@poolzin/pool-bot 2026.1.26 → 2026.1.30

package/docs/nodes/audio.md

@@ -6,7 +6,7 @@ read_when:
 # Audio / Voice Notes — 2026-01-17
 
 ## What works
-- **Media understanding (audio)**: If audio understanding is enabled (or auto‑detected), Clawdbot:
+- **Media understanding (audio)**: If audio understanding is enabled (or auto‑detected), Pool Bot:
   1) Locates the first audio attachment (local path or URL) and downloads it if needed.
   2) Enforces `maxBytes` before sending to each model entry.
   3) Runs the first eligible model entry in order (provider or CLI).
@@ -17,7 +17,7 @@ read_when:
 
 ## Auto-detection (default)
 If you **don’t configure models** and `tools.media.audio.enabled` is **not** set to `false`,
-Clawdbot auto-detects in this order and stops at the first working option:
+Pool Bot auto-detects in this order and stops at the first working option:
 
 1) **Local CLIs** (if installed)
    - `sherpa-onnx-offline` (requires `SHERPA_ONNX_MODEL_DIR` with encoder/decoder/joiner/tokens)

package/docs/nodes/camera.md

@@ -7,7 +7,7 @@ read_when:
 
 # Camera capture (agent)
 
-Clawdbot supports **camera capture** for agent workflows:
+Pool Bot supports **camera capture** for agent workflows:
 
 - **iOS node** (paired via Gateway): capture a **photo** (`jpg`) or **short video clip** (`mp4`, with optional audio) via `node.invoke`.
 - **Android node** (paired via Gateway): capture a **photo** (`jpg`) or **short video clip** (`mp4`, with optional audio) via `node.invoke`.
@@ -67,10 +67,10 @@ The easiest way to get attachments is via the CLI helper, which writes decoded m
 Examples:
 
 ```bash
-clawdbot nodes camera snap --node <id>               # default: both front + back (2 MEDIA lines)
-clawdbot nodes camera snap --node <id> --facing front
-clawdbot nodes camera clip --node <id> --duration 3000
-clawdbot nodes camera clip --node <id> --no-audio
+poolbot nodes camera snap --node <id>               # default: both front + back (2 MEDIA lines)
+poolbot nodes camera snap --node <id> --facing front
+poolbot nodes camera clip --node <id> --duration 3000
+poolbot nodes camera clip --node <id> --no-audio
 ```
 
 Notes:
@@ -108,30 +108,30 @@ Photos are recompressed to keep the base64 payload under 5 MB.
 
 The macOS companion app exposes a checkbox:
 
-- **Settings → General → Allow Camera** (`clawdbot.cameraEnabled`)
+- **Settings → General → Allow Camera** (`poolbot.cameraEnabled`)
   - Default: **off**
   - When off: camera requests return “Camera disabled by user”.
 
 ### CLI helper (node invoke)
 
-Use the main `clawdbot` CLI to invoke camera commands on the macOS node.
+Use the main `poolbot` CLI to invoke camera commands on the macOS node.
 
 Examples:
 
 ```bash
-clawdbot nodes camera list --node <id>            # list camera ids
-clawdbot nodes camera snap --node <id>            # prints MEDIA:<path>
-clawdbot nodes camera snap --node <id> --max-width 1280
-clawdbot nodes camera snap --node <id> --delay-ms 2000
-clawdbot nodes camera snap --node <id> --device-id <id>
-clawdbot nodes camera clip --node <id> --duration 10s          # prints MEDIA:<path>
-clawdbot nodes camera clip --node <id> --duration-ms 3000      # prints MEDIA:<path> (legacy flag)
-clawdbot nodes camera clip --node <id> --device-id <id>
-clawdbot nodes camera clip --node <id> --no-audio
+poolbot nodes camera list --node <id>            # list camera ids
+poolbot nodes camera snap --node <id>            # prints MEDIA:<path>
+poolbot nodes camera snap --node <id> --max-width 1280
+poolbot nodes camera snap --node <id> --delay-ms 2000
+poolbot nodes camera snap --node <id> --device-id <id>
+poolbot nodes camera clip --node <id> --duration 10s          # prints MEDIA:<path>
+poolbot nodes camera clip --node <id> --duration-ms 3000      # prints MEDIA:<path> (legacy flag)
+poolbot nodes camera clip --node <id> --device-id <id>
+poolbot nodes camera clip --node <id> --no-audio
 ```
 
 Notes:
-- `clawdbot nodes camera snap` defaults to `maxWidth=1600` unless overridden.
+- `poolbot nodes camera snap` defaults to `maxWidth=1600` unless overridden.
 - On macOS, `camera.snap` waits `delayMs` (default 2000ms) after warm-up/exposure settle before capturing.
 - Photo payloads are recompressed to keep base64 under 5 MB.
 
@@ -145,7 +145,7 @@ Notes:
 For *screen* video (not camera), use the macOS companion:
 
 ```bash
-clawdbot nodes screen record --node <id> --duration 10s --fps 15   # prints MEDIA:<path>
+poolbot nodes screen record --node <id> --duration 10s --fps 15   # prints MEDIA:<path>
 ```
 
 Notes:

package/docs/nodes/images.md

@@ -8,12 +8,12 @@ read_when:
 The WhatsApp channel runs via **Baileys Web**. This document captures the current media handling rules for send, gateway, and agent replies.
 
 ## Goals
-- Send media with optional captions via `clawdbot message send --media`.
+- Send media with optional captions via `poolbot message send --media`.
 - Allow auto-replies from the web inbox to include media alongside text.
 - Keep per-type limits sane and predictable.
 
 ## CLI Surface
-- `clawdbot message send --media <path-or-url> [--message <caption>]`
+- `poolbot message send --media <path-or-url> [--message <caption>]`
   - `--media` optional; caption can be empty for media-only sends.
   - `--dry-run` prints the resolved payload; `--json` emits `{ channel, to, messageId, mediaUrl, caption }`.
 
@@ -30,11 +30,11 @@ The WhatsApp channel runs via **Baileys Web**. This document captures the curren
 
 ## Auto-Reply Pipeline
 - `getReplyFromConfig` returns `{ text?, mediaUrl?, mediaUrls? }`.
-- When media is present, the web sender resolves local paths or URLs using the same pipeline as `clawdbot message send`.
+- When media is present, the web sender resolves local paths or URLs using the same pipeline as `poolbot message send`.
 - Multiple media entries are sent sequentially if provided.
 
 ## Inbound Media to Commands (Pi)
-- When inbound web messages include media, Clawdbot downloads to a temp file and exposes templating variables:
+- When inbound web messages include media, Pool Bot downloads to a temp file and exposes templating variables:
   - `{{MediaUrl}}` pseudo-URL for the inbound media.
   - `{{MediaPath}}` local temp path written before running the command.
 - When a per-session Docker sandbox is enabled, inbound media is copied into the sandbox workspace and `MediaPath`/`MediaUrl` are rewritten to a relative path like `media/inbound/<filename>`.

package/docs/nodes/index.md

@@ -12,7 +12,7 @@ A **node** is a companion device (macOS/iOS/Android/headless) that connects to t
 
 Legacy transport: [Bridge protocol](/gateway/bridge-protocol) (TCP JSONL; deprecated/removed for current nodes).
 
-macOS can also run in **node mode**: the menubar app connects to the Gateway’s WS server and exposes its local canvas/camera commands as a node (so `clawdbot nodes …` works against this Mac).
+macOS can also run in **node mode**: the menubar app connects to the Gateway’s WS server and exposes its local canvas/camera commands as a node (so `poolbot nodes …` works against this Mac).
 
 Notes:
 - Nodes are **peripherals**, not gateways. They don’t run the gateway service.
@@ -26,16 +26,16 @@ creates a device pairing request for `role: node`. Approve via the devices CLI (
 Quick CLI:
 
 ```bash
-clawdbot devices list
-clawdbot devices approve <requestId>
-clawdbot devices reject <requestId>
-clawdbot nodes status
-clawdbot nodes describe --node <idOrNameOrIp>
+poolbot devices list
+poolbot devices approve <requestId>
+poolbot devices reject <requestId>
+poolbot nodes status
+poolbot nodes describe --node <idOrNameOrIp>
 ```
 
 Notes:
 - `nodes status` marks a node as **paired** when its device pairing role includes `node`.
-- `node.pair.*` (CLI: `clawdbot nodes pending/approve/reject`) is a separate gateway-owned
+- `node.pair.*` (CLI: `poolbot nodes pending/approve/reject`) is a separate gateway-owned
   node pairing store; it does **not** gate the WS `connect` handshake.
 
 ## Remote node host (system.run)
@@ -47,21 +47,21 @@ forwards `exec` calls to the **node host** when `host=node` is selected.
 ### What runs where
 - **Gateway host**: receives messages, runs the model, routes tool calls.
 - **Node host**: executes `system.run`/`system.which` on the node machine.
-- **Approvals**: enforced on the node host via `~/.clawdbot/exec-approvals.json`.
+- **Approvals**: enforced on the node host via `~/.poolbot/exec-approvals.json`.
 
 ### Start a node host (foreground)
 
 On the node machine:
 
 ```bash
-clawdbot node run --host <gateway-host> --port 18789 --display-name "Build Node"
+poolbot node run --host <gateway-host> --port 18789 --display-name "Build Node"
 ```
 
 ### Start a node host (service)
 
 ```bash
-clawdbot node install --host <gateway-host> --port 18789 --display-name "Build Node"
-clawdbot node restart
+poolbot node install --host <gateway-host> --port 18789 --display-name "Build Node"
+poolbot node restart
 ```
 
 ### Pair + name
@@ -69,34 +69,34 @@ clawdbot node restart
 On the gateway host:
 
 ```bash
-clawdbot nodes pending
-clawdbot nodes approve <requestId>
-clawdbot nodes list
+poolbot nodes pending
+poolbot nodes approve <requestId>
+poolbot nodes list
 ```
 
 Naming options:
-- `--display-name` on `clawdbot node run` / `clawdbot node install` (persists in `~/.clawdbot/node.json` on the node).
-- `clawdbot nodes rename --node <id|name|ip> --name "Build Node"` (gateway override).
+- `--display-name` on `poolbot node run` / `poolbot node install` (persists in `~/.poolbot/node.json` on the node).
+- `poolbot nodes rename --node <id|name|ip> --name "Build Node"` (gateway override).
 
 ### Allowlist the commands
 
 Exec approvals are **per node host**. Add allowlist entries from the gateway:
 
 ```bash
-clawdbot approvals allowlist add --node <id|name|ip> "/usr/bin/uname"
-clawdbot approvals allowlist add --node <id|name|ip> "/usr/bin/sw_vers"
+poolbot approvals allowlist add --node <id|name|ip> "/usr/bin/uname"
+poolbot approvals allowlist add --node <id|name|ip> "/usr/bin/sw_vers"
 ```
 
-Approvals live on the node host at `~/.clawdbot/exec-approvals.json`.
+Approvals live on the node host at `~/.poolbot/exec-approvals.json`.
 
 ### Point exec at the node
 
 Configure defaults (gateway config):
 
 ```bash
-clawdbot config set tools.exec.host node
-clawdbot config set tools.exec.security allowlist
-clawdbot config set tools.exec.node "<id-or-name>"
+poolbot config set tools.exec.host node
+poolbot config set tools.exec.security allowlist
+poolbot config set tools.exec.node "<id-or-name>"
 ```
 
 Or per session:
@@ -118,7 +118,7 @@ Related:
 Low-level (raw RPC):
 
 ```bash
-clawdbot nodes invoke --node <idOrNameOrIp> --command canvas.eval --params '{"javaScript":"location.href"}'
+poolbot nodes invoke --node <idOrNameOrIp> --command canvas.eval --params '{"javaScript":"location.href"}'
 ```
 
 Higher-level helpers exist for the common “give the agent a MEDIA attachment” workflows.
@@ -130,17 +130,17 @@ If the node is showing the Canvas (WebView), `canvas.snapshot` returns `{ format
 CLI helper (writes to a temp file and prints `MEDIA:<path>`):
 
 ```bash
-clawdbot nodes canvas snapshot --node <idOrNameOrIp> --format png
-clawdbot nodes canvas snapshot --node <idOrNameOrIp> --format jpg --max-width 1200 --quality 0.9
+poolbot nodes canvas snapshot --node <idOrNameOrIp> --format png
+poolbot nodes canvas snapshot --node <idOrNameOrIp> --format jpg --max-width 1200 --quality 0.9
 ```
 
 ### Canvas controls
 
 ```bash
-clawdbot nodes canvas present --node <idOrNameOrIp> --target https://example.com
-clawdbot nodes canvas hide --node <idOrNameOrIp>
-clawdbot nodes canvas navigate https://example.com --node <idOrNameOrIp>
-clawdbot nodes canvas eval --node <idOrNameOrIp> --js "document.title"
+poolbot nodes canvas present --node <idOrNameOrIp> --target https://example.com
+poolbot nodes canvas hide --node <idOrNameOrIp>
+poolbot nodes canvas navigate https://example.com --node <idOrNameOrIp>
+poolbot nodes canvas eval --node <idOrNameOrIp> --js "document.title"
 ```
 
 Notes:
@@ -150,9 +150,9 @@ Notes:
 ### A2UI (Canvas)
 
 ```bash
-clawdbot nodes canvas a2ui push --node <idOrNameOrIp> --text "Hello"
-clawdbot nodes canvas a2ui push --node <idOrNameOrIp> --jsonl ./payload.jsonl
-clawdbot nodes canvas a2ui reset --node <idOrNameOrIp>
+poolbot nodes canvas a2ui push --node <idOrNameOrIp> --text "Hello"
+poolbot nodes canvas a2ui push --node <idOrNameOrIp> --jsonl ./payload.jsonl
+poolbot nodes canvas a2ui reset --node <idOrNameOrIp>
 ```
 
 Notes:
@@ -163,16 +163,16 @@ Notes:
 Photos (`jpg`):
 
 ```bash
-clawdbot nodes camera list --node <idOrNameOrIp>
-clawdbot nodes camera snap --node <idOrNameOrIp>            # default: both facings (2 MEDIA lines)
-clawdbot nodes camera snap --node <idOrNameOrIp> --facing front
+poolbot nodes camera list --node <idOrNameOrIp>
+poolbot nodes camera snap --node <idOrNameOrIp>            # default: both facings (2 MEDIA lines)
+poolbot nodes camera snap --node <idOrNameOrIp> --facing front
 ```
 
 Video clips (`mp4`):
 
 ```bash
-clawdbot nodes camera clip --node <idOrNameOrIp> --duration 10s
-clawdbot nodes camera clip --node <idOrNameOrIp> --duration 3000 --no-audio
+poolbot nodes camera clip --node <idOrNameOrIp> --duration 10s
+poolbot nodes camera clip --node <idOrNameOrIp> --duration 3000 --no-audio
 ```
 
 Notes:
@@ -185,8 +185,8 @@ Notes:
 Nodes expose `screen.record` (mp4). Example:
 
 ```bash
-clawdbot nodes screen record --node <idOrNameOrIp> --duration 10s --fps 10
-clawdbot nodes screen record --node <idOrNameOrIp> --duration 10s --fps 10 --no-audio
+poolbot nodes screen record --node <idOrNameOrIp> --duration 10s --fps 10
+poolbot nodes screen record --node <idOrNameOrIp> --duration 10s --fps 10 --no-audio
 ```
 
 Notes:
@@ -203,8 +203,8 @@ Nodes expose `location.get` when Location is enabled in settings.
 CLI helper:
 
 ```bash
-clawdbot nodes location get --node <idOrNameOrIp>
-clawdbot nodes location get --node <idOrNameOrIp> --accuracy precise --max-age 15000 --location-timeout 10000
+poolbot nodes location get --node <idOrNameOrIp>
+poolbot nodes location get --node <idOrNameOrIp> --accuracy precise --max-age 15000 --location-timeout 10000
 ```
 
 Notes:
@@ -219,7 +219,7 @@ Android nodes can expose `sms.send` when the user grants **SMS** permission and
 Low-level invoke:
 
 ```bash
-clawdbot nodes invoke --node <idOrNameOrIp> --command sms.send --params '{"to":"+15555550123","message":"Hello from Clawdbot"}'
+poolbot nodes invoke --node <idOrNameOrIp> --command sms.send --params '{"to":"+15555550123","message":"Hello from Pool Bot"}'
 ```
 
 Notes:
@@ -234,8 +234,8 @@ The headless node host exposes `system.run`, `system.which`, and `system.execApp
 Examples:
 
 ```bash
-clawdbot nodes run --node <idOrNameOrIp> -- echo "Hello from mac node"
-clawdbot nodes notify --node <idOrNameOrIp> --title "Ping" --body "Gateway ready"
+poolbot nodes run --node <idOrNameOrIp> -- echo "Hello from mac node"
+poolbot nodes notify --node <idOrNameOrIp> --title "Ping" --body "Gateway ready"
 ```
 
 Notes:
@@ -246,7 +246,7 @@ Notes:
 - macOS nodes drop `PATH` overrides; headless node hosts only accept `PATH` when it prepends the node host PATH.
 - On macOS node mode, `system.run` is gated by exec approvals in the macOS app (Settings → Exec approvals).
   Ask/allowlist/full behave the same as the headless node host; denied prompts return `SYSTEM_RUN_DENIED`.
-- On headless node host, `system.run` is gated by exec approvals (`~/.clawdbot/exec-approvals.json`).
+- On headless node host, `system.run` is gated by exec approvals (`~/.poolbot/exec-approvals.json`).
 
 ## Exec node binding
 
@@ -256,21 +256,21 @@ This sets the default node for `exec host=node` (and can be overridden per agent
 Global default:
 
 ```bash
-clawdbot config set tools.exec.node "node-id-or-name"
+poolbot config set tools.exec.node "node-id-or-name"
 ```
 
 Per-agent override:
 
 ```bash
-clawdbot config get agents.list
-clawdbot config set agents.list[0].tools.exec.node "node-id-or-name"
+poolbot config get agents.list
+poolbot config set agents.list[0].tools.exec.node "node-id-or-name"
 ```
 
 Unset to allow any node:
 
 ```bash
-clawdbot config unset tools.exec.node
-clawdbot config unset agents.list[0].tools.exec.node
+poolbot config unset tools.exec.node
+poolbot config unset agents.list[0].tools.exec.node
 ```
 
 ## Permissions map
@@ -279,20 +279,20 @@ Nodes may include a `permissions` map in `node.list` / `node.describe`, keyed by
 
 ## Headless node host (cross-platform)
 
-Clawdbot can run a **headless node host** (no UI) that connects to the Gateway
+Pool Bot can run a **headless node host** (no UI) that connects to the Gateway
 WebSocket and exposes `system.run` / `system.which`. This is useful on Linux/Windows
 or for running a minimal node alongside a server.
 
 Start it:
 
 ```bash
-clawdbot node run --host <gateway-host> --port 18789
+poolbot node run --host <gateway-host> --port 18789
 ```
 
 Notes:
 - Pairing is still required (the Gateway will show a node approval prompt).
-- The node host stores its node id, token, display name, and gateway connection info in `~/.clawdbot/node.json`.
-- Exec approvals are enforced locally via `~/.clawdbot/exec-approvals.json`
+- The node host stores its node id, token, display name, and gateway connection info in `~/.poolbot/node.json`.
+- Exec approvals are enforced locally via `~/.poolbot/exec-approvals.json`
   (see [Exec approvals](/tools/exec-approvals)).
 - On macOS, the headless node host prefers the companion app exec host when reachable and falls
   back to local execution if the app is unavailable. Set `CLAWDBOT_NODE_EXEC_HOST=app` to require
@@ -301,5 +301,5 @@ Notes:
 
 ## Mac node mode
 
-- The macOS menubar app connects to the Gateway WS server as a node (so `clawdbot nodes …` works against this Mac).
+- The macOS menubar app connects to the Gateway WS server as a node (so `poolbot nodes …` works against this Mac).
 - In remote mode, the app opens an SSH tunnel for the Gateway port and connects to `localhost`.

package/docs/nodes/location-command.md

@@ -85,11 +85,11 @@ Notes:
 
 ## Model/tooling integration
 - Tool surface: `nodes` tool adds `location_get` action (node required).
-- CLI: `clawdbot nodes location get --node <id>`.
+- CLI: `poolbot nodes location get --node <id>`.
 - Agent guidelines: only call when user enabled location and understands the scope.
 
 ## UX copy (suggested)
 - Off: “Location sharing is disabled.”
-- While Using: “Only when Clawdbot is open.”
+- While Using: “Only when Pool Bot is open.”
 - Always: “Allow background location. Requires system permission.”
 - Precise: “Use precise GPS location. Toggle off to share approximate location.”

package/docs/nodes/media-understanding.md

@@ -6,7 +6,7 @@ read_when:
 ---
 # Media Understanding (Inbound) — 2026-01-17
 
-Clawdbot can **summarize inbound media** (image/audio/video) before the reply pipeline runs. It auto‑detects when local tools or provider keys are available, and can be disabled or customized. If understanding is off, models still receive the original files/URLs as usual.
+Pool Bot can **summarize inbound media** (image/audio/video) before the reply pipeline runs. It auto‑detects when local tools or provider keys are available, and can be disabled or customized. If understanding is off, models still receive the original files/URLs as usual.
 
 ## Goals
 - Optional: pre‑digest inbound media into short text for faster routing + better command parsing.
@@ -106,12 +106,12 @@ Rules:
 - If media exceeds `maxBytes`, that model is skipped and the **next model is tried**.
 - If the model returns more than `maxChars`, output is trimmed.
 - `prompt` defaults to simple “Describe the {media}.” plus the `maxChars` guidance (image/video only).
-- If `<capability>.enabled: true` but no models are configured, Clawdbot tries the
+- If `<capability>.enabled: true` but no models are configured, Pool Bot tries the
   **active reply model** when its provider supports the capability.
 
 ### Auto-detect media understanding (default)
 If `tools.media.<capability>.enabled` is **not** set to `false` and you haven’t
-configured models, Clawdbot auto-detects in this order and **stops at the first
+configured models, Pool Bot auto-detects in this order and **stops at the first
 working option**:
 
 1) **Local CLIs** (audio only; if installed)
@@ -140,7 +140,7 @@ Note: Binary detection is best-effort across macOS/Linux/Windows; ensure the CLI
 
 ## Capabilities (optional)
 If you set `capabilities`, the entry only runs for those media types. For shared
-lists, Clawdbot can infer defaults:
+lists, Pool Bot can infer defaults:
 - `openai`, `anthropic`, `minimax`: **image**
 - `google` (Gemini API): **image + audio + video**
 - `groq`: **audio**
@@ -149,7 +149,7 @@ lists, Clawdbot can infer defaults:
 For CLI entries, **set `capabilities` explicitly** to avoid surprising matches.
 If you omit `capabilities`, the entry is eligible for the list it appears in.
 
-## Provider support matrix (Clawdbot integrations)
+## Provider support matrix (Pool Bot integrations)
 | Capability | Provider integration | Notes |
 |------------|----------------------|-------|
 | Image | OpenAI / Anthropic / Google / others via `pi-ai` | Any image-capable model in the registry works. |

package/docs/nodes/talk.md

@@ -40,7 +40,7 @@ Supported keys:
 - `seed`, `normalize`, `lang`, `output_format`, `latency_tier`
 - `once`
 
-## Config (`~/.clawdbot/clawdbot.json`)
+## Config (`~/.poolbot/poolbot.json`)
 ```json5
 {
   "talk": {

package/docs/nodes/voicewake.md

@@ -6,7 +6,7 @@ read_when:
 ---
 # Voice Wake (Global Wake Words)
 
-Clawdbot treats **wake words as a single global list** owned by the **Gateway**.
+Pool Bot treats **wake words as a single global list** owned by the **Gateway**.
 
 - There are **no per-node custom wake words**.
 - **Any node/app UI may edit** the list; changes are persisted by the Gateway and broadcast to everyone.
@@ -16,7 +16,7 @@ Clawdbot treats **wake words as a single global list** owned by the **Gateway**.
 
 Wake words are stored on the gateway machine at:
 
-- `~/.clawdbot/settings/voicewake.json`
+- `~/.poolbot/settings/voicewake.json`
 
 Shape:
 

package/docs/northflank.mdx

@@ -0,0 +1,53 @@
+---
+title: Deploy on Northflank
+---
+
+Deploy Moltbot on Northflank with a one-click template and finish setup in your browser.
+This is the easiest “no terminal on the server” path: Northflank runs the Gateway for you,
+and you configure everything via the `/setup` web wizard.
+
+## How to get started
+
+1. Click [Deploy Moltbot](https://northflank.com/stacks/deploy-moltbot) to open the template.  
+2. Create an [account on Northflank](https://app.northflank.com/signup) if you don’t already have one.  
+3. Click **Deploy Moltbot now**.  
+4. Set the required environment variable: `SETUP_PASSWORD`.
+5. Click **Deploy stack** to build and run the Moltbot template.
+6. Wait for the deployment to complete, then click **View resources**.
+7. Open the Moltbot service.
+8. Open the public Moltbot URL and complete setup at `/setup`.
+9. Open the Control UI at `/moltbot`.
+
+## What you get
+
+- Hosted Moltbot Gateway + Control UI
+- Web setup wizard at `/setup` (no terminal commands)
+- Persistent storage via Northflank Volume (`/data`) so config/credentials/workspace survive redeploys
+
+## Setup flow
+
+1) Visit `https://<your-northflank-domain>/setup` and enter your `SETUP_PASSWORD`.
+2) Choose a model/auth provider and paste your key.
+3) (Optional) Add Telegram/Discord/Slack tokens.
+4) Click **Run setup**.
+5) Open the Control UI at `https://<your-northflank-domain>/moltbot`
+
+If Telegram DMs are set to pairing, the setup wizard can approve the pairing code.
+
+## Getting chat tokens
+
+### Telegram bot token
+
+1) Message `@BotFather` in Telegram
+2) Run `/newbot`
+3) Copy the token (looks like `123456789:AA...`)
+4) Paste it into `/setup`
+
+### Discord bot token
+
+1) Go to https://discord.com/developers/applications
+2) **New Application** → choose a name
+3) **Bot** → **Add Bot**
+4) **Enable MESSAGE CONTENT INTENT** under Bot → Privileged Gateway Intents (required or the bot will crash on startup)
+5) Copy the **Bot Token** and paste into `/setup`
+6) Invite the bot to your server (OAuth2 URL Generator; scopes: `bot`, `applications.commands`)

package/docs/perplexity.md

@@ -7,7 +7,7 @@ read_when:
 
 # Perplexity Sonar
 
-Clawdbot can use Perplexity Sonar for the `web_search` tool. You can connect
+Pool Bot can use Perplexity Sonar for the `web_search` tool. You can connect
 through Perplexity’s direct API or via OpenRouter.
 
 ## API options
@@ -64,7 +64,7 @@ If both `PERPLEXITY_API_KEY` and `OPENROUTER_API_KEY` are set, set
 `tools.web.search.perplexity.baseUrl` (or `tools.web.search.perplexity.apiKey`)
 to disambiguate.
 
-If no base URL is set, Clawdbot chooses a default based on the API key source:
+If no base URL is set, Pool Bot chooses a default based on the API key source:
 
 - `PERPLEXITY_API_KEY` or `pplx-...` → direct Perplexity (`https://api.perplexity.ai`)
 - `OPENROUTER_API_KEY` or `sk-or-...` → OpenRouter (`https://openrouter.ai/api/v1`)

package/docs/platforms/android.md

@@ -31,12 +31,12 @@ Android connects directly to the Gateway WebSocket (default `ws://<host>:18789`)
   - Same LAN with mDNS/NSD, **or**
   - Same Tailscale tailnet using Wide-Area Bonjour / unicast DNS-SD (see below), **or**
   - Manual gateway host/port (fallback)
-- You can run the CLI (`clawdbot`) on the gateway machine (or via SSH).
+- You can run the CLI (`poolbot`) on the gateway machine (or via SSH).
 
 ### 1) Start the Gateway
 
 ```bash
-clawdbot gateway --port 18789 --verbose
+poolbot gateway --port 18789 --verbose
 ```
 
 Confirm in logs you see something like:
@@ -44,7 +44,7 @@ Confirm in logs you see something like:
 
 For tailnet-only setups (recommended for Vienna ⇄ London), bind the gateway to the tailnet IP:
 
-- Set `gateway.bind: "tailnet"` in `~/.clawdbot/clawdbot.json` on the gateway host.
+- Set `gateway.bind: "tailnet"` in `~/.poolbot/poolbot.json` on the gateway host.
 - Restart the Gateway / macOS menubar app.
 
 ### 2) Verify discovery (optional)
@@ -52,7 +52,7 @@ For tailnet-only setups (recommended for Vienna ⇄ London), bind the gateway to
 From the gateway machine:
 
 ```bash
-dns-sd -B _clawdbot-gw._tcp local.
+dns-sd -B _poolbot-gw._tcp local.
 ```
 
 More debugging notes: [Bonjour](/gateway/bonjour).
@@ -61,8 +61,8 @@ More debugging notes: [Bonjour](/gateway/bonjour).
 
 Android NSD/mDNS discovery won’t cross networks. If your Android node and the gateway are on different networks but connected via Tailscale, use Wide-Area Bonjour / unicast DNS-SD instead:
 
-1) Set up a DNS-SD zone (example `clawdbot.internal.`) on the gateway host and publish `_clawdbot-gw._tcp` records.
-2) Configure Tailscale split DNS for `clawdbot.internal` pointing at that DNS server.
+1) Set up a DNS-SD zone (example `poolbot.internal.`) on the gateway host and publish `_poolbot-gw._tcp` records.
+2) Configure Tailscale split DNS for `poolbot.internal` pointing at that DNS server.
 
 Details and example CoreDNS config: [Bonjour](/gateway/bonjour).
 
@@ -84,8 +84,8 @@ After the first successful pairing, Android auto-reconnects on launch:
 On the gateway machine:
 
 ```bash
-clawdbot nodes pending
-clawdbot nodes approve <requestId>
+poolbot nodes pending
+poolbot nodes approve <requestId>
 ```
 
 Pairing details: [Gateway pairing](/gateway/pairing).
@@ -94,11 +94,11 @@ Pairing details: [Gateway pairing](/gateway/pairing).
 
 - Via nodes status:
   ```bash
-  clawdbot nodes status
+  poolbot nodes status
   ```
 - Via Gateway:
   ```bash
-  clawdbot gateway call node.list --params "{}"
+  poolbot gateway call node.list --params "{}"
   ```
 
 ### 6) Chat + history
@@ -122,13 +122,13 @@ Note: nodes use the standalone canvas host on `canvasHost.port` (default `18793`
 2) Navigate the node to it (LAN):
 
 ```bash
-clawdbot nodes invoke --node "<Android Node>" --command canvas.navigate --params '{"url":"http://<gateway-hostname>.local:18793/__clawdbot__/canvas/"}'
+poolbot nodes invoke --node "<Android Node>" --command canvas.navigate --params '{"url":"http://<gateway-hostname>.local:18793/__poolbot__/canvas/"}'
 ```
 
-Tailnet (optional): if both devices are on Tailscale, use a MagicDNS name or tailnet IP instead of `.local`, e.g. `http://<gateway-magicdns>:18793/__clawdbot__/canvas/`.
+Tailnet (optional): if both devices are on Tailscale, use a MagicDNS name or tailnet IP instead of `.local`, e.g. `http://<gateway-magicdns>:18793/__poolbot__/canvas/`.
 
 This server injects a live-reload client into HTML and reloads on file changes.
-The A2UI host lives at `http://<gateway-host>:18793/__clawdbot__/a2ui/`.
+The A2UI host lives at `http://<gateway-host>:18793/__poolbot__/a2ui/`.
 
 Canvas commands (foreground only):
 - `canvas.eval`, `canvas.snapshot`, `canvas.navigate` (use `{"url":""}` or `{"url":"/"}` to return to the default scaffold). `canvas.snapshot` returns `{ format, base64 }` (default `format="jpeg"`).