mirror of
https://github.com/openclaw/openclaw.git
synced 2026-05-06 14:50:45 +00:00
docs: remove duplicate H1 where frontmatter title already sets it
This commit is contained in:
Vincent Koc
@@ -10,8 +10,6 @@ read_when:
|
||||
title: "ACP agents"
|
||||
---
|
||||
|
||||
# ACP agents
|
||||
|
||||
[Agent Client Protocol (ACP)](https://agentclientprotocol.com/) sessions let OpenClaw run external coding harnesses (for example Pi, Claude Code, Codex, Cursor, Copilot, OpenClaw ACP, OpenCode, Gemini CLI, and other supported ACPX harnesses) through an ACP backend plugin.
|
||||
|
||||
If you ask OpenClaw in plain language to "run this in Codex" or "start Claude Code in a thread", OpenClaw should route that request to the ACP runtime (not the native sub-agent runtime). Each ACP session spawn is tracked as a [background task](/automation/tasks).
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
title: "Agent Send"
|
||||
---
|
||||
|
||||
# Agent Send
|
||||
|
||||
`openclaw agent` runs a single agent turn from the command line without needing
|
||||
an inbound chat message. Use it for scripted workflows, testing, and
|
||||
programmatic delivery.
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
title: "apply_patch Tool"
|
||||
---
|
||||
|
||||
# apply_patch tool
|
||||
|
||||
Apply file changes using a structured patch format. This is ideal for multi-file
|
||||
or multi-hunk edits where a single `edit` call would be brittle.
|
||||
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "WSL2 + Windows + remote Chrome CDP troubleshooting"
|
||||
---
|
||||
|
||||
# WSL2 + Windows + remote Chrome CDP troubleshooting
|
||||
|
||||
This guide covers the common split-host setup where:
|
||||
|
||||
- OpenClaw Gateway runs inside WSL2
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "Browser (OpenClaw-managed)"
|
||||
---
|
||||
|
||||
# Browser (openclaw-managed)
|
||||
|
||||
OpenClaw can run a **dedicated Chrome/Brave/Edge/Chromium profile** that the agent controls.
|
||||
It is isolated from your personal browser and is managed through a small local
|
||||
control service inside the Gateway (loopback only).
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
title: "BTW Side Questions"
|
||||
---
|
||||
|
||||
# BTW Side Questions
|
||||
|
||||
`/btw` lets you ask a quick side question about the **current session** without
|
||||
turning that question into normal conversation history.
|
||||
|
||||
|
||||
@@ -8,8 +8,6 @@ title: "Adding Capabilities (Contributor Guide)"
|
||||
sidebarTitle: "Adding Capabilities"
|
||||
---
|
||||
|
||||
# Adding Capabilities
|
||||
|
||||
<Info>
|
||||
This is a **contributor guide** for OpenClaw core developers. If you are
|
||||
building an external plugin, see [Building Plugins](/plugins/building-plugins)
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "ClawHub"
|
||||
---
|
||||
|
||||
# ClawHub
|
||||
|
||||
ClawHub is the public registry for **OpenClaw skills and plugins**.
|
||||
|
||||
- Use native `openclaw` commands to search/install/update skills and install
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "Code Execution"
|
||||
---
|
||||
|
||||
# Code Execution
|
||||
|
||||
`code_execution` runs sandboxed remote Python analysis on xAI's Responses API.
|
||||
This is different from local [`exec`](/tools/exec):
|
||||
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
- You need a quick starter workflow for SKILL.md-based skills
|
||||
---
|
||||
|
||||
# Creating Skills
|
||||
|
||||
Skills teach the agent how and when to use tools. Each skill is a directory
|
||||
containing a `SKILL.md` file with YAML frontmatter and markdown instructions.
|
||||
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
- You need controlled, temporary diff artifacts with secure defaults
|
||||
---
|
||||
|
||||
# Diffs
|
||||
|
||||
`diffs` is an optional plugin tool with short built-in system guidance and a companion skill that turns change content into a read-only diff artifact for agents.
|
||||
|
||||
It accepts either:
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "DuckDuckGo Search"
|
||||
---
|
||||
|
||||
# DuckDuckGo Search
|
||||
|
||||
OpenClaw supports DuckDuckGo as a **key-free** `web_search` provider. No API
|
||||
key or account is required.
|
||||
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
title: "Elevated Mode"
|
||||
---
|
||||
|
||||
# Elevated Mode
|
||||
|
||||
When an agent runs inside a sandbox, its `exec` commands are confined to the
|
||||
sandbox environment. **Elevated mode** lets the agent break out and run commands
|
||||
outside the sandbox instead, with configurable approval gates.
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "Exa Search"
|
||||
---
|
||||
|
||||
# Exa Search
|
||||
|
||||
OpenClaw supports [Exa AI](https://exa.ai/) as a `web_search` provider. Exa
|
||||
offers neural, keyword, and hybrid search modes with built-in content
|
||||
extraction (highlights, text, summaries).
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "Exec approvals"
|
||||
---
|
||||
|
||||
# Exec approvals
|
||||
|
||||
Exec approvals are the **companion app / node host guardrail** for letting a
|
||||
sandboxed agent run commands on a real host (`gateway` or `node`). A safety
|
||||
interlock: commands are allowed only when policy + allowlist + (optional) user
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
title: "Exec Tool"
|
||||
---
|
||||
|
||||
# Exec tool
|
||||
|
||||
Run shell commands in the workspace. Supports foreground + background execution via `process`.
|
||||
If `process` is disallowed, `exec` runs synchronously and ignores `yieldMs`/`background`.
|
||||
Background sessions are scoped per agent; `process` only sees sessions from the same agent.
|
||||
|
||||
@@ -8,8 +8,6 @@ read_when:
|
||||
title: "Firecrawl"
|
||||
---
|
||||
|
||||
# Firecrawl
|
||||
|
||||
OpenClaw can use **Firecrawl** in three ways:
|
||||
|
||||
- as the `web_search` provider
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "Gemini Search"
|
||||
---
|
||||
|
||||
# Gemini Search
|
||||
|
||||
OpenClaw supports Gemini models with built-in
|
||||
[Google Search grounding](https://ai.google.dev/gemini-api/docs/grounding),
|
||||
which returns AI-synthesized answers backed by live Google Search results with
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
title: "Grok Search"
|
||||
---
|
||||
|
||||
# Grok Search
|
||||
|
||||
OpenClaw supports Grok as a `web_search` provider, using xAI web-grounded
|
||||
responses to produce AI-synthesized answers backed by live search results
|
||||
with citations.
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "Image Generation"
|
||||
---
|
||||
|
||||
# Image Generation
|
||||
|
||||
The `image_generate` tool lets the agent create and edit images using your configured providers. Generated images are delivered automatically as media attachments in the agent's reply.
|
||||
|
||||
<Note>
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "Tools and Plugins"
|
||||
---
|
||||
|
||||
# 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.
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
title: "Kimi Search"
|
||||
---
|
||||
|
||||
# Kimi Search
|
||||
|
||||
OpenClaw supports Kimi as a `web_search` provider, using Moonshot web search
|
||||
to produce AI-synthesized answers with citations.
|
||||
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
title: "LLM Task"
|
||||
---
|
||||
|
||||
# LLM Task
|
||||
|
||||
`llm-task` is an **optional plugin tool** that runs a JSON-only LLM task and
|
||||
returns structured output (optionally validated against JSON Schema).
|
||||
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
- You need to resume a workflow without re-running earlier steps
|
||||
---
|
||||
|
||||
# Lobster
|
||||
|
||||
Lobster is a workflow shell that lets OpenClaw run multi-step tool sequences as a single, deterministic operation with explicit approval checkpoints.
|
||||
|
||||
Lobster is one authoring layer above detached background work. For flow orchestration above individual tasks, see [Task Flow](/automation/taskflow) (`openclaw tasks flow`). For the task activity ledger, see [`openclaw tasks`](/automation/tasks).
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
- You are editing agent tool/runtime policies
|
||||
---
|
||||
|
||||
# Tool-loop detection
|
||||
|
||||
OpenClaw can keep agents from getting stuck in repeated tool-call patterns.
|
||||
The guard is **disabled by default**.
|
||||
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "MiniMax Search"
|
||||
---
|
||||
|
||||
# MiniMax Search
|
||||
|
||||
OpenClaw supports MiniMax as a `web_search` provider through the MiniMax
|
||||
Coding Plan search API. It returns structured search results with titles, URLs,
|
||||
snippets, and related queries.
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "Music Generation"
|
||||
---
|
||||
|
||||
# Music Generation
|
||||
|
||||
The `music_generate` tool lets the agent create music or audio through the
|
||||
shared music-generation capability with configured providers such as Google,
|
||||
MiniMax, and workflow-configured ComfyUI.
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "Ollama Web Search"
|
||||
---
|
||||
|
||||
# Ollama Web Search
|
||||
|
||||
OpenClaw supports **Ollama Web Search** as a bundled `web_search` provider.
|
||||
It uses Ollama's experimental web-search API and returns structured results
|
||||
with titles, URLs, and snippets.
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
- You are debugging native PDF mode vs extraction fallback
|
||||
---
|
||||
|
||||
# PDF tool
|
||||
|
||||
`pdf` analyzes one or more PDF documents and returns text.
|
||||
|
||||
Quick behavior:
|
||||
|
||||
@@ -8,8 +8,6 @@ title: "Plugins"
|
||||
sidebarTitle: "Install and Configure"
|
||||
---
|
||||
|
||||
# Plugins
|
||||
|
||||
Plugins extend OpenClaw with new capabilities: channels, model providers,
|
||||
tools, skills, speech, realtime transcription, realtime voice,
|
||||
media-understanding, image generation, video generation, web fetch, web
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
title: "Reactions"
|
||||
---
|
||||
|
||||
# Reactions
|
||||
|
||||
The agent can add and remove emoji reactions on messages using the `message`
|
||||
tool with the `react` action. Reaction behavior varies by channel.
|
||||
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "SearXNG Search"
|
||||
---
|
||||
|
||||
# SearXNG Search
|
||||
|
||||
OpenClaw supports [SearXNG](https://docs.searxng.org/) as a **self-hosted,
|
||||
key-free** `web_search` provider. SearXNG is an open-source meta-search engine
|
||||
that aggregates results from Google, Bing, DuckDuckGo, and other sources.
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
title: "Skills Config"
|
||||
---
|
||||
|
||||
# Skills Config
|
||||
|
||||
Most skills loader/install configuration lives under `skills` in
|
||||
`~/.openclaw/openclaw.json`. Agent-specific skill visibility lives under
|
||||
`agents.defaults.skills` and `agents.list[].skills`.
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
title: "Slash Commands"
|
||||
---
|
||||
|
||||
# Slash commands
|
||||
|
||||
Commands are handled by the Gateway. Most commands must be sent as a **standalone** message that starts with `/`.
|
||||
The host-only bash chat command uses `! <cmd>` (with `/bash <cmd>` as an alias).
|
||||
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "Sub-Agents"
|
||||
---
|
||||
|
||||
# Sub-agents
|
||||
|
||||
Sub-agents are background agent runs spawned from an existing agent run. They run in their own session (`agent:<agentId>:subagent:<uuid>`) and, when finished, **announce** their result back to the requester chat channel. Each sub-agent run is tracked as a [background task](/automation/tasks).
|
||||
|
||||
## Slash command
|
||||
|
||||
@@ -8,8 +8,6 @@ read_when:
|
||||
title: "Tavily"
|
||||
---
|
||||
|
||||
# Tavily
|
||||
|
||||
OpenClaw can use **Tavily** in two ways:
|
||||
|
||||
- as the `web_search` provider
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
- You need to understand what tokenjuice changes and what it leaves raw
|
||||
---
|
||||
|
||||
# Tokenjuice
|
||||
|
||||
`tokenjuice` is an optional bundled plugin that compacts noisy `exec` and `bash`
|
||||
tool results after the command has already run.
|
||||
|
||||
|
||||
@@ -8,8 +8,6 @@ read_when:
|
||||
title: "Trajectory Bundles"
|
||||
---
|
||||
|
||||
# Trajectory bundles
|
||||
|
||||
Trajectory capture is OpenClaw's per-session flight recorder. It records a
|
||||
structured timeline for each agent run, then `/export-trajectory` packages the
|
||||
current session into a redacted support bundle.
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "Video Generation"
|
||||
---
|
||||
|
||||
# Video Generation
|
||||
|
||||
OpenClaw agents can generate videos from text prompts, reference images, or existing videos. Fourteen provider backends are supported, each with different model options, input modes, and feature sets. The agent picks the right provider automatically based on your configuration and available API keys.
|
||||
|
||||
<Note>
|
||||
|
||||
@@ -8,8 +8,6 @@ title: "Web Fetch"
|
||||
sidebarTitle: "Web Fetch"
|
||||
---
|
||||
|
||||
# Web Fetch
|
||||
|
||||
The `web_fetch` tool does a plain HTTP GET and extracts readable content
|
||||
(HTML to markdown or text). It does **not** execute JavaScript.
|
||||
|
||||
|
||||
@@ -9,8 +9,6 @@ read_when:
|
||||
- You want to understand auto-detection and provider fallback
|
||||
---
|
||||
|
||||
# Web Search
|
||||
|
||||
The `web_search` tool searches the web using your configured provider and
|
||||
returns results. Results are cached by query for 15 minutes (configurable).
|
||||
|
||||
|
||||
Reference in New Issue
Block a user