OpenShell
    OpenTelemetry export
    Gateway-owned pairing
    Prometheus metrics
    Gateway protocol
    Remote access
    Remote gateway setup
    Sandbox vs tool policy vs elevated
    Sandboxing
    Secrets management
    Secrets apply plan contract
    Security audit checks
    Security
    Tailscale
    Tools invoke API
    Troubleshooting
    Trusted proxy auth
    Debugging
    Environment variables
    FAQ
    FAQ: first-run setup
    FAQ: models and auth
    GPT-5.5 / Codex agentic parity
    GPT-5.5 / Codex parity maintainer notes
    Help
    Scripts
    Testing
    Testing: live suites
    General troubleshooting
    OpenClaw
    Ansible
    Azure
    Bun (experimental)
    ClawDock
    Release channels
    DigitalOcean
    Docker
    Docker VM runtime
    exe.dev
    Fly.io
    GCP
    Hetzner
    Hostinger
    Install
    Installer internals
    Kubernetes
    macOS VMs
    Migration guide
    Migrating from Claude
    Migrating from Hermes
    Nix
    Node.js
    Northflank
    Oracle Cloud
    Podman
    Railway
    Raspberry Pi
    Render
    Uninstall
    Updating
    Logging
    Network
    Audio and voice notes
    Camera capture
    Image and media support
    Nodes
    Location command
    Media understanding
    Talk mode
    Node troubleshooting
    Voice wake
    Pi integration architecture
    Pi development workflow
    Android app
    Platforms
    iOS app
    Linux app
    Gateway on macOS
    Canvas
    Gateway lifecycle
    macOS dev setup
    Health checks (macOS)
    Menu bar icon
    macOS logging
    Menu bar
    Peekaboo bridge
    macOS permissions
    Remote control
    macOS signing
    Skills (macOS)
    Voice overlay
    Voice wake (macOS)
    WebChat (macOS)
    macOS IPC
    macOS app
    Windows
    Plugin internals
    Plugin architecture internals
    Building plugins
    Plugin bundles
    Codex Computer Use
    Codex harness
    Community plugins
    Plugin compatibility
    Google Meet plugin
    Plugin hooks
    Plugin manifest
    Memory LanceDB
    Memory wiki
    Message presentation
    Agent harness plugins
    Building channel plugins
    Channel turn kernel
    Plugin entry points
    Plugin SDK migration
    Plugin SDK overview
    Building provider plugins
    Plugin runtime helpers
    Plugin setup and config
    Plugin SDK subpaths
    Plugin testing
    Skill workshop plugin
    Voice call plugin
    Webhooks plugin
    Zalo personal plugin
    OpenProse
    Alibaba Model Studio
    Anthropic
    Arcee AI
    Azure Speech
    Amazon Bedrock
    Amazon Bedrock Mantle
    Chutes
    Claude Max API proxy
    Cloudflare AI gateway
    ComfyUI
    Deepgram
    Deepinfra
    DeepSeek
    ElevenLabs
    Fal
    Fireworks
    GitHub Copilot
    GLM (Zhipu)
    Google (Gemini)
    Gradium
    Groq
    Hugging Face (inference)
    Provider directory
    Inferrs
    Inworld
    Kilocode
    LiteLLM
    LM Studio
    MiniMax
    Mistral
    Model provider quickstart
    Moonshot AI
    NVIDIA
    Ollama
    OpenAI
    OpenCode
    OpenCode Go
    OpenRouter
    Perplexity
    Qianfan
    Qwen
    Runway
    SGLang
    StepFun
    Synthetic
    Tencent Cloud (TokenHub)
    Together AI
    Venice AI
    Vercel AI gateway
    vLLM
    Volcengine (Doubao)
    Vydra
    xAI
    Xiaomi MiMo
    Z.AI
    Default AGENTS.md
    Release policy
    API usage and costs
    Credits
    Device model database
    Full release validation
    Memory configuration reference
    OpenClaw App SDK API design
    Prompt caching
    Rich output protocol
    RPC adapters
    SecretRef credential surface
    Session management deep dive
    AGENTS.md template
    BOOT.md template
    BOOTSTRAP.md template
    HEARTBEAT.md template
    IDENTITY template
    SOUL.md template
    TOOLS.md template
    USER template
    Tests
    Token use and costs
    Transcript hygiene
    Onboarding reference
    Contributing to the threat model
    Threat model (MITRE ATLAS)
    Formal verification (security models)
    Network proxy
    Agent bootstrapping
    Docs directory
    Getting started
    Docs hubs
    OpenClaw lore
    Onboarding (macOS app)
    Onboarding overview
    Personal assistant setup
    Setup
    Showcase
    Onboarding (CLI)
    CLI automation
    CLI setup reference
    ACP agents
    ACP agents — setup
    Agent send
    apply_patch tool
    Brave search
    Browser (OpenClaw-managed)
    Browser control API
    Browser troubleshooting
    Browser login
    WSL2 + Windows + remote Chrome CDP troubleshooting
    BTW side questions
    ClawHub
    Code execution
    Creating skills
    Diffs
    DuckDuckGo search
    Elevated mode
    Exa search
    Exec tool
    Exec approvals
    Exec approvals — advanced
    Firecrawl
    Gemini search
    Grok search
    Image generation
    Tools and plugins
    Kimi search
    LLM task
    Lobster
    Tool-loop detection
    Media overview
    MiniMax search
    Multi-agent sandbox and tools
    Music generation
    Ollama web search
    PDF tool
    Perplexity search
    Plugins
    Reactions
    SearXNG search
    Skills
    Skills config
    Slash commands
    Sub-agents
    Tavily
    Thinking levels
    Tokenjuice
    Trajectory bundles
    Text-to-speech
    Video generation
    Web search
    Web fetch
    Linux server
    Control UI
    Dashboard
    Web
    TUI
    WebChat

    OpenAPI Specs

    openapi
    TaskFlow
    docs/openclaw
    Original Docs

    Real-time Synchronized Documentation

    Last sync: 01/05/2026 07:01:30

    Note: This content is mirrored from docs.openclaw.ai and is subject to their terms and conditions.

    OpenClaw Docs

    v2.4.0 Production

    Last synced: Today, 22:00

    Technical reference for the OpenClaw framework. Real-time synchronization with the official documentation engine.

    Use this file to discover all available pages before exploring further.

    Tools and plugins

    Everything the agent does beyond generating text happens through tools. Tools are how the agent reads files, runs commands, browses the web, sends messages, and interacts with devices.

    Tools, skills, and plugins

    OpenClaw has three layers that work together:

    Tools are what the agent calls

    A tool is a typed function the agent can invoke (e.g. `exec`, `browser`, `web_search`, `message`). OpenClaw ships a set of **built-in tools** and plugins can register additional ones.
    text
    The agent sees tools as structured function definitions sent to the model API.

    Skills teach the agent when and how

    A skill is a markdown file (`SKILL.md`) injected into the system prompt. Skills give 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.
    text
    [Skills reference](/tools/skills) | [Creating skills](/tools/creating-skills)

    Plugins package everything together

    A plugin is a package that can register any combination of capabilities: channels, model providers, tools, skills, speech, realtime transcription, realtime voice, media understanding, image generation, video generation, web fetch, web search, and more. Some plugins are **core** (shipped with OpenClaw), others are **external** (published on npm by the community).
    text
    [Install and configure plugins](/tools/plugin) | [Build your own](/plugins/building-plugins)

    Built-in tools

    These tools ship with OpenClaw and are available without installing any plugins:

    ToolWhat it doesPage
    text
    exec
    /
    text
    process
    Run shell commands, manage background processesExec, Exec Approvals
    text
    code_execution
    Run sandboxed remote Python analysisCode Execution
    text
    browser
    Control a Chromium browser (navigate, click, screenshot)Browser
    text
    web_search
    /
    text
    x_search
    /
    text
    web_fetch
    Search the web, search X posts, fetch page contentWeb, Web Fetch
    text
    read
    /
    text
    write
    /
    text
    edit
    File I/O in the workspace
    text
    apply_patch
    Multi-hunk file patchesApply Patch
    text
    message
    Send messages across all channelsAgent Send
    text
    canvas
    Drive node Canvas (present, eval, snapshot)
    text
    nodes
    Discover and target paired devices
    text
    cron
    /
    text
    gateway
    Manage scheduled jobs; inspect, patch, restart, or update the gateway
    text
    image
    /
    text
    image_generate
    Analyze or generate imagesImage Generation
    text
    music_generate
    Generate music tracksMusic Generation
    text
    video_generate
    Generate videosVideo Generation
    text
    tts
    One-shot text-to-speech conversionTTS
    text
    sessions_*
    /
    text
    subagents
    /
    text
    agents_list
    Session management, status, and sub-agent orchestrationSub-agents
    text
    session_status
    Lightweight
    text
    /status
    -style readback and session model override
    Session Tools

    For image work, use

    text
    image
    for analysis and
    text
    image_generate
    for generation or editing. If you target
    text
    openai/*
    ,
    text
    google/*
    ,
    text
    fal/*
    , or another non-default image provider, configure that provider's auth/API key first.

    For music work, use

    text
    music_generate
    . If you target
    text
    google/*
    ,
    text
    minimax/*
    , or another non-default music provider, configure that provider's auth/API key first.

    For video work, use

    text
    video_generate
    . If you target
    text
    qwen/*
    or another non-default video provider, configure that provider's auth/API key first.

    For workflow-driven audio generation, use

    text
    music_generate
    when a plugin such as ComfyUI registers it. This is separate from
    text
    tts
    , which is text-to-speech.

    text
    session_status
    is the lightweight status/readback tool in the sessions group. It answers
    text
    /status
    -style questions about the current session and can optionally set a per-session model override;
    text
    model=default
    clears that override. Like
    text
    /status
    , it can backfill sparse token/cache counters and the active runtime model label from the latest transcript usage entry.

    text
    gateway
    is the owner-only runtime tool for gateway operations:

    • text
      config.schema.lookup
      for one path-scoped config subtree before edits
    • text
      config.get
      for the current config snapshot + hash
    • text
      config.patch
      for partial config updates with restart
    • text
      config.apply
      only for full-config replacement
    • text
      update.run
      for explicit self-update + restart

    For partial changes, prefer

    text
    config.schema.lookup
    then
    text
    config.patch
    . Use
    text
    config.apply
    only when you intentionally replace the entire config. For broader config docs, read Configuration and Configuration reference. The tool also refuses to change
    text
    tools.exec.ask
    or
    text
    tools.exec.security
    ; legacy
    text
    tools.bash.*
    aliases normalize to the same protected exec paths.

    Plugin-provided tools

    Plugins can register additional tools. Some examples:

    • Diffs — diff viewer and renderer
    • LLM Task — JSON-only LLM step for structured output
    • Lobster — typed workflow runtime with resumable approvals
    • Music Generation — shared
      text
      music_generate
      tool with workflow-backed providers
    • OpenProse — markdown-first workflow orchestration
    • Tokenjuice — compact noisy
      text
      exec
      and
      text
      bash
      tool results

    Tool configuration

    Allow and deny lists

    Control which tools the agent can call via

    text
    tools.allow
    /
    text
    tools.deny
    in config. Deny always wins over allow.

    json5
    { tools: { allow: ["group:fs", "browser", "web_search"], deny: ["exec"], }, }

    OpenClaw fails closed when an explicit allowlist resolves to no callable tools. For example,

    text
    tools.allow: ["query_db"]
    only works if a loaded plugin actually registers
    text
    query_db
    . If no built-in, plugin, or bundled MCP tool matches the allowlist, the run stops before the model call instead of continuing as a text-only run that could hallucinate tool results.

    Tool profiles

    text
    tools.profile
    sets a base allowlist before
    text
    allow
    /
    text
    deny
    is applied. Per-agent override:
    text
    agents.list[].tools.profile
    .

    ProfileWhat it includes
    text
    full
    Unrestricted baseline for broader command/control access; same as leaving
    text
    tools.profile
    unset
    text
    coding
    text
    group:fs
    ,
    text
    group:runtime
    ,
    text
    group:web
    ,
    text
    group:sessions
    ,
    text
    group:memory
    ,
    text
    cron
    ,
    text
    image
    ,
    text
    image_generate
    ,
    text
    music_generate
    ,
    text
    video_generate
    text
    messaging
    text
    group:messaging
    ,
    text
    sessions_list
    ,
    text
    sessions_history
    ,
    text
    sessions_send
    ,
    text
    session_status
    text
    minimal
    text
    session_status
    only

    note

    `tools.profile: "messaging"` is intentionally narrow for channel-focused agents. It leaves out broader command/control tools such as filesystem, runtime, browser, canvas, nodes, cron, and gateway control. Use `tools.profile: "full"` as the unrestricted baseline for broader command/control access, then trim access with `tools.allow` / `tools.deny` when needed.

    text
    coding
    includes lightweight web tools (
    text
    web_search
    ,
    text
    web_fetch
    ,
    text
    x_search
    ) but not the full browser-control tool. Browser automation can drive real sessions and logged-in profiles, so add it explicitly with
    text
    tools.alsoAllow: ["browser"]
    or a per-agent
    text
    agents.list[].tools.alsoAllow: ["browser"]
    .

    note

    Configuring `tools.exec` or `tools.fs` under a restrictive profile (`messaging`, `minimal`) does not implicitly widen the profile's allowlist. Add explicit `tools.alsoAllow` entries (for example `["exec", "process"]` for exec, or `["read", "write", "edit"]` for fs) when you want a restrictive profile to use those configured sections. OpenClaw logs a startup warning when a config section is present without a matching `alsoAllow` grant.

    The

    text
    coding
    and
    text
    messaging
    profiles also allow configured bundle MCP tools under the plugin key
    text
    bundle-mcp
    . Add
    text
    tools.deny: ["bundle-mcp"]
    when you want a profile to keep its normal built-ins but hide all configured MCP tools. The
    text
    minimal
    profile does not include bundle MCP tools.

    Example (broadest tool surface by default):

    json5
    { tools: { profile: "full", }, }

    Tool groups

    Use

    text
    group:*
    shorthands in allow/deny lists:

    GroupTools
    text
    group:runtime
    exec, process, code_execution (
    text
    bash
    is accepted as an alias for
    text
    exec
    )
    text
    group:fs
    read, write, edit, apply_patch
    text
    group:sessions
    sessions_list, sessions_history, sessions_send, sessions_spawn, sessions_yield, subagents, session_status
    text
    group:memory
    memory_search, memory_get
    text
    group:web
    web_search, x_search, web_fetch
    text
    group:ui
    browser, canvas
    text
    group:automation
    cron, gateway
    text
    group:messaging
    message
    text
    group:nodes
    nodes
    text
    group:agents
    agents_list
    text
    group:media
    image, image_generate, music_generate, video_generate, tts
    text
    group:openclaw
    All built-in OpenClaw tools (excludes plugin tools)

    text
    sessions_history
    returns a bounded, safety-filtered recall view. It strips thinking tags,
    text
    <relevant-memories>
    scaffolding, plain-text tool-call XML payloads (including
    text
    <tool_call>...</tool_call>
    ,
    text
    <function_call>...</function_call>
    ,
    text
    <tool_calls>...</tool_calls>
    ,
    text
    <function_calls>...</function_calls>
    , and truncated tool-call blocks), downgraded tool-call scaffolding, leaked ASCII/full-width model control tokens, and malformed MiniMax tool-call XML from assistant text, then applies redaction/truncation and possible oversized-row placeholders instead of acting as a raw transcript dump.

    Provider-specific restrictions

    Use

    text
    tools.byProvider
    to restrict tools for specific providers without changing global defaults:

    json5
    { tools: { profile: "coding", byProvider: { "google-antigravity": { profile: "minimal" }, }, }, }

    © 2024 TaskFlow Mirror

    Powered by TaskFlow Sync Engine