vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-04 08:10:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor: rename to openclaw

Browse Source
This commit is contained in:
Peter Steinberger
2026-01-30 03:15:10 +01:00
parent 4583f88626
commit 9a7160786a
2357 changed files with 16688 additions and 16788 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
docs/tools/agent-send.md
View File

@@ -1,11 +1,11 @@
---
summary: "Direct `moltbot agent` CLI runs (with optional delivery)"
summary: "Direct `openclaw agent` CLI runs (with optional delivery)"
read_when:
- Adding or modifying the agent CLI entrypoint
---
# `moltbot agent` (direct agent runs)
# `openclaw agent` (direct agent runs)
`moltbot agent` runs a single agent turn without needing an inbound chat message.
`openclaw agent` runs a single agent turn without needing an inbound chat message.
By default it goes **through the Gateway**; add `--local` to force the embedded
runtime on the current machine.
@@ -21,7 +21,7 @@ runtime on the current machine.
- Output:
- default: prints reply text (plus `MEDIA:<url>` lines)
- `--json`: prints structured payload + metadata
- Optional delivery back to a channel with `--deliver` + `--channel` (target formats match `moltbot message --target`).
- Optional delivery back to a channel with `--deliver` + `--channel` (target formats match `openclaw message --target`).
- Use `--reply-channel`/`--reply-to`/`--reply-account` to override delivery without changing the session.
If the Gateway is unreachable, the CLI **falls back** to the embedded local run.
@@ -29,12 +29,12 @@ If the Gateway is unreachable, the CLI **falls back** to the embedded local run.
## Examples
```bash
moltbot agent --to +15555550123 --message "status update"
moltbot agent --agent ops --message "Summarize logs"
moltbot agent --session-id 1234 --message "Summarize inbox" --thinking medium
moltbot agent --to +15555550123 --message "Trace logs" --verbose on --json
moltbot agent --to +15555550123 --message "Summon reply" --deliver
moltbot agent --agent ops --message "Generate report" --deliver --reply-channel slack --reply-to "#reports"
openclaw agent --to +15555550123 --message "status update"
openclaw agent --agent ops --message "Summarize logs"
openclaw agent --session-id 1234 --message "Summarize inbox" --thinking medium
openclaw agent --to +15555550123 --message "Trace logs" --verbose on --json
openclaw agent --to +15555550123 --message "Summon reply" --deliver
openclaw agent --agent ops --message "Generate report" --deliver --reply-channel slack --reply-to "#reports"
```
## Flags

32
docs/tools/browser-linux-troubleshooting.md
View File

@@ -1,5 +1,5 @@
---
summary: "Fix Chrome/Brave/Edge/Chromium CDP startup issues for Moltbot browser control on Linux"
summary: "Fix Chrome/Brave/Edge/Chromium CDP startup issues for OpenClaw browser control on Linux"
read_when: "Browser control fails on Linux, especially with snap Chromium"
---
@@ -7,14 +7,14 @@ read_when: "Browser control fails on Linux, especially with snap Chromium"
## Problem: "Failed to start Chrome CDP on port 18800"
Moltbot's browser control server fails to launch Chrome/Brave/Edge/Chromium with the error:
OpenClaw's browser control server fails to launch Chrome/Brave/Edge/Chromium with the error:
```
{"error":"Error: Failed to start Chrome CDP on port 18800 for profile \"clawd\"."}
{"error":"Error: Failed to start Chrome CDP on port 18800 for profile \"openclaw\"."}
```
### Root Cause
On Ubuntu (and many Linux distros), the default Chromium installation is a **snap package**. Snap's AppArmor confinement interferes with how Moltbot spawns and monitors the browser process.
On Ubuntu (and many Linux distros), the default Chromium installation is a **snap package**. Snap's AppArmor confinement interferes with how OpenClaw spawns and monitors the browser process.
The `apt install chromium` command installs a stub package that redirects to snap:
```
@@ -34,7 +34,7 @@ sudo dpkg -i google-chrome-stable_current_amd64.deb
sudo apt --fix-broken install -y # if there are dependency errors
```
Then update your Moltbot config (`~/.clawdbot/moltbot.json`):
Then update your OpenClaw config (`~/.openclaw/openclaw.json`):
```json
{
@@ -49,7 +49,7 @@ Then update your Moltbot config (`~/.clawdbot/moltbot.json`):
### Solution 2: Use Snap Chromium with Attach-Only Mode
If you must use snap Chromium, configure Moltbot to attach to a manually-started browser:
If you must use snap Chromium, configure OpenClaw to attach to a manually-started browser:
1. Update config:
```json
@@ -67,19 +67,19 @@ If you must use snap Chromium, configure Moltbot to attach to a manually-started
```bash
chromium-browser --headless --no-sandbox --disable-gpu \
--remote-debugging-port=18800 \
--user-data-dir=$HOME/.clawdbot/browser/clawd/user-data \
--user-data-dir=$HOME/.openclaw/browser/openclaw/user-data \
about:blank &
```
3. Optionally create a systemd user service to auto-start Chrome:
```ini
# ~/.config/systemd/user/clawd-browser.service
# ~/.config/systemd/user/openclaw-browser.service
[Unit]
Description=Clawd Browser (Chrome CDP)
Description=OpenClaw Browser (Chrome CDP)
After=network.target
[Service]
ExecStart=/snap/bin/chromium --headless --no-sandbox --disable-gpu --remote-debugging-port=18800 --user-data-dir=%h/.clawdbot/browser/clawd/user-data about:blank
ExecStart=/snap/bin/chromium --headless --no-sandbox --disable-gpu --remote-debugging-port=18800 --user-data-dir=%h/.openclaw/browser/openclaw/user-data about:blank
Restart=on-failure
RestartSec=5
@@ -87,7 +87,7 @@ RestartSec=5
WantedBy=default.target
```
Enable with: `systemctl --user enable --now clawd-browser.service`
Enable with: `systemctl --user enable --now openclaw-browser.service`
### Verifying the Browser Works
@@ -115,15 +115,15 @@ curl -s http://127.0.0.1:18791/tabs
### Problem: "Chrome extension relay is running, but no tab is connected"
You’re using the `chrome` profile (extension relay). It expects the Moltbot
You’re using the `chrome` profile (extension relay). It expects the OpenClaw
browser extension to be attached to a live tab.
Fix options:
1. **Use the managed browser:** `moltbot browser start --browser-profile clawd`
(or set `browser.defaultProfile: "clawd"`).
1. **Use the managed browser:** `openclaw browser start --browser-profile openclaw`
(or set `browser.defaultProfile: "openclaw"`).
2. **Use the extension relay:** install the extension, open a tab, and click the
Moltbot extension icon to attach it.
OpenClaw extension icon to attach it.
Notes:
- The `chrome` profile uses your **system default Chromium browser** when possible.
- Local `clawd` profiles auto-assign `cdpPort`/`cdpUrl`; only set those for remote CDP.
- Local `openclaw` profiles auto-assign `cdpPort`/`cdpUrl`; only set those for remote CDP.

12
docs/tools/browser-login.md
View File

@@ -9,7 +9,7 @@ read_when:
## Manual login (recommended)
When a site requires login, **sign in manually** in the **host** browser profile (the clawd browser).
When a site requires login, **sign in manually** in the **host** browser profile (the openclaw browser).
Do **not** give the model your credentials. Automated logins often trigger anti‑bot defenses and can lock the account.
@@ -17,7 +17,7 @@ Back to the main browser docs: [Browser](/tools/browser).
## Which Chrome profile is used?
Moltbot controls a **dedicated Chrome profile** (named `clawd`, orange‑tinted UI). This is separate from your daily browser profile.
OpenClaw controls a **dedicated Chrome profile** (named `openclaw`, orange‑tinted UI). This is separate from your daily browser profile.
Two easy ways to access it:
@@ -25,11 +25,11 @@ Two easy ways to access it:
2) **Open it via CLI**:
```bash
moltbot browser start
moltbot browser open https://x.com
openclaw browser start
openclaw browser open https://x.com
```
If you have multiple profiles, pass `--browser-profile <name>` (the default is `clawd`).
If you have multiple profiles, pass `--browser-profile <name>` (the default is `openclaw`).
## X/Twitter: recommended flow
@@ -61,7 +61,7 @@ If the agent is sandboxed, the browser tool defaults to the sandbox. To allow ho
Then target the host browser:
```bash
moltbot browser open https://x.com --browser-profile clawd --target host
openclaw browser open https://x.com --browser-profile openclaw --target host
```
Or disable sandboxing for the agent that posts updates.

252
docs/tools/browser.md
View File

@@ -2,29 +2,29 @@
summary: "Integrated browser control service + action commands"
read_when:
- Adding agent-controlled browser automation
- Debugging why clawd is interfering with your own Chrome
- Debugging why openclaw is interfering with your own Chrome
- Implementing browser settings + lifecycle in the macOS app
---
# Browser (clawd-managed)
# Browser (openclaw-managed)
Moltbot can run a **dedicated Chrome/Brave/Edge/Chromium profile** that the agent controls.
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).
Beginner view:
- Think of it as a **separate, agent-only browser**.
- The `clawd` profile does **not** touch your personal browser profile.
- The `openclaw` profile does **not** touch your personal browser profile.
- The agent can **open tabs, read pages, click, and type** in a safe lane.
- The default `chrome` profile uses the **system default Chromium browser** via the
extension relay; switch to `clawd` for the isolated managed browser.
extension relay; switch to `openclaw` for the isolated managed browser.
## What you get
- A separate browser profile named **clawd** (orange accent by default).
- A separate browser profile named **openclaw** (orange accent by default).
- Deterministic tab control (list/open/focus/close).
- Agent actions (click/type/drag/select), snapshots, screenshots, PDFs.
- Optional multi-profile support (`clawd`, `work`, `remote`, ...).
- Optional multi-profile support (`openclaw`, `work`, `remote`, ...).
This browser is **not** your daily driver. It is a safe, isolated surface for
agent automation and verification.
@@ -32,26 +32,26 @@ agent automation and verification.
## Quick start
```bash
moltbot browser --browser-profile clawd status
moltbot browser --browser-profile clawd start
moltbot browser --browser-profile clawd open https://example.com
moltbot browser --browser-profile clawd snapshot
openclaw browser --browser-profile openclaw status
openclaw browser --browser-profile openclaw start
openclaw browser --browser-profile openclaw open https://example.com
openclaw browser --browser-profile openclaw snapshot
```
If you get “Browser disabled”, enable it in config (see below) and restart the
Gateway.
## Profiles: `clawd` vs `chrome`
## Profiles: `openclaw` vs `chrome`
- `clawd`: managed, isolated browser (no extension required).
- `chrome`: extension relay to your **system browser** (requires the Moltbot
- `openclaw`: managed, isolated browser (no extension required).
- `chrome`: extension relay to your **system browser** (requires the OpenClaw
extension to be attached to a tab).
Set `browser.defaultProfile: "clawd"` if you want managed mode by default.
Set `browser.defaultProfile: "openclaw"` if you want managed mode by default.
## Configuration
Browser settings live in `~/.clawdbot/moltbot.json`.
Browser settings live in `~/.openclaw/openclaw.json`.
```json5
{
@@ -67,7 +67,7 @@ Browser settings live in `~/.clawdbot/moltbot.json`.
attachOnly: false,
executablePath: "/Applications/Brave Browser.app/Contents/MacOS/Brave Browser",
profiles: {
clawd: { cdpPort: 18800, color: "#FF4500" },
openclaw: { cdpPort: 18800, color: "#FF4500" },
work: { cdpPort: 18801, color: "#0066CC" },
remote: { cdpUrl: "http://10.0.0.42:9222", color: "#00AA00" }
}
@@ -78,27 +78,27 @@ Browser settings live in `~/.clawdbot/moltbot.json`.
Notes:
- The browser control service binds to loopback on a port derived from `gateway.port`
(default: `18791`, which is gateway + 2). The relay uses the next port (`18792`).
- If you override the Gateway port (`gateway.port` or `CLAWDBOT_GATEWAY_PORT`),
- If you override the Gateway port (`gateway.port` or `OPENCLAW_GATEWAY_PORT`),
the derived browser ports shift to stay in the same “family”.
- `cdpUrl` defaults to the relay port when unset.
- `remoteCdpTimeoutMs` applies to remote (non-loopback) CDP reachability checks.
- `remoteCdpHandshakeTimeoutMs` applies to remote CDP WebSocket reachability checks.
- `attachOnly: true` means “never launch a local browser; only attach if it is already running.”
- `color` + per-profile `color` tint the browser UI so you can see which profile is active.
- Default profile is `chrome` (extension relay). Use `defaultProfile: "clawd"` for the managed browser.
- Default profile is `chrome` (extension relay). Use `defaultProfile: "openclaw"` for the managed browser.
- Auto-detect order: system default browser if Chromium-based; otherwise Chrome → Brave → Edge → Chromium → Chrome Canary.
- Local `clawd` profiles auto-assign `cdpPort`/`cdpUrl` — set those only for remote CDP.
- Local `openclaw` profiles auto-assign `cdpPort`/`cdpUrl` — set those only for remote CDP.
## Use Brave (or another Chromium-based browser)
If your **system default** browser is Chromium-based (Chrome/Brave/Edge/etc),
Moltbot uses it automatically. Set `browser.executablePath` to override
OpenClaw uses it automatically. Set `browser.executablePath` to override
auto-detection:
CLI example:
```bash
moltbot config set browser.executablePath "/usr/bin/google-chrome"
openclaw config set browser.executablePath "/usr/bin/google-chrome"
```
```json5
@@ -129,19 +129,19 @@ moltbot config set browser.executablePath "/usr/bin/google-chrome"
- **Local control (default):** the Gateway starts the loopback control service and can launch a local browser.
- **Remote control (node host):** run a node host on the machine that has the browser; the Gateway proxies browser actions to it.
- **Remote CDP:** set `browser.profiles.<name>.cdpUrl` (or `browser.cdpUrl`) to
attach to a remote Chromium-based browser. In this case, Moltbot will not launch a local browser.
attach to a remote Chromium-based browser. In this case, OpenClaw will not launch a local browser.
Remote CDP URLs can include auth:
- Query tokens (e.g., `https://provider.example?token=<token>`)
- HTTP Basic auth (e.g., `https://user:pass@provider.example`)
Moltbot preserves the auth when calling `/json/*` endpoints and when connecting
OpenClaw preserves the auth when calling `/json/*` endpoints and when connecting
to the CDP WebSocket. Prefer environment variables or secrets managers for
tokens instead of committing them to config files.
## Node browser proxy (zero-config default)
If you run a **node host** on the machine that has your browser, Moltbot can
If you run a **node host** on the machine that has your browser, OpenClaw can
auto-route browser tool calls to that node without any extra browser config.
This is the default path for remote gateways.
@@ -155,7 +155,7 @@ Notes:
## Browserless (hosted remote CDP)
[Browserless](https://browserless.io) is a hosted Chromium service that exposes
CDP endpoints over HTTPS. You can point a Moltbot browser profile at a
CDP endpoints over HTTPS. You can point a OpenClaw browser profile at a
Browserless region endpoint and authenticate with your API key.
Example:
@@ -193,13 +193,13 @@ Remote CDP tips:
## Profiles (multi-browser)
Moltbot supports multiple named profiles (routing configs). Profiles can be:
- **clawd-managed**: a dedicated Chromium-based browser instance with its own user data directory + CDP port
OpenClaw supports multiple named profiles (routing configs). Profiles can be:
- **openclaw-managed**: a dedicated Chromium-based browser instance with its own user data directory + CDP port
- **remote**: an explicit CDP URL (Chromium-based browser running elsewhere)
- **extension relay**: your existing Chrome tab(s) via the local relay + Chrome extension
Defaults:
- The `clawd` profile is auto-created if missing.
- The `openclaw` profile is auto-created if missing.
- The `chrome` profile is built-in for the Chrome extension relay (points at `http://127.0.0.1:18792` by default).
- Local CDP ports allocate from **18800–18899** by default.
- Deleting a profile moves its local data directory to Trash.
@@ -208,14 +208,14 @@ All control endpoints accept `?profile=<name>`; the CLI uses `--browser-profile`
## Chrome extension relay (use your existing Chrome)
Moltbot can also drive **your existing Chrome tabs** (no separate “clawd” Chrome instance) via a local CDP relay + a Chrome extension.
OpenClaw can also drive **your existing Chrome tabs** (no separate “openclaw” Chrome instance) via a local CDP relay + a Chrome extension.
Full guide: [Chrome extension](/tools/chrome-extension)
Flow:
- The Gateway runs locally (same machine) or a node host runs on the browser machine.
- A local **relay server** listens at a loopback `cdpUrl` (default: `http://127.0.0.1:18792`).
- You click the **Moltbot Browser Relay** extension icon on a tab to attach (it does not auto-attach).
- You click the **OpenClaw Browser Relay** extension icon on a tab to attach (it does not auto-attach).
- The agent controls that tab via the normal `browser` tool, by selecting the right profile.
If the Gateway runs elsewhere, run a node host on the browser machine so the Gateway can proxy browser actions.
@@ -232,21 +232,21 @@ Chrome extension relay takeover requires host browser control, so either:
1) Load the extension (dev/unpacked):
```bash
moltbot browser extension install
openclaw browser extension install
```
- Chrome → `chrome://extensions` → enable “Developer mode”
- “Load unpacked” → select the directory printed by `moltbot browser extension path`
- “Load unpacked” → select the directory printed by `openclaw browser extension path`
- Pin the extension, then click it on the tab you want to control (badge shows `ON`).
2) Use it:
- CLI: `moltbot browser --browser-profile chrome tabs`
- CLI: `openclaw browser --browser-profile chrome tabs`
- Agent tool: `browser` with `profile="chrome"`
Optional: if you want a different name or relay port, create your own profile:
```bash
moltbot browser create-profile \
openclaw browser create-profile \
--name my-chrome \
--driver extension \
--cdp-url http://127.0.0.1:18792 \
@@ -265,7 +265,7 @@ Notes:
## Browser selection
When launching locally, Moltbot picks the first available:
When launching locally, OpenClaw picks the first available:
1. Chrome
2. Brave
3. Edge
@@ -302,12 +302,12 @@ All endpoints accept `?profile=<name>`.
Some features (navigate/act/AI snapshot/role snapshot, element screenshots, PDF) require
Playwright. If Playwright isn’t installed, those endpoints return a clear 501
error. ARIA snapshots and basic screenshots still work for clawd-managed Chrome.
error. ARIA snapshots and basic screenshots still work for openclaw-managed Chrome.
For the Chrome extension relay driver, ARIA snapshots and screenshots require Playwright.
If you see `Playwright is not available in this gateway build`, install the full
Playwright package (not `playwright-core`) and restart the gateway, or reinstall
Moltbot with browser support.
OpenClaw with browser support.
## How it works (internal)
@@ -327,76 +327,76 @@ All commands accept `--browser-profile <name>` to target a specific profile.
All commands also accept `--json` for machine-readable output (stable payloads).
Basics:
- `moltbot browser status`
- `moltbot browser start`
- `moltbot browser stop`
- `moltbot browser tabs`
- `moltbot browser tab`
- `moltbot browser tab new`
- `moltbot browser tab select 2`
- `moltbot browser tab close 2`
- `moltbot browser open https://example.com`
- `moltbot browser focus abcd1234`
- `moltbot browser close abcd1234`
- `openclaw browser status`
- `openclaw browser start`
- `openclaw browser stop`
- `openclaw browser tabs`
- `openclaw browser tab`
- `openclaw browser tab new`
- `openclaw browser tab select 2`
- `openclaw browser tab close 2`
- `openclaw browser open https://example.com`
- `openclaw browser focus abcd1234`
- `openclaw browser close abcd1234`
Inspection:
- `moltbot browser screenshot`
- `moltbot browser screenshot --full-page`
- `moltbot browser screenshot --ref 12`
- `moltbot browser screenshot --ref e12`
- `moltbot browser snapshot`
- `moltbot browser snapshot --format aria --limit 200`
- `moltbot browser snapshot --interactive --compact --depth 6`
- `moltbot browser snapshot --efficient`
- `moltbot browser snapshot --labels`
- `moltbot browser snapshot --selector "#main" --interactive`
- `moltbot browser snapshot --frame "iframe#main" --interactive`
- `moltbot browser console --level error`
- `moltbot browser errors --clear`
- `moltbot browser requests --filter api --clear`
- `moltbot browser pdf`
- `moltbot browser responsebody "**/api" --max-chars 5000`
- `openclaw browser screenshot`
- `openclaw browser screenshot --full-page`
- `openclaw browser screenshot --ref 12`
- `openclaw browser screenshot --ref e12`
- `openclaw browser snapshot`
- `openclaw browser snapshot --format aria --limit 200`
- `openclaw browser snapshot --interactive --compact --depth 6`
- `openclaw browser snapshot --efficient`
- `openclaw browser snapshot --labels`
- `openclaw browser snapshot --selector "#main" --interactive`
- `openclaw browser snapshot --frame "iframe#main" --interactive`
- `openclaw browser console --level error`
- `openclaw browser errors --clear`
- `openclaw browser requests --filter api --clear`
- `openclaw browser pdf`
- `openclaw browser responsebody "**/api" --max-chars 5000`
Actions:
- `moltbot browser navigate https://example.com`
- `moltbot browser resize 1280 720`
- `moltbot browser click 12 --double`
- `moltbot browser click e12 --double`
- `moltbot browser type 23 "hello" --submit`
- `moltbot browser press Enter`
- `moltbot browser hover 44`
- `moltbot browser scrollintoview e12`
- `moltbot browser drag 10 11`
- `moltbot browser select 9 OptionA OptionB`
- `moltbot browser download e12 /tmp/report.pdf`
- `moltbot browser waitfordownload /tmp/report.pdf`
- `moltbot browser upload /tmp/file.pdf`
- `moltbot browser fill --fields '[{"ref":"1","type":"text","value":"Ada"}]'`
- `moltbot browser dialog --accept`
- `moltbot browser wait --text "Done"`
- `moltbot browser wait "#main" --url "**/dash" --load networkidle --fn "window.ready===true"`
- `moltbot browser evaluate --fn '(el) => el.textContent' --ref 7`
- `moltbot browser highlight e12`
- `moltbot browser trace start`
- `moltbot browser trace stop`
- `openclaw browser navigate https://example.com`
- `openclaw browser resize 1280 720`
- `openclaw browser click 12 --double`
- `openclaw browser click e12 --double`
- `openclaw browser type 23 "hello" --submit`
- `openclaw browser press Enter`
- `openclaw browser hover 44`
- `openclaw browser scrollintoview e12`
- `openclaw browser drag 10 11`
- `openclaw browser select 9 OptionA OptionB`
- `openclaw browser download e12 /tmp/report.pdf`
- `openclaw browser waitfordownload /tmp/report.pdf`
- `openclaw browser upload /tmp/file.pdf`
- `openclaw browser fill --fields '[{"ref":"1","type":"text","value":"Ada"}]'`
- `openclaw browser dialog --accept`
- `openclaw browser wait --text "Done"`
- `openclaw browser wait "#main" --url "**/dash" --load networkidle --fn "window.ready===true"`
- `openclaw browser evaluate --fn '(el) => el.textContent' --ref 7`
- `openclaw browser highlight e12`
- `openclaw browser trace start`
- `openclaw browser trace stop`
State:
- `moltbot browser cookies`
- `moltbot browser cookies set session abc123 --url "https://example.com"`
- `moltbot browser cookies clear`
- `moltbot browser storage local get`
- `moltbot browser storage local set theme dark`
- `moltbot browser storage session clear`
- `moltbot browser set offline on`
- `moltbot browser set headers --json '{"X-Debug":"1"}'`
- `moltbot browser set credentials user pass`
- `moltbot browser set credentials --clear`
- `moltbot browser set geo 37.7749 -122.4194 --origin "https://example.com"`
- `moltbot browser set geo --clear`
- `moltbot browser set media dark`
- `moltbot browser set timezone America/New_York`
- `moltbot browser set locale en-US`
- `moltbot browser set device "iPhone 14"`
- `openclaw browser cookies`
- `openclaw browser cookies set session abc123 --url "https://example.com"`
- `openclaw browser cookies clear`
- `openclaw browser storage local get`
- `openclaw browser storage local set theme dark`
- `openclaw browser storage session clear`
- `openclaw browser set offline on`
- `openclaw browser set headers --json '{"X-Debug":"1"}'`
- `openclaw browser set credentials user pass`
- `openclaw browser set credentials --clear`
- `openclaw browser set geo 37.7749 -122.4194 --origin "https://example.com"`
- `openclaw browser set geo --clear`
- `openclaw browser set media dark`
- `openclaw browser set timezone America/New_York`
- `openclaw browser set locale en-US`
- `openclaw browser set device "iPhone 14"`
Notes:
- `upload` and `dialog` are **arming** calls; run them before the click/press
@@ -406,7 +406,7 @@ Notes:
- `--format ai` (default when Playwright is installed): returns an AI snapshot with numeric refs (`aria-ref="<n>"`).
- `--format aria`: returns the accessibility tree (no refs; inspection only).
- `--efficient` (or `--mode efficient`): compact role snapshot preset (interactive + compact + depth + lower maxChars).
- Config default (tool/CLI only): set `browser.snapshotDefaults.mode: "efficient"` to use efficient snapshots when the caller does not pass a mode (see [Gateway configuration](/gateway/configuration#browser-clawd-managed-browser)).
- Config default (tool/CLI only): set `browser.snapshotDefaults.mode: "efficient"` to use efficient snapshots when the caller does not pass a mode (see [Gateway configuration](/gateway/configuration#browser-openclaw-managed-browser)).
- Role snapshot options (`--interactive`, `--compact`, `--depth`, `--selector`) force a role-based snapshot with refs like `ref=e12`.
- `--frame "<iframe selector>"` scopes role snapshots to an iframe (pairs with role refs like `e12`).
- `--interactive` outputs a flat, easy-to-pick list of interactive elements (best for driving actions).
@@ -416,16 +416,16 @@ Notes:
## Snapshots and refs
Moltbot supports two “snapshot” styles:
OpenClaw supports two “snapshot” styles:
- **AI snapshot (numeric refs)**: `moltbot browser snapshot` (default; `--format ai`)
- **AI snapshot (numeric refs)**: `openclaw browser snapshot` (default; `--format ai`)
- Output: a text snapshot that includes numeric refs.
- Actions: `moltbot browser click 12`, `moltbot browser type 23 "hello"`.
- Actions: `openclaw browser click 12`, `openclaw browser type 23 "hello"`.
- Internally, the ref is resolved via Playwright’s `aria-ref`.
- **Role snapshot (role refs like `e12`)**: `moltbot browser snapshot --interactive` (or `--compact`, `--depth`, `--selector`, `--frame`)
- **Role snapshot (role refs like `e12`)**: `openclaw browser snapshot --interactive` (or `--compact`, `--depth`, `--selector`, `--frame`)
- Output: a role-based list/tree with `[ref=e12]` (and optional `[nth=1]`).
- Actions: `moltbot browser click e12`, `moltbot browser highlight e12`.
- Actions: `openclaw browser click e12`, `openclaw browser highlight e12`.
- Internally, the ref is resolved via `getByRole(...)` (plus `nth()` for duplicates).
- Add `--labels` to include a viewport screenshot with overlayed `e12` labels.
@@ -438,18 +438,18 @@ Ref behavior:
You can wait on more than just time/text:
- Wait for URL (globs supported by Playwright):
- `moltbot browser wait --url "**/dash"`
- `openclaw browser wait --url "**/dash"`
- Wait for load state:
- `moltbot browser wait --load networkidle`
- `openclaw browser wait --load networkidle`
- Wait for a JS predicate:
- `moltbot browser wait --fn "window.ready===true"`
- `openclaw browser wait --fn "window.ready===true"`
- Wait for a selector to become visible:
- `moltbot browser wait "#main"`
- `openclaw browser wait "#main"`
These can be combined:
```bash
moltbot browser wait "#main" \
openclaw browser wait "#main" \
--url "**/dash" \
--load networkidle \
--fn "window.ready===true" \
@@ -460,16 +460,16 @@ moltbot browser wait "#main" \
When an action fails (e.g. “not visible”, “strict mode violation”, “covered”):
1. `moltbot browser snapshot --interactive`
1. `openclaw browser snapshot --interactive`
2. Use `click <ref>` / `type <ref>` (prefer role refs in interactive mode)
3. If it still fails: `moltbot browser highlight <ref>` to see what Playwright is targeting
3. If it still fails: `openclaw browser highlight <ref>` to see what Playwright is targeting
4. If the page behaves oddly:
- `moltbot browser errors --clear`
- `moltbot browser requests --filter api --clear`
- `openclaw browser errors --clear`
- `openclaw browser requests --filter api --clear`
5. For deep debugging: record a trace:
- `moltbot browser trace start`
- `openclaw browser trace start`
- reproduce the issue
- `moltbot browser trace stop` (prints `TRACE:<path>`)
- `openclaw browser trace stop` (prints `TRACE:<path>`)
## JSON output
@@ -478,10 +478,10 @@ When an action fails (e.g. “not visible”, “strict mode violation”, “co
Examples:
```bash
moltbot browser status --json
moltbot browser snapshot --interactive --json
moltbot browser requests --filter api --json
moltbot browser cookies --json
openclaw browser status --json
openclaw browser snapshot --interactive --json
openclaw browser requests --filter api --json
openclaw browser cookies --json
```
Role snapshots in JSON include `refs` plus a small `stats` block (lines/chars/refs/interactive) so tools can reason about payload size and density.
@@ -504,8 +504,8 @@ These are useful for “make the site behave like X” workflows:
## Security & privacy
- The clawd browser profile may contain logged-in sessions; treat it as sensitive.
- `browser act kind=evaluate` / `moltbot browser evaluate` and `wait --fn`
- The openclaw browser profile may contain logged-in sessions; treat it as sensitive.
- `browser act kind=evaluate` / `openclaw browser evaluate` and `wait --fn`
execute arbitrary JavaScript in the page context. Prompt injection can steer
this. Disable it with `browser.evaluateEnabled=false` if you do not need it.
- For logins and anti-bot notes (X/Twitter, etc.), see [Browser login + X/Twitter posting](/tools/browser-login).
@@ -527,7 +527,7 @@ How it maps:
- `browser act` uses the snapshot `ref` IDs to click/type/drag/select.
- `browser screenshot` captures pixels (full page or element).
- `browser` accepts:
- `profile` to choose a named browser profile (clawd, chrome, or remote CDP).
- `profile` to choose a named browser profile (openclaw, chrome, or remote CDP).
- `target` (`sandbox` | `host` | `node`) to select where the browser lives.
- In sandboxed sessions, `target: "host"` requires `agents.defaults.sandbox.browser.allowHostControl=true`.
- If `target` is omitted: sandboxed sessions default to `sandbox`, non-sandbox sessions default to `host`.

34
docs/tools/chrome-extension.md
View File

@@ -1,5 +1,5 @@
---
summary: "Chrome extension: let Moltbot drive your existing Chrome tab"
summary: "Chrome extension: let OpenClaw drive your existing Chrome tab"
read_when:
- You want the agent to drive an existing Chrome tab (toolbar button)
- You need remote Gateway + local browser automation via Tailscale
@@ -8,7 +8,7 @@ read_when:
# Chrome extension (browser relay)
The Moltbot Chrome extension lets the agent control your **existing Chrome tabs** (your normal Chrome window) instead of launching a separate clawd-managed Chrome profile.
The OpenClaw Chrome extension lets the agent control your **existing Chrome tabs** (your normal Chrome window) instead of launching a separate openclaw-managed Chrome profile.
Attach/detach happens via a **single Chrome toolbar button**.
@@ -19,20 +19,20 @@ There are three parts:
- **Local relay server** (loopback CDP): bridges between the control server and the extension (`http://127.0.0.1:18792` by default)
- **Chrome MV3 extension**: attaches to the active tab using `chrome.debugger` and pipes CDP messages to the relay
Moltbot then controls the attached tab through the normal `browser` tool surface (selecting the right profile).
OpenClaw then controls the attached tab through the normal `browser` tool surface (selecting the right profile).
## Install / load (unpacked)
1) Install the extension to a stable local path:
```bash
moltbot browser extension install
openclaw browser extension install
```
2) Print the installed extension directory path:
```bash
moltbot browser extension path
openclaw browser extension path
```
3) Chrome → `chrome://extensions`
@@ -43,24 +43,24 @@ moltbot browser extension path
## Updates (no build step)
The extension ships inside the Moltbot release (npm package) as static files. There is no separate “build” step.
The extension ships inside the OpenClaw release (npm package) as static files. There is no separate “build” step.
After upgrading Moltbot:
- Re-run `moltbot browser extension install` to refresh the installed files under your Moltbot state directory.
After upgrading OpenClaw:
- Re-run `openclaw browser extension install` to refresh the installed files under your OpenClaw state directory.
- Chrome → `chrome://extensions` → click “Reload” on the extension.
## Use it (no extra config)
Moltbot ships with a built-in browser profile named `chrome` that targets the extension relay on the default port.
OpenClaw ships with a built-in browser profile named `chrome` that targets the extension relay on the default port.
Use it:
- CLI: `moltbot browser --browser-profile chrome tabs`
- CLI: `openclaw browser --browser-profile chrome tabs`
- Agent tool: `browser` with `profile="chrome"`
If you want a different name or a different relay port, create your own profile:
```bash
moltbot browser create-profile \
openclaw browser create-profile \
--name my-chrome \
--driver extension \
--cdp-url http://127.0.0.1:18792 \
@@ -69,7 +69,7 @@ moltbot browser create-profile \
## Attach / detach (toolbar button)
- Open the tab you want Moltbot to control.
- Open the tab you want OpenClaw to control.
- Click the extension icon.
- Badge shows `ON` when attached.
- Click again to detach.
@@ -82,7 +82,7 @@ moltbot browser create-profile \
## Badge + common errors
- `ON`: attached; Moltbot can drive that tab.
- `ON`: attached; OpenClaw can drive that tab.
- `…`: connecting to the local relay.
- `!`: relay not reachable (most common: browser relay server isn’t running on this machine).
@@ -131,7 +131,7 @@ Options:
Then ensure the tool isn’t denied by tool policy, and (if needed) call `browser` with `target="host"`.
Debugging: `moltbot sandbox explain`
Debugging: `openclaw sandbox explain`
## Remote access tips
@@ -140,9 +140,9 @@ Debugging: `moltbot sandbox explain`
## How “extension path” works
`moltbot browser extension path` prints the **installed** on-disk directory containing the extension files.
`openclaw browser extension path` prints the **installed** on-disk directory containing the extension files.
The CLI intentionally does **not** print a `node_modules` path. Always run `moltbot browser extension install` first to copy the extension to a stable location under your Moltbot state directory.
The CLI intentionally does **not** print a `node_modules` path. Always run `openclaw browser extension install` first to copy the extension to a stable location under your OpenClaw state directory.
If you move or delete that install directory, Chrome will mark the extension as broken until you reload it from a valid path.
@@ -154,7 +154,7 @@ This is powerful and risky. Treat it like giving the model “hands on your brow
- click/type/navigate in that tab
- read page content
- access whatever the tab’s logged-in session can access
- **This is not isolated** like the dedicated clawd-managed profile.
- **This is not isolated** like the dedicated openclaw-managed profile.
- If you attach to your daily-driver profile/tab, you’re granting access to that account state.
Recommendations:

14
docs/tools/clawdhub.md
View File

@@ -8,13 +8,13 @@ read_when:
# ClawdHub
ClawdHub is the **public skill registry for Moltbot**. It is a free service: all skills are public, open, and visible to everyone for sharing and reuse. A skill is just a folder with a `SKILL.md` file (plus supporting text files). You can browse skills in the web app or use the CLI to search, install, update, and publish skills.
ClawdHub is the **public skill registry for OpenClaw**. It is a free service: all skills are public, open, and visible to everyone for sharing and reuse. A skill is just a folder with a `SKILL.md` file (plus supporting text files). You can browse skills in the web app or use the CLI to search, install, update, and publish skills.
Site: [clawdhub.com](https://clawdhub.com)
## Who this is for (beginner-friendly)
If you want to add new capabilities to your Moltbot agent, ClawdHub is the easiest way to find and install skills. You do not need to know how the backend works. You can:
If you want to add new capabilities to your OpenClaw agent, ClawdHub is the easiest way to find and install skills. You do not need to know how the backend works. You can:
- Search for skills by plain language.
- Install a skill into your workspace.
@@ -28,7 +28,7 @@ If you want to add new capabilities to your Moltbot agent, ClawdHub is the easie
- `clawdhub search "calendar"`
3) Install a skill:
- `clawdhub install <skill-slug>`
4) Start a new Moltbot session so it picks up the new skill.
4) Start a new OpenClaw session so it picks up the new skill.
## Install the CLI
@@ -42,9 +42,9 @@ npm i -g clawdhub
pnpm add -g clawdhub
```
## How it fits into Moltbot
## How it fits into OpenClaw
By default, the CLI installs skills into `./skills` under your current working directory. If a Moltbot workspace is configured, `clawdhub` falls back to that workspace unless you override `--workdir` (or `CLAWDHUB_WORKDIR`). Moltbot loads workspace skills from `<workspace>/skills` and will pick them up in the **next** session. If you already use `~/.clawdbot/skills` or bundled skills, workspace skills take precedence.
By default, the CLI installs skills into `./skills` under your current working directory. If a OpenClaw workspace is configured, `clawdhub` falls back to that workspace unless you override `--workdir` (or `CLAWDHUB_WORKDIR`). OpenClaw loads workspace skills from `<workspace>/skills` and will pick them up in the **next** session. If you already use `~/.openclaw/skills` or bundled skills, workspace skills take precedence.
For more detail on how skills are loaded, shared, and gated, see
[Skills](/tools/skills).
@@ -63,7 +63,7 @@ For more detail on how skills are loaded, shared, and gated, see
Global options (apply to all commands):
- `--workdir <dir>`: Working directory (default: current dir; falls back to Moltbot workspace).
- `--workdir <dir>`: Working directory (default: current dir; falls back to OpenClaw workspace).
- `--dir <dir>`: Skills directory, relative to workdir (default: `skills`).
- `--site <url>`: Site base URL (browser login).
- `--registry <url>`: Registry API base URL.
@@ -177,7 +177,7 @@ Updates compare the local skill contents to registry versions using a content ha
### Sync scanning and fallback roots
`clawdhub sync` scans your current workdir first. If no skills are found, it falls back to known legacy locations (for example `~/moltbot/skills` and `~/.clawdbot/skills`). This is designed to find older skill installs without extra flags.
`clawdhub sync` scans your current workdir first. If no skills are found, it falls back to known legacy locations (for example `~/openclaw/skills` and `~/.openclaw/skills`). This is designed to find older skill installs without extra flags.
### Storage and lockfile

12
docs/tools/creating-skills.md
View File

@@ -1,6 +1,6 @@
# Creating Custom Skills 🛠
Moltbot is designed to be easily extensible. "Skills" are the primary way to add new capabilities to your assistant.
OpenClaw is designed to be easily extensible. "Skills" are the primary way to add new capabilities to your assistant.
## What is a Skill?
A skill is a directory containing a `SKILL.md` file (which provides instructions and tool definitions to the LLM) and optionally some scripts or resources.
@@ -8,9 +8,9 @@ A skill is a directory containing a `SKILL.md` file (which provides instructions
## Step-by-Step: Your First Skill
### 1. Create the Directory
Skills live in your workspace, usually `~/clawd/skills/`. Create a new folder for your skill:
Skills live in your workspace, usually `~/.openclaw/workspace/skills/`. Create a new folder for your skill:
```bash
mkdir -p ~/clawd/skills/hello-world
mkdir -p ~/.openclaw/workspace/skills/hello-world
```
### 2. Define the `SKILL.md`
@@ -29,13 +29,13 @@ When the user asks for a greeting, use the `echo` tool to say "Hello from your c
### 3. Add Tools (Optional)
You can define custom tools in the frontmatter or instruct the agent to use existing system tools (like `bash` or `browser`).
### 4. Refresh Moltbot
Ask your agent to "refresh skills" or restart the gateway. Moltbot will discover the new directory and index the `SKILL.md`.
### 4. Refresh OpenClaw
Ask your agent to "refresh skills" or restart the gateway. OpenClaw will discover the new directory and index the `SKILL.md`.
## Best Practices
- **Be Concise**: Instruct the model on *what* to do, not how to be an AI.
- **Safety First**: If your skill uses `bash`, ensure the prompts don't allow arbitrary command injection from untrusted user input.
- **Test Locally**: Use `moltbot agent --message "use my new skill"` to test.
- **Test Locally**: Use `openclaw agent --message "use my new skill"` to test.
## Shared Skills
You can also browse and contribute skills to [ClawdHub](https://clawdhub.com).

10
docs/tools/exec-approvals.md
View File

@@ -20,7 +20,7 @@ resolved by the **ask fallback** (default: deny).
## Where it applies
Exec approvals are enforced locally on the execution host:
- **gateway host** → `moltbot` process on the gateway machine
- **gateway host** → `openclaw` process on the gateway machine
- **node host** → node runner (macOS companion app or headless node host)
macOS split:
@@ -31,14 +31,14 @@ macOS split:
Approvals live in a local JSON file on the execution host:
`~/.clawdbot/exec-approvals.json`
`~/.openclaw/exec-approvals.json`
Example schema:
```json
{
"version": 1,
"socket": {
"path": "~/.clawdbot/exec-approvals.sock",
"path": "~/.openclaw/exec-approvals.sock",
"token": "base64url-token"
},
"defaults": {
@@ -131,9 +131,9 @@ per pattern so you can keep the list tidy.
The target selector chooses **Gateway** (local approvals) or a **Node**. Nodes
must advertise `system.execApprovals.get/set` (macOS app or headless node host).
If a node does not advertise exec approvals yet, edit its local
`~/.clawdbot/exec-approvals.json` directly.
`~/.openclaw/exec-approvals.json` directly.
CLI: `moltbot approvals` supports gateway or node editing (see [Approvals CLI](/cli/approvals)).
CLI: `openclaw approvals` supports gateway or node editing (see [Approvals CLI](/cli/approvals)).
## Approval flow

8
docs/tools/exec.md
View File

@@ -29,7 +29,7 @@ Background sessions are scoped per agent; `process` only sees sessions from the
Notes:
- `host` defaults to `sandbox`.
- `elevated` is ignored when sandboxing is off (exec already runs on the host).
- `gateway`/`node` approvals are controlled by `~/.clawdbot/exec-approvals.json`.
- `gateway`/`node` approvals are controlled by `~/.openclaw/exec-approvals.json`.
- `node` requires a paired node (companion app or headless node host).
- If multiple nodes are available, set `exec.node` or `tools.exec.node` to select one.
- On non-Windows hosts, exec uses `SHELL` when set; if `SHELL` is `fish`, it prefers `bash` (or `sh`)
@@ -67,7 +67,7 @@ Example:
- macOS: `/opt/homebrew/bin`, `/usr/local/bin`, `/usr/bin`, `/bin`
- Linux: `/usr/local/bin`, `/usr/bin`, `/bin`
- `host=sandbox`: runs `sh -lc` (login shell) inside the container, so `/etc/profile` may reset `PATH`.
Moltbot prepends `env.PATH` after profile sourcing via an internal env var (no shell interpolation);
OpenClaw prepends `env.PATH` after profile sourcing via an internal env var (no shell interpolation);
`tools.exec.pathPrepend` applies here too.
- `host=node`: only env overrides you pass are sent to the node. `tools.exec.pathPrepend` only applies
if the exec call already sets `env.PATH`. Headless node hosts accept `PATH` only when it prepends
@@ -76,8 +76,8 @@ Example:
Per-agent node binding (use the agent list index in config):
```bash
moltbot config get agents.list
moltbot config set agents.list[0].tools.exec.node "node-id-or-name"
openclaw config get agents.list
openclaw config set agents.list[0].tools.exec.node "node-id-or-name"
```
Control UI: the Nodes tab includes a small “Exec node binding” panel for the same settings.

4
docs/tools/firecrawl.md
View File

@@ -8,7 +8,7 @@ read_when:
# Firecrawl
Moltbot can use **Firecrawl** as a fallback extractor for `web_fetch`. It is a hosted
OpenClaw can use **Firecrawl** as a fallback extractor for `web_fetch`. It is a hosted
content extraction service that supports bot circumvention and caching, which helps
with JS-heavy sites or pages that block plain HTTP fetches.
@@ -44,7 +44,7 @@ Notes:
## Stealth / bot circumvention
Firecrawl exposes a **proxy mode** parameter for bot circumvention (`basic`, `stealth`, or `auto`).
Moltbot always uses `proxy: "auto"` plus `storeInCache: true` for Firecrawl requests.
OpenClaw always uses `proxy: "auto"` plus `storeInCache: true` for Firecrawl requests.
If proxy is omitted, Firecrawl defaults to `auto`. `auto` retries with stealth proxies if a basic attempt fails, which may use more credits
than basic-only scraping.

26
docs/tools/index.md
View File

@@ -1,19 +1,19 @@
---
summary: "Agent tool surface for Moltbot (browser, canvas, nodes, message, cron) replacing legacy `moltbot-*` skills"
summary: "Agent tool surface for OpenClaw (browser, canvas, nodes, message, cron) replacing legacy `openclaw-*` skills"
read_when:
- Adding or modifying agent tools
- Retiring or changing `moltbot-*` skills
- Retiring or changing `openclaw-*` skills
---
# Tools (Moltbot)
# Tools (OpenClaw)
Moltbot exposes **first-class agent tools** for browser, canvas, nodes, and cron.
These replace the old `moltbot-*` skills: the tools are typed, no shelling,
OpenClaw exposes **first-class agent tools** for browser, canvas, nodes, and cron.
These replace the old `openclaw-*` skills: the tools are typed, no shelling,
and the agent should rely on them directly.
## Disabling tools
You can globally allow/deny tools via `tools.allow` / `tools.deny` in `moltbot.json`
You can globally allow/deny tools via `tools.allow` / `tools.deny` in `openclaw.json`
(deny wins). This prevents disallowed tools from being sent to model providers.
```json5
@@ -25,7 +25,7 @@ You can globally allow/deny tools via `tools.allow` / `tools.deny` in `moltbot.j
Notes:
- Matching is case-insensitive.
- `*` wildcards are supported (`"*"` means all tools).
- If `tools.allow` only references unknown or unloaded plugin tool names, Moltbot logs a warning and ignores the allowlist so core tools stay available.
- If `tools.allow` only references unknown or unloaded plugin tool names, OpenClaw logs a warning and ignores the allowlist so core tools stay available.
## Tool profiles (base allowlist)
@@ -141,7 +141,7 @@ Available groups:
- `group:automation`: `cron`, `gateway`
- `group:messaging`: `message`
- `group:nodes`: `nodes`
- `group:moltbot`: all built-in Moltbot tools (excludes provider plugins)
- `group:openclaw`: all built-in OpenClaw tools (excludes provider plugins)
Example (allow only file tools + browser):
```json5
@@ -190,7 +190,7 @@ Notes:
- If `process` is disallowed, `exec` runs synchronously and ignores `yieldMs`/`background`.
- `elevated` is gated by `tools.elevated` plus any `agents.list[].tools.elevated` override (both must allow) and is an alias for `host=gateway` + `security=full`.
- `elevated` only changes behavior when the agent is sandboxed (otherwise it’s a no-op).
- `host=node` can target a macOS companion app or a headless node host (`moltbot node run`).
- `host=node` can target a macOS companion app or a headless node host (`openclaw node run`).
- gateway/node approvals and allowlists: [Exec approvals](/tools/exec-approvals).
### `process`
@@ -212,7 +212,7 @@ Core parameters:
- `count` (1–10; default from `tools.web.search.maxResults`)
Notes:
- Requires a Brave API key (recommended: `moltbot configure --section web`, or set `BRAVE_API_KEY`).
- Requires a Brave API key (recommended: `openclaw configure --section web`, or set `BRAVE_API_KEY`).
- Enable via `tools.web.search.enabled`.
- Responses are cached (default 15 min).
- See [Web tools](/tools/web) for setup.
@@ -233,7 +233,7 @@ Notes:
- See [Firecrawl](/tools/firecrawl) for the optional anti-bot fallback.
### `browser`
Control the dedicated clawd browser.
Control the dedicated OpenClaw-managed browser.
Core actions:
- `status`, `start`, `stop`, `tabs`, `open`, `focus`, `close`
@@ -279,7 +279,7 @@ Notes:
- Uses gateway `node.invoke` under the hood.
- If no `node` is provided, the tool picks a default (single connected node or local mac node).
- A2UI is v0.8 only (no `createSurface`); the CLI rejects v0.9 JSONL with line errors.
- Quick smoke: `moltbot nodes canvas a2ui push --node <id> --text "Hello from A2UI"`.
- Quick smoke: `openclaw nodes canvas a2ui push --node <id> --text "Hello from A2UI"`.
### `nodes`
Discover and target paired nodes; send notifications; capture camera/screen.
@@ -366,7 +366,7 @@ Notes:
Restart or apply updates to the running Gateway process (in-place).
Core actions:
- `restart` (authorizes + sends `SIGUSR1` for in-process restart; `moltbot gateway` restart in-place)
- `restart` (authorizes + sends `SIGUSR1` for in-process restart; `openclaw gateway` restart in-place)
- `config.get` / `config.schema`
- `config.apply` (validate + write config + restart + wake)
- `config.patch` (merge partial update + restart + wake)

4
docs/tools/llm-task.md
View File

@@ -11,7 +11,7 @@ read_when:
returns structured output (optionally validated against JSON Schema).
This is ideal for workflow engines like Lobster: you can add a single LLM step
without writing custom Moltbot code for each workflow.
without writing custom OpenClaw code for each workflow.
## Enable the plugin
@@ -87,7 +87,7 @@ Returns `details.json` containing the parsed JSON (and validates against
## Example: Lobster workflow step
```lobster
clawd.invoke --tool llm-task --action json --args-json '{
openclaw.invoke --tool llm-task --action json --args-json '{
"prompt": "Given the input email, return intent and draft.",
"input": {
"subject": "Hello",

26
docs/tools/lobster.md
View File

@@ -1,7 +1,7 @@
---
title: Lobster
summary: "Typed workflow runtime for Moltbot with resumable approval gates."
description: Typed workflow runtime for Moltbot — composable pipelines with approval gates.
summary: "Typed workflow runtime for OpenClaw with resumable approval gates."
description: Typed workflow runtime for OpenClaw — composable pipelines with approval gates.
read_when:
- You want deterministic multi-step workflows with explicit approvals
- You need to resume a workflow without re-running earlier steps
@@ -9,7 +9,7 @@ read_when:
# Lobster
Lobster is a workflow shell that lets Moltbot run multi-step tool sequences as a single, deterministic operation with explicit approval checkpoints.
Lobster is a workflow shell that lets OpenClaw run multi-step tool sequences as a single, deterministic operation with explicit approval checkpoints.
## Hook
@@ -19,7 +19,7 @@ Your assistant can build the tools that manage itself. Ask for a workflow, and 3
Today, complex workflows require many back-and-forth tool calls. Each call costs tokens, and the LLM has to orchestrate every step. Lobster moves that orchestration into a typed runtime:
- **One call instead of many**: Moltbot runs one Lobster tool call and gets a structured result.
- **One call instead of many**: OpenClaw runs one Lobster tool call and gets a structured result.
- **Approvals built in**: Side effects (send email, post comment) halt the workflow until explicitly approved.
- **Resumable**: Halted workflows return a token; approve and resume without re-running everything.
@@ -35,7 +35,7 @@ Lobster is intentionally small. The goal is not "a new language," it's a predict
## How it works
Moltbot launches the local `lobster` CLI in **tool mode** and parses a JSON envelope from stdout.
OpenClaw launches the local `lobster` CLI in **tool mode** and parses a JSON envelope from stdout.
If the pipeline pauses for approval, the tool returns a `resumeToken` so you can continue later.
## Pattern: small CLI + JSON pipes + approvals
@@ -72,7 +72,7 @@ Example: map input items into tool calls:
```bash
gog.gmail.search --query 'newer_than:1d' \
| clawd.invoke --tool message --action send --each --item-key message --args-json '{"provider":"telegram","to":"..."}'
| openclaw.invoke --tool message --action send --each --item-key message --args-json '{"provider":"telegram","to":"..."}'
```
## JSON-only LLM steps (llm-task)
@@ -104,7 +104,7 @@ Enable the tool:
Use it in a pipeline:
```lobster
clawd.invoke --tool llm-task --action json --args-json '{
openclaw.invoke --tool llm-task --action json --args-json '{
"prompt": "Given the input email, return intent and draft.",
"input": { "subject": "Hello", "body": "Can you help?" },
"schema": {
@@ -123,7 +123,7 @@ See [LLM Task](/tools/llm-task) for details and configuration options.
## Workflow files (.lobster)
Lobster can run YAML/JSON workflow files with `name`, `args`, `steps`, `env`, `condition`, and `approval` fields. In Moltbot tool calls, set `pipeline` to the file path.
Lobster can run YAML/JSON workflow files with `name`, `args`, `steps`, `env`, `condition`, and `approval` fields. In OpenClaw tool calls, set `pipeline` to the file path.
```yaml
name: inbox-triage
@@ -153,7 +153,7 @@ Notes:
## Install Lobster
Install the Lobster CLI on the **same host** that runs the Moltbot Gateway (see the [Lobster repo](https://github.com/moltbot/lobster)), and ensure `lobster` is on `PATH`.
Install the Lobster CLI on the **same host** that runs the OpenClaw Gateway (see the [Lobster repo](https://github.com/openclaw/lobster)), and ensure `lobster` is on `PATH`.
If you want to use a custom binary location, pass an **absolute** `lobsterPath` in the tool call.
## Enable the tool
@@ -190,7 +190,7 @@ Or per-agent:
Avoid using `tools.allow: ["lobster"]` unless you intend to run in restrictive allowlist mode.
Note: allowlists are opt-in for optional plugins. If your allowlist only names
plugin tools (like `lobster`), Moltbot keeps core tools enabled. To restrict core
plugin tools (like `lobster`), OpenClaw keeps core tools enabled. To restrict core
tools, include the core tools or groups you want in the allowlist too.
## Example: Email triage
@@ -198,12 +198,12 @@ tools, include the core tools or groups you want in the allowlist too.
Without Lobster:
```
User: "Check my email and draft replies"
→ clawd calls gmail.list
→ openclaw calls gmail.list
→ LLM summarizes
→ User: "draft replies to #2 and #5"
→ LLM drafts
→ User: "send #2"
→ clawd calls gmail.send
→ openclaw calls gmail.send
(repeat daily, no memory of what was triaged)
```
@@ -314,7 +314,7 @@ OpenProse pairs well with Lobster: use `/prose` to orchestrate multi-agent prep,
## Safety
- **Local subprocess only** — no network calls from the plugin itself.
- **No secrets** — Lobster doesn't manage OAuth; it calls clawd tools that do.
- **No secrets** — Lobster doesn't manage OAuth; it calls OpenClaw tools that do.
- **Sandbox-aware** — disabled when the tool context is sandboxed.
- **Hardened** — `lobsterPath` must be absolute if specified; timeouts and output caps enforced.

4
docs/tools/skills-config.md
View File

@@ -6,7 +6,7 @@ read_when:
---
# Skills Config
All skills-related configuration lives under `skills` in `~/.clawdbot/moltbot.json`.
All skills-related configuration lives under `skills` in `~/.openclaw/openclaw.json`.
```json5
{
@@ -60,7 +60,7 @@ Per-skill fields:
## Notes
- Keys under `entries` map to the skill name by default. If a skill defines
`metadata.moltbot.skillKey`, use that key instead.
`metadata.openclaw.skillKey`, use that key instead.
- Changes to skills are picked up on the next agent turn when the watcher is enabled.
### Sandboxed skills + env vars

62
docs/tools/skills.md
View File

@@ -4,31 +4,31 @@ read_when:
- Adding or modifying skills
- Changing skill gating or load rules
---
# Skills (Moltbot)
# Skills (OpenClaw)
Moltbot uses **[AgentSkills](https://agentskills.io)-compatible** skill folders to teach the agent how to use tools. Each skill is a directory containing a `SKILL.md` with YAML frontmatter and instructions. Moltbot loads **bundled skills** plus optional local overrides, and filters them at load time based on environment, config, and binary presence.
OpenClaw uses **[AgentSkills](https://agentskills.io)-compatible** skill folders to teach the agent how to use tools. Each skill is a directory containing a `SKILL.md` with YAML frontmatter and instructions. OpenClaw loads **bundled skills** plus optional local overrides, and filters them at load time based on environment, config, and binary presence.
## Locations and precedence
Skills are loaded from **three** places:
1) **Bundled skills**: shipped with the install (npm package or Moltbot.app)
2) **Managed/local skills**: `~/.clawdbot/skills`
1) **Bundled skills**: shipped with the install (npm package or OpenClaw.app)
2) **Managed/local skills**: `~/.openclaw/skills`
3) **Workspace skills**: `<workspace>/skills`
If a skill name conflicts, precedence is:
`<workspace>/skills` (highest) → `~/.clawdbot/skills` → bundled skills (lowest)
`<workspace>/skills` (highest) → `~/.openclaw/skills` → bundled skills (lowest)
Additionally, you can configure extra skill folders (lowest precedence) via
`skills.load.extraDirs` in `~/.clawdbot/moltbot.json`.
`skills.load.extraDirs` in `~/.openclaw/openclaw.json`.
## Per-agent vs shared skills
In **multi-agent** setups, each agent has its own workspace. That means:
- **Per-agent skills** live in `<workspace>/skills` for that agent only.
- **Shared skills** live in `~/.clawdbot/skills` (managed/local) and are visible
- **Shared skills** live in `~/.openclaw/skills` (managed/local) and are visible
to **all agents** on the same machine.
- **Shared folders** can also be added via `skills.load.extraDirs` (lowest
precedence) if you want a common skills pack used by multiple agents.
@@ -39,15 +39,15 @@ applies: workspace wins, then managed/local, then bundled.
## Plugins + skills
Plugins can ship their own skills by listing `skills` directories in
`moltbot.plugin.json` (paths relative to the plugin root). Plugin skills load
`openclaw.plugin.json` (paths relative to the plugin root). Plugin skills load
when the plugin is enabled and participate in the normal skill precedence rules.
You can gate them via `metadata.moltbot.requires.config` on the plugin’s config
You can gate them via `metadata.openclaw.requires.config` on the plugin’s config
entry. See [Plugins](/plugin) for discovery/config and [Tools](/tools) for the
tool surface those skills teach.
## ClawdHub (install + sync)
ClawdHub is the public skills registry for Moltbot. Browse at
ClawdHub is the public skills registry for OpenClaw. Browse at
https://clawdhub.com. Use it to discover, install, update, and back up skills.
Full guide: [ClawdHub](/tools/clawdhub).
@@ -61,7 +61,7 @@ Common flows:
- `clawdhub sync --all`
By default, `clawdhub` installs into `./skills` under your current working
directory (or falls back to the configured Moltbot workspace). Moltbot picks
directory (or falls back to the configured OpenClaw workspace). OpenClaw picks
that up as `<workspace>/skills` on the next session.
## Security notes
@@ -89,7 +89,7 @@ Notes:
- `metadata` should be a **single-line JSON object**.
- Use `{baseDir}` in instructions to reference the skill folder path.
- Optional frontmatter keys:
- `homepage` — URL surfaced as “Website” in the macOS Skills UI (also supported via `metadata.moltbot.homepage`).
- `homepage` — URL surfaced as “Website” in the macOS Skills UI (also supported via `metadata.openclaw.homepage`).
- `user-invocable` — `true|false` (default: `true`). When `true`, the skill is exposed as a user slash command.
- `disable-model-invocation` — `true|false` (default: `false`). When `true`, the skill is excluded from the model prompt (still available via user invocation).
- `command-dispatch` — `tool` (optional). When set to `tool`, the slash command bypasses the model and dispatches directly to a tool.
@@ -101,17 +101,17 @@ Notes:
## Gating (load-time filters)
Moltbot **filters skills at load time** using `metadata` (single-line JSON):
OpenClaw **filters skills at load time** using `metadata` (single-line JSON):
```markdown
---
name: nano-banana-pro
description: Generate or edit images via Gemini 3 Pro Image
metadata: {"moltbot":{"requires":{"bins":["uv"],"env":["GEMINI_API_KEY"],"config":["browser.enabled"]},"primaryEnv":"GEMINI_API_KEY"}}
metadata: {"openclaw":{"requires":{"bins":["uv"],"env":["GEMINI_API_KEY"],"config":["browser.enabled"]},"primaryEnv":"GEMINI_API_KEY"}}
---
```
Fields under `metadata.moltbot`:
Fields under `metadata.openclaw`:
- `always: true` — always include the skill (skip other gates).
- `emoji` — optional emoji used by the macOS Skills UI.
- `homepage` — optional URL shown as “Website” in the macOS Skills UI.
@@ -119,7 +119,7 @@ Fields under `metadata.moltbot`:
- `requires.bins` — list; each must exist on `PATH`.
- `requires.anyBins` — list; at least one must exist on `PATH`.
- `requires.env` — list; env var must exist **or** be provided in config.
- `requires.config` — list of `moltbot.json` paths that must be truthy.
- `requires.config` — list of `openclaw.json` paths that must be truthy.
- `primaryEnv` — env var name associated with `skills.entries.<name>.apiKey`.
- `install` — optional array of installer specs used by the macOS Skills UI (brew/node/go/uv/download).
@@ -138,24 +138,24 @@ Installer example:
---
name: gemini
description: Use Gemini CLI for coding assistance and Google search lookups.
metadata: {"moltbot":{"emoji":"♊️","requires":{"bins":["gemini"]},"install":[{"id":"brew","kind":"brew","formula":"gemini-cli","bins":["gemini"],"label":"Install Gemini CLI (brew)"}]}}
metadata: {"openclaw":{"emoji":"♊️","requires":{"bins":["gemini"]},"install":[{"id":"brew","kind":"brew","formula":"gemini-cli","bins":["gemini"],"label":"Install Gemini CLI (brew)"}]}}
---
```
Notes:
- If multiple installers are listed, the gateway picks a **single** preferred option (brew when available, otherwise node).
- If all installers are `download`, Moltbot lists each entry so you can see the available artifacts.
- If all installers are `download`, OpenClaw lists each entry so you can see the available artifacts.
- Installer specs can include `os: ["darwin"|"linux"|"win32"]` to filter options by platform.
- Node installs honor `skills.install.nodeManager` in `moltbot.json` (default: npm; options: npm/pnpm/yarn/bun).
- Node installs honor `skills.install.nodeManager` in `openclaw.json` (default: npm; options: npm/pnpm/yarn/bun).
This only affects **skill installs**; the Gateway runtime should still be Node
(Bun is not recommended for WhatsApp/Telegram).
- Go installs: if `go` is missing and `brew` is available, the gateway installs Go via Homebrew first and sets `GOBIN` to Homebrew’s `bin` when possible.
- Download installs: `url` (required), `archive` (`tar.gz` | `tar.bz2` | `zip`), `extract` (default: auto when archive detected), `stripComponents`, `targetDir` (default: `~/.clawdbot/tools/<skillKey>`).
- Download installs: `url` (required), `archive` (`tar.gz` | `tar.bz2` | `zip`), `extract` (default: auto when archive detected), `stripComponents`, `targetDir` (default: `~/.openclaw/tools/<skillKey>`).
If no `metadata.moltbot` is present, the skill is always eligible (unless
If no `metadata.openclaw` is present, the skill is always eligible (unless
disabled in config or blocked by `skills.allowBundled` for bundled skills).
## Config overrides (`~/.clawdbot/moltbot.json`)
## Config overrides (`~/.openclaw/openclaw.json`)
Bundled/managed skills can be toggled and supplied with env values:
@@ -184,19 +184,19 @@ Bundled/managed skills can be toggled and supplied with env values:
Note: if the skill name contains hyphens, quote the key (JSON5 allows quoted keys).
Config keys match the **skill name** by default. If a skill defines
`metadata.moltbot.skillKey`, use that key under `skills.entries`.
`metadata.openclaw.skillKey`, use that key under `skills.entries`.
Rules:
- `enabled: false` disables the skill even if it’s bundled/installed.
- `env`: injected **only if** the variable isn’t already set in the process.
- `apiKey`: convenience for skills that declare `metadata.moltbot.primaryEnv`.
- `apiKey`: convenience for skills that declare `metadata.openclaw.primaryEnv`.
- `config`: optional bag for custom per-skill fields; custom keys must live here.
- `allowBundled`: optional allowlist for **bundled** skills only. If set, only
bundled skills in the list are eligible (managed/workspace skills unaffected).
## Environment injection (per agent run)
When an agent run starts, Moltbot:
When an agent run starts, OpenClaw:
1) Reads skill metadata.
2) Applies any `skills.entries.<key>.env` or `skills.entries.<key>.apiKey` to
`process.env`.
@@ -207,19 +207,19 @@ This is **scoped to the agent run**, not a global shell environment.
## Session snapshot (performance)
Moltbot snapshots the eligible skills **when a session starts** and reuses that list for subsequent turns in the same session. Changes to skills or config take effect on the next new session.
OpenClaw snapshots the eligible skills **when a session starts** and reuses that list for subsequent turns in the same session. Changes to skills or config take effect on the next new session.
Skills can also refresh mid-session when the skills watcher is enabled or when a new eligible remote node appears (see below). Think of this as a **hot reload**: the refreshed list is picked up on the next agent turn.
## Remote macOS nodes (Linux gateway)
If the Gateway is running on Linux but a **macOS node** is connected **with `system.run` allowed** (Exec approvals security not set to `deny`), Moltbot can treat macOS-only skills as eligible when the required binaries are present on that node. The agent should execute those skills via the `nodes` tool (typically `nodes.run`).
If the Gateway is running on Linux but a **macOS node** is connected **with `system.run` allowed** (Exec approvals security not set to `deny`), OpenClaw can treat macOS-only skills as eligible when the required binaries are present on that node. The agent should execute those skills via the `nodes` tool (typically `nodes.run`).
This relies on the node reporting its command support and on a bin probe via `system.run`. If the macOS node goes offline later, the skills remain visible; invocations may fail until the node reconnects.
## Skills watcher (auto-refresh)
By default, Moltbot watches skill folders and bumps the skills snapshot when `SKILL.md` files change. Configure this under `skills.load`:
By default, OpenClaw watches skill folders and bumps the skills snapshot when `SKILL.md` files change. Configure this under `skills.load`:
```json5
{
@@ -234,7 +234,7 @@ By default, Moltbot watches skill folders and bumps the skills snapshot when `SK
## Token impact (skills list)
When skills are eligible, Moltbot injects a compact XML list of available skills into the system prompt (via `formatSkillsForPrompt` in `pi-coding-agent`). The cost is deterministic:
When skills are eligible, OpenClaw injects a compact XML list of available skills into the system prompt (via `formatSkillsForPrompt` in `pi-coding-agent`). The cost is deterministic:
- **Base overhead (only when ≥1 skill):** 195 characters.
- **Per skill:** 97 characters + the length of the XML-escaped `<name>`, `<description>`, and `<location>` values.
@@ -251,8 +251,8 @@ Notes:
## Managed skills lifecycle
Moltbot ships a baseline set of skills as **bundled skills** as part of the
install (npm package or Moltbot.app). `~/.clawdbot/skills` exists for local
OpenClaw ships a baseline set of skills as **bundled skills** as part of the
install (npm package or OpenClaw.app). `~/.openclaw/skills` exists for local
overrides (for example, pinning/patching a skill without changing the bundled
copy). Workspace skills are user-owned and override both on name conflicts.

16
docs/tools/slash-commands.md
View File

@@ -51,7 +51,7 @@ They run immediately, are stripped before the model sees the message, and the re
- Set `channels.discord.commands.nativeSkills`, `channels.telegram.commands.nativeSkills`, or `channels.slack.commands.nativeSkills` to override per provider (bool or `"auto"`).
- `commands.bash` (default `false`) enables `! <cmd>` to run host shell commands (`/bash <cmd>` is an alias; requires `tools.elevated` allowlists).
- `commands.bashForegroundMs` (default `2000`) controls how long bash waits before switching to background mode (`0` backgrounds immediately).
- `commands.config` (default `false`) enables `/config` (reads/writes `moltbot.json`).
- `commands.config` (default `false`) enables `/config` (reads/writes `openclaw.json`).
- `commands.debug` (default `false`) enables `/debug` (runtime-only overrides).
- `commands.useAccessGroups` (default `true`) enforces allowlists/policies for commands.
@@ -98,9 +98,9 @@ Text-only:
Notes:
- Commands accept an optional `:` between the command and args (e.g. `/think: high`, `/send: on`, `/help:`).
- `/new <model>` accepts a model alias, `provider/model`, or a provider name (fuzzy match); if no match, the text is treated as the message body.
- For full provider usage breakdown, use `moltbot status --usage`.
- For full provider usage breakdown, use `openclaw status --usage`.
- `/allowlist add|remove` requires `commands.config=true` and honors channel `configWrites`.
- `/usage` controls the per-response usage footer; `/usage cost` prints a local cost summary from Moltbot session logs.
- `/usage` controls the per-response usage footer; `/usage cost` prints a local cost summary from OpenClaw session logs.
- `/restart` is disabled by default; set `commands.restart: true` to enable it.
- `/verbose` is meant for debugging and extra visibility; keep it **off** in normal use.
- `/reasoning` (and `/verbose`) are risky in group settings: they may reveal internal reasoning or tool output you did not intend to expose. Prefer leaving them off, especially in group chats.
@@ -151,19 +151,19 @@ Examples:
```
/debug show
/debug set messages.responsePrefix="[moltbot]"
/debug set messages.responsePrefix="[openclaw]"
/debug set channels.whatsapp.allowFrom=["+1555","+4477"]
/debug unset messages.responsePrefix
/debug reset
```
Notes:
- Overrides apply immediately to new config reads, but do **not** write to `moltbot.json`.
- Overrides apply immediately to new config reads, but do **not** write to `openclaw.json`.
- Use `/debug reset` to clear all overrides and return to the on-disk config.
## Config updates
`/config` writes to your on-disk config (`moltbot.json`). Owner-only. Disabled by default; enable with `commands.config: true`.
`/config` writes to your on-disk config (`openclaw.json`). Owner-only. Disabled by default; enable with `commands.config: true`.
Examples:
@@ -171,7 +171,7 @@ Examples:
/config show
/config show messages.responsePrefix
/config get messages.responsePrefix
/config set messages.responsePrefix="[moltbot]"
/config set messages.responsePrefix="[openclaw]"
/config unset messages.responsePrefix
```
@@ -187,4 +187,4 @@ Notes:
- Slack: `agent:<agentId>:slack:slash:<userId>` (prefix configurable via `channels.slack.slashCommand.sessionPrefix`)
- Telegram: `telegram:slash:<userId>` (targets the chat session via `CommandTargetSessionKey`)
- **`/stop`** targets the active chat session so it can abort the current run.
- **Slack:** `channels.slack.slashCommand` is still supported for a single `/clawd`-style command. If you enable `commands.native`, you must create one Slack slash command per built-in command (same names as `/help`). Command argument menus for Slack are delivered as ephemeral Block Kit buttons.
- **Slack:** `channels.slack.slashCommand` is still supported for a single `/openclaw`-style command. If you enable `commands.native`, you must create one Slack slash command per built-in command (same names as `/help`). Command argument menus for Slack are delivered as ephemeral Block Kit buttons.

16
docs/tools/web.md
View File

@@ -8,7 +8,7 @@ read_when:
# Web tools
Moltbot ships two lightweight web tools:
OpenClaw ships two lightweight web tools:
- `web_search` — Search the web via Brave Search API (default) or Perplexity Sonar (direct or via OpenRouter).
- `web_fetch` — HTTP fetch + readable extraction (HTML → markdown/text).
@@ -72,19 +72,19 @@ Example: switch to Perplexity Sonar (direct API):
1) Create a Brave Search API account at https://brave.com/search/api/
2) In the dashboard, choose the **Data for Search** plan (not “Data for AI”) and generate an API key.
3) Run `moltbot configure --section web` to store the key in config (recommended), or set `BRAVE_API_KEY` in your environment.
3) Run `openclaw configure --section web` to store the key in config (recommended), or set `BRAVE_API_KEY` in your environment.
Brave provides a free tier plus paid plans; check the Brave API portal for the
current limits and pricing.
### Where to set the key (recommended)
**Recommended:** run `moltbot configure --section web`. It stores the key in
`~/.clawdbot/moltbot.json` under `tools.web.search.apiKey`.
**Recommended:** run `openclaw configure --section web`. It stores the key in
`~/.openclaw/openclaw.json` under `tools.web.search.apiKey`.
**Environment alternative:** set `BRAVE_API_KEY` in the Gateway process
environment. For a gateway install, put it in `~/.clawdbot/.env` (or your
service environment). See [Env vars](/help/faq#how-does-moltbot-load-environment-variables).
environment. For a gateway install, put it in `~/.openclaw/.env` (or your
service environment). See [Env vars](/help/faq#how-does-openclaw-load-environment-variables).
## Using Perplexity (direct or via OpenRouter)
@@ -122,9 +122,9 @@ crypto/prepaid).
```
**Environment alternative:** set `OPENROUTER_API_KEY` or `PERPLEXITY_API_KEY` in the Gateway
environment. For a gateway install, put it in `~/.clawdbot/.env`.
environment. For a gateway install, put it in `~/.openclaw/.env`.
If no base URL is set, Moltbot chooses a default based on the API key source:
If no base URL is set, OpenClaw chooses a default based on the API key source:
- `PERPLEXITY_API_KEY` or `pplx-...` → `https://api.perplexity.ai`
- `OPENROUTER_API_KEY` or `sk-or-...` → `https://openrouter.ai/api/v1`