vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-06 05:30:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: drop in-body H1s and typography hygiene across 4 pages

Browse Source 
docs/install/macos-vm.md: removed the duplicate '# OpenClaw on macOS
VMs (Sandboxing)' H1 (Mintlify renders title from frontmatter; the
in-body H1 plus parens produced a brittle anchor).

docs/install/development-channels.md: removed the duplicate
'# Development channels' H1.

docs/install/index.md: replaced 3 typography characters (curly quotes
and en-dash) with ASCII equivalents.

docs/concepts/delegate-architecture.md: replaced 10 typography
characters (curly quotes, apostrophes, em/en dashes) with ASCII
equivalents.
This commit is contained in:
Vincent Koc
2026-05-05 19:04:11 -07:00
parent 6ad601d195
commit bff5051e38
4 changed files with 13 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
docs/concepts/delegate-architecture.md
View File

@@ -5,7 +5,7 @@ read_when: "You want an agent with its own identity that acts on behalf of human
status: active
---
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.
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.
@@ -14,15 +14,15 @@ This extends [Multi-Agent Routing](/concepts/multi-agent) from personal use into
A **delegate** is an OpenClaw agent that:
- Has its **own identity** (email address, display name, calendar).
- Acts **on behalf of** one or more humans — never pretends to be them.
- Acts **on behalf of** one or more humans - never pretends to be them.
- Operates under **explicit permissions** granted by the organization's identity provider.
- Follows **[standing orders](/automation/standing-orders)** — rules defined in the agent's `AGENTS.md` that specify what it may do autonomously vs. what requires human approval (see [Cron Jobs](/automation/cron-jobs) for scheduled execution).
- Follows **[standing orders](/automation/standing-orders)** - rules defined in the agent's `AGENTS.md` that specify what it may do autonomously vs. what requires human approval (see [Cron Jobs](/automation/cron-jobs) for scheduled execution).
The delegate model maps directly to how executive assistants work: they have their own credentials, send mail "on behalf of" their principal, and follow a defined scope of authority.
## Why delegates?
OpenClaw's default mode is a **personal assistant** — one human, one agent. Delegates extend this to organizations:
OpenClaw's default mode is a **personal assistant** - one human, one agent. Delegates extend this to organizations:
| Personal mode | Delegate mode |
| --------------------------- | ---------------------------------------------- |
@@ -48,7 +48,7 @@ The delegate can **read** organizational data and **draft** messages for human r
- Calendar: read events, surface conflicts, summarize the day.
- Files: read shared documents, summarize content.
This tier requires only read permissions from the identity provider. The agent does not write to any mailbox or calendar — drafts and proposals are delivered via chat for the human to act on.
This tier requires only read permissions from the identity provider. The agent does not write to any mailbox or calendar - drafts and proposals are delivered via chat for the human to act on.
### Tier 2: Send on Behalf
@@ -93,7 +93,7 @@ These rules load every session. They are the last line of defense regardless of
### Tool restrictions
Use per-agent tool policy (v2026.1.6+) to enforce boundaries at the Gateway level. This operates independently of the agent's personality files — even if the agent is instructed to bypass its rules, the Gateway blocks the tool call:
Use per-agent tool policy (v2026.1.6+) to enforce boundaries at the Gateway level. This operates independently of the agent's personality files - even if the agent is instructed to bypass its rules, the Gateway blocks the tool call:
```json5
{
@@ -159,7 +159,7 @@ Configure the delegate's personality in its workspace files:
### 2. Configure identity provider delegation
The delegate needs its own account in your identity provider with explicit delegation permissions. **Apply the principle of least privilege** — start with Tier 1 (read-only) and escalate only when the use case demands it.
The delegate needs its own account in your identity provider with explicit delegation permissions. **Apply the principle of least privilege** - start with Tier 1 (read-only) and escalate only when the use case demands it.
#### Microsoft 365
@@ -286,7 +286,7 @@ A complete delegate configuration for an organizational assistant that handles e
}
```
The delegate's `AGENTS.md` defines its autonomous authority — what it may do without asking, what requires approval, and what is forbidden. [Cron Jobs](/automation/cron-jobs) drive its daily schedule.
The delegate's `AGENTS.md` defines its autonomous authority - what it may do without asking, what requires approval, and what is forbidden. [Cron Jobs](/automation/cron-jobs) drive its daily schedule.
If you grant `sessions_history`, remember it is a bounded, safety-filtered
recall view. OpenClaw redacts credential/token-like text, truncates long
@@ -304,13 +304,13 @@ instead of returning a raw transcript dump.
The delegate model works for any small organization:
1. **Create one delegate agent** per organization.
2. **Harden first** — tool restrictions, sandbox, hard blocks, audit trail.
2. **Harden first** - tool restrictions, sandbox, hard blocks, audit trail.
3. **Grant scoped permissions** via the identity provider (least privilege).
4. **Define [standing orders](/automation/standing-orders)** for autonomous operations.
5. **Schedule cron jobs** for recurring tasks.
6. **Review and adjust** the capability tier as trust builds.
Multiple organizations can share one Gateway server using multi-agent routing — each org gets its own isolated agent, workspace, and credentials.
Multiple organizations can share one Gateway server using multi-agent routing - each org gets its own isolated agent, workspace, and credentials.
## Related

2
docs/install/development-channels.md
View File

@@ -8,8 +8,6 @@ title: "Release channels"
sidebarTitle: "Release Channels"
---
# Development channels
OpenClaw ships three update channels:
- **stable**: npm dist-tag `latest`. Recommended for most users.

6
docs/install/index.md
View File

@@ -1,5 +1,5 @@
---
summary: "Install OpenClaw — installer script, npm/pnpm/bun, from source, Docker, and more"
summary: "Install OpenClaw - installer script, npm/pnpm/bun, from source, Docker, and more"
read_when:
- You need an install method other than the Getting Started quickstart
- You want to deploy to a cloud platform
@@ -9,8 +9,8 @@ title: "Install"
## System requirements
- **Node 24** (recommended) or Node 22.14+ — the installer script handles this automatically
- **macOS, Linux, or Windows** — both native Windows and WSL2 are supported; WSL2 is more stable. See [Windows](/platforms/windows).
- **Node 24** (recommended) or Node 22.14+ - the installer script handles this automatically
- **macOS, Linux, or Windows** - both native Windows and WSL2 are supported; WSL2 is more stable. See [Windows](/platforms/windows).
- `pnpm` is only needed if you build from source
## Recommended: installer script

2
docs/install/macos-vm.md
View File

@@ -8,8 +8,6 @@ read_when:
title: "macOS VMs"
---
# OpenClaw on macOS VMs (Sandboxing)
## Recommended default (most users)
- **Small Linux VPS** for an always-on Gateway and low cost. See [VPS hosting](/vps).