@gguf/pigbot 0.0.5 → 0.0.7

package/docs/concepts/system-prompt.md

@@ -1,14 +1,14 @@
 ---
-summary: "What the Moltbot system prompt contains and how it is assembled"
+summary: "What the OpenClaw system prompt contains and how it is assembled"
 read_when:
   - Editing system prompt text, tools list, or time/heartbeat sections
   - Changing workspace bootstrap or skills injection behavior
 ---
 # System Prompt
 
-Moltbot builds a custom system prompt for every agent run. The prompt is **Moltbot-owned** and does not use the p-coding-agent default prompt.
+OpenClaw builds a custom system prompt for every agent run. The prompt is **OpenClaw-owned** and does not use the p-coding-agent default prompt.
 
-The prompt is assembled by Moltbot and injected into each agent run.
+The prompt is assembled by OpenClaw and injected into each agent run.
 
 ## Structure
 
@@ -16,9 +16,9 @@ The prompt is intentionally compact and uses fixed sections:
 
 - **Tooling**: current tool list + short descriptions.
 - **Skills** (when available): tells the model how to load skill instructions on demand.
-- **Moltbot Self-Update**: how to run `config.apply` and `update.run`.
+- **OpenClaw Self-Update**: how to run `config.apply` and `update.run`.
 - **Workspace**: working directory (`agents.defaults.workspace`).
-- **Documentation**: local path to Moltbot docs (repo or npm package) and when to read them.
+- **Documentation**: local path to OpenClaw docs (repo or npm package) and when to read them.
 - **Workspace Files (injected)**: indicates bootstrap files are included below.
 - **Sandbox** (when enabled): indicates sandboxed runtime, sandbox paths, and whether elevated exec is available.
 - **Current Date & Time**: user-local time, timezone, and time format.
@@ -29,11 +29,11 @@ The prompt is intentionally compact and uses fixed sections:
 
 ## Prompt modes
 
-Moltbot can render smaller system prompts for sub-agents. The runtime sets a
+OpenClaw can render smaller system prompts for sub-agents. The runtime sets a
 `promptMode` for each run (not a user-facing config):
 
 - `full` (default): includes all sections above.
-- `minimal`: used for sub-agents; omits **Skills**, **Memory Recall**, **Moltbot
+- `minimal`: used for sub-agents; omits **Skills**, **Memory Recall**, **OpenClaw
   Self-Update**, **Model Aliases**, **User Identity**, **Reply Tags**,
   **Messaging**, **Silent Replies**, and **Heartbeats**. Tooling, Workspace,
   Sandbox, Current Date & Time (when known), Runtime, and injected context stay
@@ -82,7 +82,7 @@ See [Date & Time](/date-time) for full behavior details.
 
 ## Skills
 
-When eligible skills exist, Moltbot injects a compact **available skills list**
+When eligible skills exist, OpenClaw injects a compact **available skills list**
 (`formatSkillsForPrompt`) that includes the **file path** for each skill. The
 prompt instructs the model to use `read` to load the SKILL.md at the listed
 location (workspace, managed, or bundled). If no skills are eligible, the
@@ -103,8 +103,8 @@ This keeps the base prompt small while still enabling targeted skill usage.
 ## Documentation
 
 When available, the system prompt includes a **Documentation** section that points to the
-local Moltbot docs directory (either `docs/` in the repo workspace or the bundled npm
+local OpenClaw docs directory (either `docs/` in the repo workspace or the bundled npm
 package docs) and also notes the public mirror, source repo, community Discord, and
 ClawdHub (https://clawdhub.com) for skills discovery. The prompt instructs the model to consult local docs first
-for Moltbot behavior, commands, configuration, or architecture, and to run
-`moltbot status` itself when possible (asking the user only when it lacks access).
+for OpenClaw behavior, commands, configuration, or architecture, and to run
+`openclaw status` itself when possible (asking the user only when it lacks access).

package/docs/concepts/timezone.md

@@ -7,7 +7,7 @@ read_when:
 
 # Timezones
 
-Moltbot standardizes timestamps so the model sees a **single reference time**.
+OpenClaw standardizes timestamps so the model sees a **single reference time**.
 
 ## Message envelopes (local by default)
 
@@ -72,7 +72,7 @@ Raw provider fields are preserved.
 ## User timezone for the system prompt
 
 Set `agents.defaults.userTimezone` to tell the model the user's local time zone. If it is
-unset, Moltbot resolves the **host timezone at runtime** (no config write).
+unset, OpenClaw resolves the **host timezone at runtime** (no config write).
 
 ```json5
 {

package/docs/concepts/typebox.md

@@ -58,7 +58,7 @@ Authoritative list lives in `src/gateway/server.ts` (`METHODS`, `EVENTS`).
 - Server handshake + method dispatch: `src/gateway/server.ts`
 - Node client: `src/gateway/client.ts`
 - Generated JSON Schema: `dist/protocol.schema.json`
-- Generated Swift models: `apps/macos/Sources/MoltbotProtocol/GatewayModels.swift`
+- Generated Swift models: `apps/macos/Sources/OpenClawProtocol/GatewayModels.swift`
 
 ## Current pipeline
 
@@ -91,7 +91,7 @@ Connect (first message):
     "minProtocol": 2,
     "maxProtocol": 2,
     "client": {
-      "id": "moltbot-macos",
+      "id": "openclaw-macos",
       "displayName": "macos",
       "version": "1.0.0",
       "platform": "macos 15.1",
@@ -272,7 +272,7 @@ Unknown frame types are preserved as raw payloads for forward compatibility.
 Generated JSON Schema is in the repo at `dist/protocol.schema.json`. The
 published raw file is typically available at:
 
-- https://raw.githubusercontent.com/moltbot/moltbot/main/dist/protocol.schema.json
+- https://raw.githubusercontent.com/openclaw/openclaw/main/dist/protocol.schema.json
 
 ## When you change schemas
 

package/docs/concepts/typing-indicators.md

@@ -1,5 +1,5 @@
 ---
-summary: "When Moltbot shows typing indicators and how to tune them"
+summary: "When OpenClaw shows typing indicators and how to tune them"
 read_when:
   - Changing typing indicator behavior or defaults
 ---
@@ -10,7 +10,7 @@ Typing indicators are sent to the chat channel while a run is active. Use
 to control **how often** it refreshes.
 
 ## Defaults
-When `agents.defaults.typingMode` is **unset**, Moltbot keeps the legacy behavior:
+When `agents.defaults.typingMode` is **unset**, OpenClaw keeps the legacy behavior:
 - **Direct chats**: typing starts immediately once the model loop begins.
 - **Group chats with a mention**: typing starts immediately.
 - **Group chats without a mention**: typing starts only when message text begins streaming.

package/docs/concepts/usage-tracking.md

@@ -13,9 +13,9 @@ read_when:
 ## Where it shows up
 - `/status` in chats: emoji‑rich status card with session tokens + estimated cost (API key only). Provider usage shows for the **current model provider** when available.
 - `/usage off|tokens|full` in chats: per-response usage footer (OAuth shows tokens only).
-- `/usage cost` in chats: local cost summary aggregated from Moltbot session logs.
-- CLI: `moltbot status --usage` prints a full per-provider breakdown.
-- CLI: `moltbot channels list` prints the same usage snapshot alongside provider config (use `--no-usage` to skip).
+- `/usage cost` in chats: local cost summary aggregated from OpenClaw session logs.
+- CLI: `openclaw status --usage` prints a full per-provider breakdown.
+- CLI: `openclaw channels list` prints the same usage snapshot alongside provider config (use `--no-usage` to skip).
 - macOS menu bar: “Usage” section under Context (only if available).
 
 ## Providers + credentials

package/docs/date-time.md

@@ -7,7 +7,7 @@ read_when:
 
 # Date & Time
 
-Moltbot defaults to **host-local time for transport timestamps** and **user timezone only in the system prompt**.
+OpenClaw defaults to **host-local time for transport timestamps** and **user timezone only in the system prompt**.
 Provider timestamps are preserved so tools keep their native semantics (current time is available via `session_status`).
 
 ## Message envelopes (local by default)
@@ -101,7 +101,7 @@ System: [2026-01-12 12:19:17 PST] Model switched.
 
 ## Time format detection (auto)
 
-When `timeFormat: "auto"`, Moltbot inspects the OS preference (macOS/Windows)
+When `timeFormat: "auto"`, OpenClaw inspects the OS preference (macOS/Windows)
 and falls back to locale formatting. The detected value is **cached per process**
 to avoid repeated system calls.
 

package/docs/debug/node-issue.md

@@ -2,16 +2,16 @@
 summary: Node + tsx "__name is not a function" crash notes and workarounds
 read_when:
   - Debugging Node-only dev scripts or watch mode failures
-  - Investigating tsx/esbuild loader crashes in Moltbot
+  - Investigating tsx/esbuild loader crashes in OpenClaw
 ---
 
 # Node + tsx "__name is not a function" crash
 
 ## Summary
-Running Moltbot via Node with `tsx` fails at startup with:
+Running OpenClaw via Node with `tsx` fails at startup with:
 
 ```
-[moltbot] Failed to start CLI: TypeError: __name is not a function
+[openclaw] Failed to start CLI: TypeError: __name is not a function
     at createSubsystemLogger (.../src/logging/subsystem.ts:203:25)
     at .../src/agents/auth-profiles/constants.ts:25:20
 ```
@@ -48,16 +48,16 @@ node --import tsx scripts/repro/tsx-name-repro.ts
 
 ## Regression history
 - `2871657e` (2026-01-06): scripts changed from Bun to tsx to make Bun optional.
-- Before that (Bun path), `moltbot status` and `gateway:watch` worked.
+- Before that (Bun path), `openclaw status` and `gateway:watch` worked.
 
 ## Workarounds
 - Use Bun for dev scripts (current temporary revert).
 - Use Node + tsc watch, then run compiled output:
   ```bash
   pnpm exec tsc --watch --preserveWatchOutput
-  node --watch dist/entry.js status
+  node --watch openclaw.mjs status
   ```
-- Confirmed locally: `pnpm exec tsc -p tsconfig.json` + `node dist/entry.js status` works on Node 25.
+- Confirmed locally: `pnpm exec tsc -p tsconfig.json` + `node openclaw.mjs status` works on Node 25.
 - Disable esbuild keepNames in the TS loader if possible (prevents `__name` helper insertion); tsx does not currently expose this.
 - Test Node LTS (22/24) with `tsx` to see if the issue is Node 25–specific.
 

package/docs/debugging.md

@@ -15,13 +15,13 @@ provider mixes reasoning into normal text.
 
 Use `/debug` in chat to set **runtime-only** config overrides (memory, not disk).
 `/debug` is disabled by default; enable with `commands.debug: true`.
-This is handy when you need to toggle obscure settings without editing `moltbot.json`.
+This is handy when you need to toggle obscure settings without editing `openclaw.json`.
 
 Examples:
 
 ```
 /debug show
-/debug set messages.responsePrefix="[moltbot]"
+/debug set messages.responsePrefix="[openclaw]"
 /debug unset messages.responsePrefix
 /debug reset
 ```
@@ -50,7 +50,7 @@ on each restart.
 Use the dev profile to isolate state and spin up a safe, disposable setup for
 debugging. There are **two** `--dev` flags:
 
-- **Global `--dev` (profile):** isolates state under `~/.clawdbot-dev` and
+- **Global `--dev` (profile):** isolates state under `~/.openclaw-dev` and
   defaults the gateway port to `19001` (derived ports shift with it).
 - **`gateway --dev`: tells the Gateway to auto-create a default config +
   workspace** when missing (and skip BOOTSTRAP.md).
@@ -59,18 +59,18 @@ Recommended flow (dev profile + dev bootstrap):
 
 ```bash
 pnpm gateway:dev
-CLAWDBOT_PROFILE=dev moltbot tui
+OPENCLAW_PROFILE=dev openclaw tui
 ```
 
-If you don’t have a global install yet, run the CLI via `pnpm moltbot ...`.
+If you don’t have a global install yet, run the CLI via `pnpm openclaw ...`.
 
 What this does:
 
 1) **Profile isolation** (global `--dev`)
-   - `CLAWDBOT_PROFILE=dev`
-   - `CLAWDBOT_STATE_DIR=~/.clawdbot-dev`
-   - `CLAWDBOT_CONFIG_PATH=~/.clawdbot-dev/moltbot.json`
-   - `CLAWDBOT_GATEWAY_PORT=19001` (browser/canvas shift accordingly)
+   - `OPENCLAW_PROFILE=dev`
+   - `OPENCLAW_STATE_DIR=~/.openclaw-dev`
+   - `OPENCLAW_CONFIG_PATH=~/.openclaw-dev/openclaw.json`
+   - `OPENCLAW_GATEWAY_PORT=19001` (browser/canvas shift accordingly)
 
 2) **Dev bootstrap** (`gateway --dev`)
    - Writes a minimal config if missing (`gateway.mode=local`, bind loopback).
@@ -79,7 +79,7 @@ What this does:
    - Seeds the workspace files if missing:
      `AGENTS.md`, `SOUL.md`, `TOOLS.md`, `IDENTITY.md`, `USER.md`, `HEARTBEAT.md`.
    - Default identity: **C3‑PO** (protocol droid).
-   - Skips channel providers in dev mode (`CLAWDBOT_SKIP_CHANNELS=1`).
+   - Skips channel providers in dev mode (`OPENCLAW_SKIP_CHANNELS=1`).
 
 Reset flow (fresh start):
 
@@ -91,7 +91,7 @@ Note: `--dev` is a **global** profile flag and gets eaten by some runners.
 If you need to spell it out, use the env var form:
 
 ```bash
-CLAWDBOT_PROFILE=dev moltbot gateway --dev --reset
+OPENCLAW_PROFILE=dev openclaw gateway --dev --reset
 ```
 
 `--reset` wipes config, credentials, sessions, and the dev workspace (using
@@ -100,12 +100,12 @@ CLAWDBOT_PROFILE=dev moltbot gateway --dev --reset
 Tip: if a non‑dev gateway is already running (launchd/systemd), stop it first:
 
 ```bash
-moltbot gateway stop
+openclaw gateway stop
 ```
 
-## Raw stream logging (Moltbot)
+## Raw stream logging (OpenClaw)
 
-Moltbot can log the **raw assistant stream** before any filtering/formatting.
+OpenClaw can log the **raw assistant stream** before any filtering/formatting.
 This is the best way to see whether reasoning is arriving as plain text deltas
 (or as separate thinking blocks).
 
@@ -118,19 +118,19 @@ pnpm gateway:watch --force --raw-stream
 Optional path override:
 
 ```bash
-pnpm gateway:watch --force --raw-stream --raw-stream-path ~/.clawdbot/logs/raw-stream.jsonl
+pnpm gateway:watch --force --raw-stream --raw-stream-path ~/.openclaw/logs/raw-stream.jsonl
 ```
 
 Equivalent env vars:
 
 ```bash
-CLAWDBOT_RAW_STREAM=1
-CLAWDBOT_RAW_STREAM_PATH=~/.clawdbot/logs/raw-stream.jsonl
+OPENCLAW_RAW_STREAM=1
+OPENCLAW_RAW_STREAM_PATH=~/.openclaw/logs/raw-stream.jsonl
 ```
 
 Default file:
 
-`~/.clawdbot/logs/raw-stream.jsonl`
+`~/.openclaw/logs/raw-stream.jsonl`
 
 ## Raw chunk logging (pi-mono)
 

package/docs/diagnostics/flags.md

@@ -41,13 +41,13 @@ Restart the gateway after changing flags.
 ## Env override (one-off)
 
 ```bash
-CLAWDBOT_DIAGNOSTICS=telegram.http,telegram.payload
+OPENCLAW_DIAGNOSTICS=telegram.http,telegram.payload
 ```
 
 Disable all flags:
 
 ```bash
-CLAWDBOT_DIAGNOSTICS=0
+OPENCLAW_DIAGNOSTICS=0
 ```
 
 ## Where logs go
@@ -55,7 +55,7 @@ CLAWDBOT_DIAGNOSTICS=0
 Flags emit logs into the standard diagnostics log file. By default:
 
 ```
-/tmp/moltbot/moltbot-YYYY-MM-DD.log
+/tmp/openclaw/openclaw-YYYY-MM-DD.log
 ```
 
 If you set `logging.file`, use that path instead. Logs are JSONL (one JSON object per line). Redaction still applies based on `logging.redactSensitive`.
@@ -65,22 +65,22 @@ If you set `logging.file`, use that path instead. Logs are JSONL (one JSON objec
 Pick the latest log file:
 
 ```bash
-ls -t /tmp/moltbot/moltbot-*.log | head -n 1
+ls -t /tmp/openclaw/openclaw-*.log | head -n 1
 ```
 
 Filter for Telegram HTTP diagnostics:
 
 ```bash
-rg "telegram http error" /tmp/moltbot/moltbot-*.log
+rg "telegram http error" /tmp/openclaw/openclaw-*.log
 ```
 
 Or tail while reproducing:
 
 ```bash
-tail -f /tmp/moltbot/moltbot-$(date +%F).log | rg "telegram http error"
+tail -f /tmp/openclaw/openclaw-$(date +%F).log | rg "telegram http error"
 ```
 
-For remote gateways, you can also use `moltbot logs --follow` (see [/cli/logs](/cli/logs)).
+For remote gateways, you can also use `openclaw logs --follow` (see [/cli/logs](/cli/logs)).
 
 ## Notes
 

package/docs/docs.json

@@ -1,6 +1,6 @@
 {
   "$schema": "https://mintlify.com/docs.json",
-  "name": "Moltbot",
+  "name": "OpenClaw",
   "theme": "mint",
   "logo": {
     "light": "/assets/pixel-lobster.svg",
@@ -13,11 +13,11 @@
   "topbarLinks": [
     {
       "name": "GitHub",
-      "url": "https://github.com/moltbot/moltbot"
+      "url": "https://github.com/openclaw/openclaw"
     },
     {
       "name": "Releases",
-      "url": "https://github.com/moltbot/moltbot/releases"
+      "url": "https://github.com/openclaw/openclaw/releases"
     }
   ],
   "redirects": [
@@ -69,6 +69,14 @@
       "source": "/minimax/",
       "destination": "/providers/minimax"
     },
+    {
+      "source": "/xiaomi",
+      "destination": "/providers/xiaomi"
+    },
+    {
+      "source": "/xiaomi/",
+      "destination": "/providers/xiaomi"
+    },
     {
       "source": "/openai",
       "destination": "/providers/openai"
@@ -351,7 +359,15 @@
     },
     {
       "source": "/clawd",
-      "destination": "/start/clawd"
+      "destination": "/start/openclaw"
+    },
+    {
+      "source": "/start/clawd",
+      "destination": "/start/openclaw"
+    },
+    {
+      "source": "/start/clawd/",
+      "destination": "/start/openclaw"
     },
     {
       "source": "/clawdhub",
@@ -824,7 +840,7 @@
           "start/wizard",
           "start/setup",
           "start/pairing",
-          "start/clawd",
+          "start/openclaw",
           "start/showcase",
           "start/hubs",
           "start/onboarding",

package/docs/environment.md

@@ -1,5 +1,5 @@
 ---
-summary: "Where Moltbot loads environment variables and the precedence order"
+summary: "Where OpenClaw loads environment variables and the precedence order"
 read_when:
   - You need to know which env vars are loaded, and in what order
   - You are debugging missing API keys in the Gateway
@@ -7,15 +7,15 @@ read_when:
 ---
 # Environment variables
 
-Moltbot pulls environment variables from multiple sources. The rule is **never override existing values**.
+OpenClaw pulls environment variables from multiple sources. The rule is **never override existing values**.
 
 ## Precedence (highest → lowest)
 
 1) **Process environment** (what the Gateway process already has from the parent shell/daemon).
 2) **`.env` in the current working directory** (dotenv default; does not override).
-3) **Global `.env`** at `~/.clawdbot/.env` (aka `$CLAWDBOT_STATE_DIR/.env`; does not override).
-4) **Config `env` block** in `~/.clawdbot/moltbot.json` (applied only if missing).
-5) **Optional login-shell import** (`env.shellEnv.enabled` or `CLAWDBOT_LOAD_SHELL_ENV=1`), applied only for missing expected keys.
+3) **Global `.env`** at `~/.openclaw/.env` (aka `$OPENCLAW_STATE_DIR/.env`; does not override).
+4) **Config `env` block** in `~/.openclaw/openclaw.json` (applied only if missing).
+5) **Optional login-shell import** (`env.shellEnv.enabled` or `OPENCLAW_LOAD_SHELL_ENV=1`), applied only for missing expected keys.
 
 If the config file is missing entirely, step 4 is skipped; shell import still runs if enabled.
 
@@ -50,8 +50,8 @@ Two equivalent ways to set inline env vars (both are non-overriding):
 ```
 
 Env var equivalents:
-- `CLAWDBOT_LOAD_SHELL_ENV=1`
-- `CLAWDBOT_SHELL_ENV_TIMEOUT_MS=15000`
+- `OPENCLAW_LOAD_SHELL_ENV=1`
+- `OPENCLAW_SHELL_ENV_TIMEOUT_MS=15000`
 
 ## Env var substitution in config
 

package/docs/experiments/plans/cron-add-hardening.md

@@ -1,6 +1,6 @@
 ---
 summary: "Harden cron.add input handling, align schemas, and improve cron UI/agent tooling"
-owner: "moltbot"
+owner: "openclaw"
 status: "complete"
 last_updated: "2026-01-05"
 ---

package/docs/experiments/plans/openresponses-gateway.md

@@ -1,6 +1,6 @@
 ---
 summary: "Plan: Add OpenResponses /v1/responses endpoint and deprecate chat completions cleanly"
-owner: "moltbot"
+owner: "openclaw"
 status: "draft"
 last_updated: "2026-01-19"
 ---
@@ -9,7 +9,7 @@ last_updated: "2026-01-19"
 
 ## Context
 
-Moltbot Gateway currently exposes a minimal OpenAI-compatible Chat Completions endpoint at
+OpenClaw Gateway currently exposes a minimal OpenAI-compatible Chat Completions endpoint at
 `/v1/chat/completions` (see [OpenAI Chat Completions](/gateway/openai-http-api)).
 
 Open Responses is an open inference standard based on the OpenAI Responses API. It is designed

package/docs/experiments/research/memory.md

@@ -1,14 +1,14 @@
 ---
 summary: "Research notes: offline memory system for Clawd workspaces (Markdown source-of-truth + derived index)"
 read_when:
-  - Designing workspace memory (~/clawd) beyond daily Markdown logs
-  - Deciding: standalone CLI vs deep Moltbot integration
+  - Designing workspace memory (~/.openclaw/workspace) beyond daily Markdown logs
+  - Deciding: standalone CLI vs deep OpenClaw integration
   - Adding offline recall + reflection (retain/recall/reflect)
 ---
 
 # Workspace Memory v2 (offline): research notes
 
-Target: Clawd-style workspace (`agents.defaults.workspace`, default `~/clawd`) where “memory” is stored as one Markdown file per day (`memory/YYYY-MM-DD.md`) plus a small set of stable files (e.g. `memory.md`, `SOUL.md`).
+Target: Clawd-style workspace (`agents.defaults.workspace`, default `~/.openclaw/workspace`) where “memory” is stored as one Markdown file per day (`memory/YYYY-MM-DD.md`) plus a small set of stable files (e.g. `memory.md`, `SOUL.md`).
 
 This doc proposes an **offline-first** memory architecture that keeps Markdown as the canonical, reviewable source of truth, but adds **structured recall** (search, entity summaries, confidence updates) via a derived index.
 
@@ -53,12 +53,12 @@ Two pieces to blend:
 
 ### Canonical store (git-friendly)
 
-Keep `~/clawd` as canonical human-readable memory.
+Keep `~/.openclaw/workspace` as canonical human-readable memory.
 
 Suggested workspace layout:
 
 ```
-~/clawd/
+~/.openclaw/workspace/
   memory.md                    # small: durable facts + preferences (core-ish)
   memory/
     YYYY-MM-DD.md              # daily log (append; narrative)
@@ -83,7 +83,7 @@ Notes:
 Add a derived index under the workspace (not necessarily git tracked):
 
 ```
-~/clawd/.memory/index.sqlite
+~/.openclaw/workspace/.memory/index.sqlite
 ```
 
 Back it with:
@@ -155,16 +155,16 @@ Opinion evolution (simple, explainable):
 
 ## CLI integration: standalone vs deep integration
 
-Recommendation: **deep integration in Moltbot**, but keep a separable core library.
+Recommendation: **deep integration in OpenClaw**, but keep a separable core library.
 
-### Why integrate into Moltbot?
-- Moltbot already knows:
+### Why integrate into OpenClaw?
+- OpenClaw already knows:
   - the workspace path (`agents.defaults.workspace`)
   - the session model + heartbeats
   - logging + troubleshooting patterns
 - You want the agent itself to call the tools:
-  - `moltbot memory recall "…" --k 25 --since 30d`
-  - `moltbot memory reflect --since 7d`
+  - `openclaw memory recall "…" --k 25 --since 30d`
+  - `openclaw memory reflect --since 7d`
 
 ### Why still split a library?
 - keep memory logic testable without gateway/runtime
@@ -177,7 +177,7 @@ The memory tooling is intended to be a small CLI + library layer, but this is ex
 
 If “S-Collide” refers to **SuCo (Subspace Collision)**: it’s an ANN retrieval approach that targets strong recall/latency tradeoffs by using learned/structured collisions in subspaces (paper: arXiv 2411.14754, 2024).
 
-Pragmatic take for `~/clawd`:
+Pragmatic take for `~/.openclaw/workspace`:
 - **don’t start** with SuCo.
 - start with SQLite FTS + (optional) simple embeddings; you’ll get most UX wins immediately.
 - consider SuCo/HNSW/ScaNN-class solutions only once: