mirror of
https://github.com/openclaw/openclaw.git
synced 2026-05-06 17:50:45 +00:00
docs: remove duplicate H1 where frontmatter title already sets it
This commit is contained in:
Vincent Koc
@@ -7,8 +7,6 @@ read_when:
|
||||
- You want to tune active memory behavior without enabling it everywhere
|
||||
---
|
||||
|
||||
# Active Memory
|
||||
|
||||
Active memory is an optional plugin-owned blocking memory sub-agent that runs
|
||||
before the main reply for eligible conversational sessions.
|
||||
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
title: "Agent Workspace"
|
||||
---
|
||||
|
||||
# Agent workspace
|
||||
|
||||
The workspace is the agent's home. It is the only working directory used for
|
||||
file tools and for workspace context. Keep it private and treat it as memory.
|
||||
|
||||
|
||||
@@ -5,8 +5,6 @@ read_when:
|
||||
title: "Agent Runtime"
|
||||
---
|
||||
|
||||
# Agent Runtime
|
||||
|
||||
OpenClaw runs a single embedded agent runtime.
|
||||
|
||||
## Workspace (required)
|
||||
|
||||
@@ -5,8 +5,6 @@ read_when:
|
||||
title: "Gateway Architecture"
|
||||
---
|
||||
|
||||
# Gateway architecture
|
||||
|
||||
## Overview
|
||||
|
||||
- A single long‑lived **Gateway** owns all messaging surfaces (WhatsApp via
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
title: "Compaction"
|
||||
---
|
||||
|
||||
# Compaction
|
||||
|
||||
Every model has a context window -- the maximum number of tokens it can process.
|
||||
When a conversation approaches that limit, OpenClaw **compacts** older messages
|
||||
into a summary so the chat can continue.
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "Context Engine"
|
||||
---
|
||||
|
||||
# Context Engine
|
||||
|
||||
A **context engine** controls how OpenClaw builds model context for each run.
|
||||
It decides which messages to include, how to summarize older history, and how
|
||||
to manage context across subagent boundaries.
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "Context"
|
||||
---
|
||||
|
||||
# Context
|
||||
|
||||
“Context” is **everything OpenClaw sends to the model for a run**. It is bounded by the model’s **context window** (token limit).
|
||||
|
||||
Beginner mental model:
|
||||
|
||||
@@ -5,8 +5,6 @@ read_when: "You want an agent with its own identity that acts on behalf of human
|
||||
status: active
|
||||
---
|
||||
|
||||
# Delegate Architecture
|
||||
|
||||
Goal: run OpenClaw as a **named delegate** — an agent with its own identity that acts "on behalf of" people in an organization. The agent never impersonates a human. It sends, reads, and schedules under its own account with explicit delegation permissions.
|
||||
|
||||
This extends [Multi-Agent Routing](/concepts/multi-agent) from personal use into organizational deployments.
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
- You want to tune consolidation without polluting MEMORY.md
|
||||
---
|
||||
|
||||
# Dreaming
|
||||
|
||||
Dreaming is the background memory consolidation system in `memory-core`.
|
||||
It helps OpenClaw move strong short-term signals into durable memory while
|
||||
keeping the process explainable and reviewable.
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
- You want one place to find the currently documented experimental flags
|
||||
---
|
||||
|
||||
# Experimental features
|
||||
|
||||
Experimental features in OpenClaw are **opt-in preview surfaces**. They are
|
||||
behind explicit flags because they still need real-world mileage before they
|
||||
deserve a stable default or a long-lived public contract.
|
||||
|
||||
@@ -5,8 +5,6 @@ read_when:
|
||||
title: "Features"
|
||||
---
|
||||
|
||||
# Features
|
||||
|
||||
## Highlights
|
||||
|
||||
<Columns>
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "Markdown Formatting"
|
||||
---
|
||||
|
||||
# Markdown formatting
|
||||
|
||||
OpenClaw formats outbound Markdown by converting it into a shared intermediate
|
||||
representation (IR) before rendering channel-specific output. The IR keeps the
|
||||
source text intact while carrying style/link spans so chunking and rendering can
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
- You want to configure embedding providers or hybrid search
|
||||
---
|
||||
|
||||
# Builtin Memory Engine
|
||||
|
||||
The builtin engine is the default memory backend. It stores your memory index in
|
||||
a per-agent SQLite database and needs no extra dependencies to get started.
|
||||
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
- You want AI-powered recall and user modeling
|
||||
---
|
||||
|
||||
# Honcho Memory
|
||||
|
||||
[Honcho](https://honcho.dev) adds AI-native memory to OpenClaw. It persists
|
||||
conversations to a dedicated service and builds user and agent models over time,
|
||||
giving your agent cross-session context that goes beyond workspace Markdown
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
- You want advanced memory features like reranking or extra indexed paths
|
||||
---
|
||||
|
||||
# QMD Memory Engine
|
||||
|
||||
[QMD](https://github.com/tobi/qmd) is a local-first search sidecar that runs
|
||||
alongside OpenClaw. It combines BM25, vector search, and reranking in a single
|
||||
binary, and can index content beyond your workspace memory files.
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
- You want to tune search quality
|
||||
---
|
||||
|
||||
# Memory Search
|
||||
|
||||
`memory_search` finds relevant notes from your memory files, even when the
|
||||
wording differs from the original text. It works by indexing memory into small
|
||||
chunks and searching them using embeddings, keywords, or both.
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
- You want to know what memory files to write
|
||||
---
|
||||
|
||||
# Memory Overview
|
||||
|
||||
OpenClaw remembers things by writing **plain Markdown files** in your agent's
|
||||
workspace. The model only "remembers" what gets saved to disk -- there is no
|
||||
hidden state.
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "Messages"
|
||||
---
|
||||
|
||||
# Messages
|
||||
|
||||
This page ties together how OpenClaw handles inbound messages, sessions, queueing,
|
||||
streaming, and reasoning visibility.
|
||||
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "Model Failover"
|
||||
---
|
||||
|
||||
# Model failover
|
||||
|
||||
OpenClaw handles failures in two stages:
|
||||
|
||||
1. **Auth profile rotation** within the current provider.
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
title: "Model providers"
|
||||
---
|
||||
|
||||
# Model providers
|
||||
|
||||
This page covers **LLM/model providers** (not chat channels like WhatsApp/Telegram).
|
||||
For model selection rules, see [/concepts/models](/concepts/models).
|
||||
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "Models CLI"
|
||||
---
|
||||
|
||||
# Models CLI
|
||||
|
||||
See [/concepts/model-failover](/concepts/model-failover) for auth profile
|
||||
rotation, cooldowns, and how that interacts with fallbacks.
|
||||
Quick provider overview + examples: [/concepts/model-providers](/concepts/model-providers).
|
||||
|
||||
@@ -5,8 +5,6 @@ read_when: "You want multiple isolated agents (workspaces + auth) in one gateway
|
||||
status: active
|
||||
---
|
||||
|
||||
# Multi-Agent Routing
|
||||
|
||||
Goal: multiple _isolated_ agents (separate workspace + `agentDir` + sessions), plus multiple channel accounts (e.g. two WhatsApps) in one running Gateway. Inbound is routed to an agent via bindings.
|
||||
|
||||
## What is "one agent"?
|
||||
|
||||
@@ -8,8 +8,6 @@ read_when:
|
||||
title: "OAuth"
|
||||
---
|
||||
|
||||
# OAuth
|
||||
|
||||
OpenClaw supports “subscription auth” via OAuth for providers that offer it
|
||||
(notably **OpenAI Codex (ChatGPT OAuth)**). For Anthropic, the practical split
|
||||
is now:
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "Presence"
|
||||
---
|
||||
|
||||
# Presence
|
||||
|
||||
OpenClaw “presence” is a lightweight, best‑effort view of:
|
||||
|
||||
- the **Gateway** itself, and
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "QA E2E Automation"
|
||||
---
|
||||
|
||||
# QA E2E Automation
|
||||
|
||||
The private QA stack is meant to exercise OpenClaw in a more realistic,
|
||||
channel-shaped way than a single unit test can.
|
||||
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
title: "Retry Policy"
|
||||
---
|
||||
|
||||
# Retry policy
|
||||
|
||||
## Goals
|
||||
|
||||
- Retry per HTTP request, not per multi-step flow.
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
- You want to understand Anthropic prompt cache optimization
|
||||
---
|
||||
|
||||
# Session Pruning
|
||||
|
||||
Session pruning trims **old tool results** from the context before each LLM
|
||||
call. It reduces context bloat from accumulated tool outputs (exec results, file
|
||||
reads, search results) without rewriting normal conversation text.
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "Session Tools"
|
||||
---
|
||||
|
||||
# Session Tools
|
||||
|
||||
OpenClaw gives agents tools to work across sessions, inspect status, and
|
||||
orchestrate sub-agents.
|
||||
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
title: "Session Management"
|
||||
---
|
||||
|
||||
# Session Management
|
||||
|
||||
OpenClaw organizes conversations into **sessions**. Each message is routed to a
|
||||
session based on where it came from -- DMs, group chats, cron jobs, etc.
|
||||
|
||||
|
||||
@@ -7,8 +7,6 @@ read_when:
|
||||
title: "SOUL.md Personality Guide"
|
||||
---
|
||||
|
||||
# SOUL.md Personality Guide
|
||||
|
||||
`SOUL.md` is where your agent's voice lives.
|
||||
|
||||
OpenClaw injects it on normal sessions, so it has real weight. If your agent
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
title: "System Prompt"
|
||||
---
|
||||
|
||||
# System Prompt
|
||||
|
||||
OpenClaw builds a custom system prompt for every agent run. The prompt is **OpenClaw-owned** and does not use the pi-coding-agent default prompt.
|
||||
|
||||
The prompt is assembled by OpenClaw and injected into each agent run.
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
title: "Timezones"
|
||||
---
|
||||
|
||||
# Timezones
|
||||
|
||||
OpenClaw standardizes timestamps so the model sees a **single reference time**.
|
||||
|
||||
## Message envelopes (local by default)
|
||||
|
||||
@@ -5,8 +5,6 @@ read_when:
|
||||
title: "Typing Indicators"
|
||||
---
|
||||
|
||||
# Typing indicators
|
||||
|
||||
Typing indicators are sent to the chat channel while a run is active. Use
|
||||
`agents.defaults.typingMode` to control **when** typing starts and `typingIntervalSeconds`
|
||||
to control **how often** it refreshes.
|
||||
|
||||
@@ -6,8 +6,6 @@ read_when:
|
||||
title: "Usage Tracking"
|
||||
---
|
||||
|
||||
# Usage tracking
|
||||
|
||||
## What it is
|
||||
|
||||
- Pulls provider usage/quota directly from their usage endpoints.
|
||||
|
||||
Reference in New Issue
Block a user