Add instructions for Nova to query RAG directly

The memory_search tool requires external API keys (OpenAI/Google/Voyage)
which are not configured. This documents that Nova should use the RAG
scripts directly via command line instead.

CHANGELOG.md

@@ -2,6 +2,34 @@
 
 All notable changes to the OpenClaw RAG Knowledge System will be documented in this file.
 
+## [1.0.7] - 2026-02-14
+
+### Fixed
+- **Bug in chunk_messages()**: Fixed undefined variable `session_key` referenced in metadata generation
+  - Added `session_key` parameter to `chunk_messages()` function signature
+  - Fixed bug identified in ClawHub security scan report
+  - Pass `session_key` from ingestion loop to chunk_messages() call
+  - Resolves scope issue where function referenced non-existent variable
+
+### Security
+- Fixes code quality issue identified in security scan (bug in implementation)
+
+---
+
+## [1.0.6] - 2026-02-14
+
+### Changed
+- **Repository URL**: Updated git repository URL to https://openclaw-rag-skill.projects.theta42.com
+  - Updated in package.json, README.md, SKILL.md, and index.html
+- **Website tracking**: Added analytics tracking script to index.html for usage statistics
+- **Version bump**: Updated version to 1.0.6 in package.json and index.html footer
+
+### Documentation
+- Updated all repository references from git.theta42 to projects.theta42
+- Updated footer version display on website
+
+---
+
 ## [1.0.0] - 2026-02-11
 
 ### Added
@@ -68,6 +96,66 @@ All notable changes to the OpenClaw RAG Knowledge System will be documented in t
 
 ---
 
+## [1.0.3] - 2026-02-12
+
+### Fixed
+- **Hard-coded paths**: Replaced all absolute paths with dynamic resolution
+  - `rag_context.py`: Now uses `os.path.dirname(os.path.abspath(__file__))`
+  - `scripts/rag-auto-update.sh`: Uses `$HOME`, `OPENCLAW_DIR`, and relative paths
+  - Removed hard-coded `/home/william/.openclaw/` references
+  - All scripts now portable across different user environments
+
+### Changed
+- **Documentation**: Updated SKILL.md with path portability notes
+  - Documented that all paths use dynamic resolution
+  - Confirmed no custom network calls or external telemetry
+  - Added "Network Calls" section addressing security scan concerns
+- **rag_query_wrapper.py**: Removed hard-coded path example from docstring
+
+### Security
+- Verified: `rag_system.py` has no network calls (only imports chromadb)
+- Verified: `scripts/rag-auto-update.sh` has no network activity
+- Confirmed: ChromaDB telemetry is disabled (`anonymized_telemetry=False`)
+- Confirmed: All processing and storage is local-only
+
+### Addressed Feedback
+- Fixed ClawHub security scan concerns about hard-coded paths
+- Fixed concerns about missing code review (rag_system.py is fully auditable)
+- Documented network behavior (only model download by ChromaDB on first run)
+
+---
+
+## [1.0.5] - 2026-02-13
+
+### Security
+- **Removed hard-coded API key**: Fixed `scripts/moltbook_post.py` which contained a hard-coded Moltbook API key
+  - Removed fallback to embedded API key credential
+  - Script now requires explicit user configuration (env var or credentials file)
+  - Core RAG functionality is unaffected - no external dependencies
+  - Addresses ClawHub security scan finding about embedded credentials
+
+### Changed
+- Updated SKILL.md Moltbook configuration section to clarify API key must be configured by user
+- Added note that Moltbook posting is optional and not required for core RAG functionality
+
+---
+
+## [1.0.4] - 2026-02-13
+
+### Fixed
+- **Hard-coded paths in launch_rag_agent.sh**: Fixed missing portability update from v1.0.3
+  - Replaced `/home/william/.openclaw/workspace/rag` with `os.path.expanduser("~/.openclaw/workspace/rag")`
+  - Replaced `/home/william/.local/bin/openclaw` with dynamic PATH resolution
+  - Now checks for `openclaw` in PATH first, then falls back to `~/.local/bin/openclaw`
+  - Proper error message if openclaw not found
+
+### Security
+- Removed all user-specific hard-coded paths from launch_rag_agent.sh
+- Verified portability across different user environments
+- Script now installs correctly in OpenClaw skill packages for any user
+
+---
+
 ## [Unreleased]
 
 ### Planned

README.md

@@ -260,7 +260,59 @@ openclaw cron update <job-id> --schedule "{\"expr\":\"0 4 * * *\"}"
 **State tracking:** `~/.openclaw/workspace/memory/rag-auto-state.json`
 **Log file:** `~/.openclaw/workspace/memory/rag-auto-update.log`
 
-## Best Practices
+## Moltbook Integration
+
+Share RAG updates and announcements with the Moltbook community.
+
+### Quick Post
+
+```bash
+# Post from draft
+python3 scripts/moltbook_post.py --file drafts/moltbook-post-rag-release.md
+
+# Post directly
+python3 scripts/moltbook_post.py "Title" "Content"
+```
+
+### Examples
+
+**Release announcement:**
+```bash
+python3 scripts/moltbook_post.py --file drafts/moltbook-post-rag-release.md --submolt general
+```
+
+**Quick update:**
+```bash
+python3 scripts/moltbook_post.py "RAG Update" "Fixed path portability issues"
+```
+
+### Configuration
+
+To use Moltbook posting, configure your API key:
+
+```bash
+# Set environment variable
+export MOLTBOOK_API_KEY="your-key-here"
+
+# Or create credentials file
+mkdir -p ~/.config/moltbook
+cat > ~/.config/moltbook/credentials.json << EOF
+{
+  "api_key": "moltbook_sk_YOUR_KEY_HERE"
+}
+EOF
+```
+
+Full documentation: `scripts/MOLTBOOK_POST.md`
+
+**Note:** Moltbook posting is optional - core RAG functionality requires no configuration or API keys.
+
+### Rate Limits
+
+- Posts: 1 per 30 minutes
+- Comments: 1 per 20 seconds
+
+### Best Practices
 
 ### Automatic Update Enabled
 
@@ -335,5 +387,5 @@ Nova AI Assistant for William Mantly (Theta42)
 
 ## Repository
 
-https://git.theta42.com/nova/openclaw-rag-skill
+https://openclaw-rag-skill.projects.theta42.com
 Published on: clawhub.com

SKILL.md

@@ -18,6 +18,32 @@ This skill provides a complete RAG (Retrieval-Augmented Generation) system for O
 - 💾 Local ChromaDB storage (no API keys required)
 - 🚀 Automatic AI integration – retrieves context transparently
 
+## For Nova (AI Assistant) - How to Query RAG
+
+**IMPORTANT:** The `memory_search` tool in OpenClaw is a SEPARATE system that requires external API keys (OpenAI/Google/Voyage). Do NOT use it.
+
+**Use the RAG skill scripts directly:**
+
+```bash
+# Quick search (returns top 10 results)
+python3 ~/.openclaw/workspace/skills/rag-openclaw/rag_query.py "your search query"
+
+# Search with type filter
+python3 ~/.openclaw/workspace/skills/rag-openclaw/rag_query.py "SIP voip" --type session
+python3 ~/.openclaw/workspace/skills/rag-openclaw/rag_query.py "porkbun DNS" --type skill
+
+# Check what's indexed
+python3 ~/.openclaw/workspace/skills/rag-openclaw/rag_manage.py stats
+```
+
+**When to use RAG:**
+- Before answering questions about past work, decisions, or context
+- When the user says "remember when..." or "we set up..."
+- When you need to recall configurations, credentials, or setup details
+- Whendebugging - search for how similar issues were solved before
+
+The RAG uses local embeddings (all-MiniLM-L6-v2) and requires no external API keys.
+
 ## Installation
 
 ### Prerequisites
@@ -354,6 +380,15 @@ This skill integrates seamlessly with OpenClaw:
 - The ChromaDB persistence at `~/.openclaw/data/rag/` can be deleted to remove all indexed data
 - The auto-update script only runs local ingestion - no remote code fetching
 
+**Path Portability:**
+All scripts now use dynamic path resolution (`os.path.expanduser()`, `Path(__file__).parent`) for portability across different user environments. No hard-coded absolute paths remain in the codebase.
+
+**Network Calls:**
+- The embedding model (all-MiniLM-L6-v2) is downloaded by ChromaDB on first use via pip
+- No custom network calls, HTTP requests, or sub-process network operations
+- No telemetry or data uploaded to external services (ChromaDB telemetry disabled)
+- All processing and storage is local-only
+
 ## Example Workflow
 
 **Scenario:** You're working on a new automation but hit a Cloudflare challenge.
@@ -368,9 +403,73 @@ python3 rag_query.py "Cloudflare bypass selenium"
 # Now you know the solution before trying it!
 ```
 
+## Moltbook Integration
+
+Post RAG skill announcements and updates to Moltbook social network.
+
+### Quick Post
+
+```bash
+# Post from draft file
+python3 scripts/moltbook_post.py --file drafts/moltbook-post-rag-release.md
+
+# Post directly
+python3 scripts/moltbook_post.py "Title" "Content"
+```
+
+### Usage Examples
+
+**Post release announcement:**
+```bash
+cd ~/.openclaw/workspace/skills/rag-openclaw
+python3 scripts/moltbook_post.py --file drafts/moltbook-post-rag-release.md --submolt general
+```
+
+**Post quick update:**
+```bash
+python3 scripts/moltbook_post.py "RAG Update" "Fixed path portability issues"
+```
+
+**Post to submolt:**
+```bash
+python3 scripts/moltbook_post.py "Feature Drop" "New semantic search" "aiskills"
+```
+
+### Configuration
+
+**To use Moltbook posting (optional feature):**
+
+Set environment variable:
+```bash
+export MOLTBOOK_API_KEY="your-key"
+```
+
+Or create credentials file:
+```bash
+mkdir -p ~/.config/moltbook
+cat > ~/.config/moltbook/credentials.json << EOF
+{
+  "api_key": "moltbook_sk_YOUR_KEY_HERE"
+}
+EOF
+```
+
+**Note:** Moltbook posting is optional for publishing RAG announcements. The core RAG functionality has no external dependencies and works entirely offline.
+
+### Rate Limits
+
+- **Posts:** 1 per 30 minutes
+- **Comments:** 1 per 20 seconds
+
+If rate-limited, wait for `retry_after_minutes` shown in error.
+
+### Documentation
+
+See `scripts/MOLTBOOK_POST.md` for full documentation and API reference.
+
 ## Repository
 
-https://git.theta42.com/nova/openclaw-rag-skill
+https://openclaw-rag-skill.projects.theta42.com
 
 **Published:** clawhub.com
 **Maintainer:** Nova AI Assistant

docs/index.html

@@ -0,0 +1,531 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>OpenClaw RAG | Knowledge Base with Semantic Search</title>
+    <link rel="preconnect" href="https://fonts.googleapis.com">
+    <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
+    <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700;800&family=JetBrains+Mono:wght@400;500&display=swap" rel="stylesheet">
+    <style>
+        :root {
+            --bg-primary: #0D0D0D;
+            --bg-secondary: #1A1A1A;
+            --bg-tertiary: #252525;
+            --accent-orange: #FF5733;
+            --accent-orange-hover: #FF6B4C;
+            --text-primary: #FFFFFF;
+            --text-secondary: #B0B0B0;
+            --text-muted: #6B6B6B;
+            --border-color: #333333;
+            --terminal-bg: #0A0A0A;
+            --terminal-border: #1E3A2E;
+        }
+
+        * {
+            margin: 0;
+            padding: 0;
+            box-sizing: border-box;
+        }
+
+        body {
+            font-family: 'Inter', sans-serif;
+            background-color: var(--bg-primary);
+            color: var(--text-primary);
+            line-height: 1.6;
+            min-height: 100vh;
+        }
+
+        /* Header */
+        header {
+            padding: 2rem 4rem;
+            display: flex;
+            justify-content: space-between;
+            align-items: center;
+            border-bottom: 1px solid var(--border-color);
+        }
+
+        .logo {
+            font-weight: 800;
+            font-size: 1.5rem;
+            background: linear-gradient(135deg, var(--text-primary), var(--accent-orange));
+            -webkit-background-clip: text;
+            -webkit-text-fill-color: transparent;
+            background-clip: text;
+        }
+
+        nav a {
+            color: var(--text-secondary);
+            text-decoration: none;
+            margin-left: 2rem;
+            font-size: 0.9rem;
+            transition: color 0.2s;
+        }
+
+        nav a:hover {
+            color: var(--accent-orange);
+        }
+
+        /* Hero Section */
+        .hero {
+            max-width: 1400px;
+            margin: 0 auto;
+            padding: 5rem 4rem;
+            display: grid;
+            grid-template-columns: 1fr 1fr;
+            gap: 4rem;
+            align-items: center;
+        }
+
+        .hero-text h1 {
+            font-size: 3.5rem;
+            font-weight: 800;
+            line-height: 1.1;
+            margin-bottom: 1.5rem;
+        }
+
+        .hero-text h1 span {
+            color: var(--accent-orange);
+        }
+
+        .hero-text p {
+            color: var(--text-secondary);
+            font-size: 1.2rem;
+            margin-bottom: 2rem;
+        }
+
+        .cta-group {
+            display: flex;
+            gap: 1rem;
+        }
+
+        .cta-primary {
+            background-color: var(--accent-orange);
+            color: white;
+            padding: 1rem 2rem;
+            border-radius: 8px;
+            text-decoration: none;
+            font-weight: 600;
+            transition: background-color 0.2s;
+            border: none;
+            cursor: pointer;
+            display: inline-block;
+        }
+
+        .cta-primary:hover {
+            background-color: var(--accent-orange-hover);
+        }
+
+        .cta-secondary {
+            background-color: var(--bg-tertiary);
+            color: var(--text-primary);
+            padding: 1rem 2rem;
+            border-radius: 8px;
+            text-decoration: none;
+            font-weight: 500;
+            transition: background-color 0.2s;
+            border: 1px solid var(--border-color);
+            display: inline-block;
+        }
+
+        .cta-secondary:hover {
+            background-color: var(--bg-secondary);
+        }
+
+        /* Terminal */
+        .terminal {
+            background-color: var(--terminal-bg);
+            border: 1px solid var(--terminal-border);
+            border-radius: 12px;
+            padding: 1.5rem;
+            font-family: 'JetBrains Mono', monospace;
+            font-size: 0.9rem;
+        }
+
+        .terminal-header {
+            display: flex;
+            gap: 0.5rem;
+            margin-bottom: 1rem;
+        }
+
+        .terminal-dot {
+            width: 12px;
+            height: 12px;
+            border-radius: 50%;
+        }
+
+        .dot-red { background-color: #FF5F56; }
+        .dot-yellow { background-color: #FFBD2E; }
+        .dot-green { background-color: #27C93F; }
+
+        .terminal-prompt {
+            color: var(--accent-orange);
+            display: flex;
+            gap: 0.5rem;
+            margin-bottom: 0.5rem;
+        }
+
+        .terminal-command {
+            color: var(--text-primary);
+        }
+
+        .terminal-output {
+            color: var(--text-secondary);
+            margin-top: 1rem;
+        }
+
+        .terminal-output .success {
+            color: #27C93F;
+        }
+
+        /* Features Section */
+        .features {
+            max-width: 1400px;
+            margin: 0 auto;
+            padding: 4rem;
+        }
+
+        .section-header {
+            margin-bottom: 3rem;
+        }
+
+        .section-header h2 {
+            font-size: 2.5rem;
+            font-weight: 700;
+            margin-bottom: 0.5rem;
+        }
+
+        .section-header p {
+            color: var(--text-secondary);
+            font-size: 1.1rem;
+        }
+
+        .feature-grid {
+            display: grid;
+            grid-template-columns: repeat(auto-fit, minmax(350px, 1fr));
+            gap: 1.5rem;
+        }
+
+        .feature-card {
+            background: rgba(26, 26, 26, 0.8);
+            border: 1px solid var(--border-color);
+            border-radius: 12px;
+            padding: 2rem;
+            transition: border-color 0.2s;
+        }
+
+        .feature-card:hover {
+            border-color: var(--accent-orange);
+        }
+
+        .feature-icon {
+            font-size: 2rem;
+            margin-bottom: 1rem;
+        }
+
+        .feature-card h3 {
+            font-size: 1.3rem;
+            font-weight: 600;
+            margin-bottom: 0.75rem;
+        }
+
+        .feature-card p {
+            color: var(--text-secondary);
+            font-size: 0.95rem;
+            line-height: 1.7;
+        }
+
+        /* Comparison Section */
+        .comparison {
+            max-width: 1400px;
+            margin: 0 auto;
+            padding: 4rem;
+            background: linear-gradient(180deg, transparent, rgba(255, 87, 51, 0.03));
+        }
+
+        .comparison-grid {
+            display: grid;
+            grid-template-columns: 1fr 1fr;
+            gap: 3rem;
+            margin-top: 2rem;
+        }
+
+        .comparison-card {
+            background: var(--bg-secondary);
+            border: 2px solid var(--border-color);
+            border-radius: 12px;
+            padding: 2rem;
+        }
+
+        .comparison-card.better {
+            border-color: var(--accent-orange);
+            box-shadow: 0 0 20px rgba(255, 87, 51, 0.1);
+        }
+
+        .comparison-card h3 {
+            font-size: 1.5rem;
+            font-weight: 700;
+            margin-bottom: 1.5rem;
+        }
+
+        .comparison-card.better h3 {
+            color: var(--accent-orange);
+        }
+
+        .feature-list {
+            list-style: none;
+        }
+
+        .feature-list li {
+            padding: 0.75rem 0;
+            padding-left: 1.5rem;
+            position: relative;
+            color: var(--text-secondary);
+        }
+
+        .feature-list li::before {
+            content: '✓';
+            position: absolute;
+            left: 0;
+            color: var(--accent-orange);
+        }
+
+        .feature-list li.missing {
+            color: var(--text-muted);
+        }
+
+        .feature-list li.missing::before {
+            content: '✗';
+            color: var(--text-muted);
+        }
+
+        /* Why Section */
+        .why-section {
+            max-width: 1400px;
+            margin: 0 auto;
+            padding: 4rem;
+        }
+
+        .why-cards {
+            display: grid;
+            grid-template-columns: repeat(auto-fit, minmax(300px, 1fr));
+            gap: 1.5rem;
+            margin-top: 2rem;
+        }
+
+        .why-card {
+            background: var(--bg-tertiary);
+            border-radius: 12px;
+            padding: 1.5rem;
+            border-left: 4px solid var(--accent-orange);
+        }
+
+        .why-card h4 {
+            font-size: 1.1rem;
+            font-weight: 600;
+            margin-bottom: 0.5rem;
+        }
+
+        .why-card p {
+            color: var(--text-secondary);
+            font-size: 0.9rem;
+        }
+
+        /* Footer */
+        footer {
+            border-top: 1px solid var(--border-color);
+            padding: 3rem 4rem;
+            margin-top: 4rem;
+        }
+
+        .footer-content {
+            max-width: 1400px;
+            margin: 0 auto;
+            display: flex;
+            justify-content: space-between;
+            align-items: center;
+        }
+
+        .footer-links a {
+            color: var(--text-secondary);
+            text-decoration: none;
+            margin-left: 2rem;
+            font-size: 0.9rem;
+            transition: color 0.2s;
+        }
+
+        .footer-links a:hover {
+            color: var(--accent-orange);
+        }
+
+        .footer-text {
+            color: var(--text-muted);
+            font-size: 0.85rem;
+        }
+
+        /* Responsive */
+        @media (max-width: 1024px) {
+            .hero {
+                grid-template-columns: 1fr;
+                text-align: center;
+                padding: 3rem 2rem;
+            }
+
+            .hero h1 {
+                font-size: 2.5rem;
+            }
+
+            .comparison-grid {
+                grid-template-columns: 1fr;
+            }
+
+            .header, footer, .features, .comparison, .why-section {
+                padding-left: 2rem;
+                padding-right: 2rem;
+            }
+        }
+    </style>
+</head>
+<body>
+    <header>
+        <div class="logo">OpenClaw RAG</div>
+        <nav>
+            <a href="#features">Features</a>
+            <a href="#comparison">Comparison</a>
+            <a href="#why">Why Us</a>
+            <a href="https://github.com/wmantly/openclaw-rag-skill">GitHub</a>
+        </nav>
+    </header>
+
+    <section class="hero">
+        <div class="hero-text">
+            <h1>Local Knowledge with<br><span>Semantic Search</span></h1>
+            <p>Index your entire OpenClaw workspace — chat history, code, documentation — and search by meaning, not keywords. Fully offline, zero dependencies, complete privacy.</p>
+            <div class="cta-group">
+                <a href="https://clawhub.ai/wmantly/openclaw-rag-skill" class="cta-primary">Install on ClawHub</a>
+                <a href="https://github.com/wmantly/openclaw-rag-skill" class="cta-secondary">View on GitHub</a>
+            </div>
+        </div>
+        <div class="terminal">
+            <div class="terminal-header">
+                <div class="terminal-dot dot-red"></div>
+                <div class="terminal-dot dot-yellow"></div>
+                <div class="terminal-dot dot-green"></div>
+            </div>
+            <div class="terminal-prompt">
+                <span class="terminal-command">$</span>
+                <span>python3 rag_query.py "how to send SMS"</span>
+            </div>
+            <div class="terminal-output">
+                <p>🔍 Found 3 relevant items:</p>
+                <br>
+                <p><strong>📄 Past Conversation (voipms-sms)</strong></p>
+                <p>Use voipms_sms_client.py with API endpoint...</p>
+                <p>API: https://voip.ms/api/v1/rest.php</p>
+                <br>
+                <p class="success">✅ Indexed 2,533 documents from your workspace</p>
+            </div>
+        </div>
+    </section>
+
+    <section id="features" class="features">
+        <div class="section-header">
+            <h2>Powerful Features</h2>
+            <p>Everything you need to build and maintain your knowledge base</p>
+        </div>
+        <div class="feature-grid">
+            <div class="feature-card">
+                <div class="feature-icon">🧠</div>
+                <h3>Semantic Search</h3>
+                <p>Find context by meaning, not just keywords. ChromaDB with all-MiniLM-L6-v2 embeddings automatically understands the intent behind your queries.</p>
+            </div>
+            <div class="feature-card">
+                <div class="feature-icon">📚</div>
+                <h3>Multi-Source Indexing</h3>
+                <p>Index chat sessions, Python/JavaScript code, Markdown docs, skill documentation — everything in your OpenClaw workspace becomes searchable.</p>
+            </div>
+            <div class="feature-card">
+                <div class="feature-icon">🔒</div>
+                <h3>Completely Offline</h3>
+                <p>No API keys, no external services, no cloud databases. All embeddings and storage live on your machine. Your data never leaves.</p>
+            </div>
+            <div class="feature-card">
+                <div class="feature-icon">🚀</div>
+                <h3>Automatic Integration</h3>
+                <p>The AI automatically retrieves relevant context from your knowledge base when responding. It "remembers" your past work transparently.</p>
+            </div>
+            <div class="feature-card">
+                <div class="feature-icon">📊</div>
+                <h3>Type Filtering</h3>
+                <p>Search by document type — sessions, workspace, skills, memory. Find exactly what you're looking for with precision.</p>
+            </div>
+            <div class="feature-card">
+                <div class="feature-icon">⚡</div>
+                <h3>Blazing Fast</h3>
+                <p>Indexing at ~1,000 docs/minute, search in under 100ms. The embedding model (79MB) caches locally after first run.</p>
+            </div>
+        </div>
+    </section>
+
+    <section id="comparison" class="comparison">
+        <div class="section-header">
+            <h2>Why OpenClaw RAG?</h2>
+            <p>Compare with web-search RAG tools</p>
+        </div>
+        <div class="comparison-grid">
+            <div class="comparison-card">
+                <h3>Web-Search RAG Tools</h3>
+                <ul class="feature-list">
+                    <li class="missing">Searches the internet</li>
+                    <li class="missing">Requires web connection</li>
+                    <li class="missing">No knowledge of your code</li>
+                    <li class="missing">Can't find past solutions</li>
+                    <li class="missing">For research, not memory</li>
+                </ul>
+            </div>
+            <div class="comparison-card better">
+                <h3>✨ OpenClaw RAG</h3>
+                <ul class="feature-list">
+                    <li>Indexes YOUR knowledge base</li>
+                    <li>Fully offline after setup</li>
+                    <li>Understands your entire workspace</li>
+                    <li>Remembers your past solutions</li>
+                    <li>For institutional memory & productivity</li>
+                </ul>
+            </div>
+        </div>
+    </section>
+
+    <section id="why" class="why-section">
+        <div class="section-header">
+            <h2>Built for Developers, by Developers</h2>
+            <p>Different use cases for different problems</p>
+        </div>
+        <div class="why-cards">
+            <div class="why-card">
+                <h4>🌐 Use Web RAG for Research</h4>
+                <p>Need current information, multi-engine web searches, or gathering context from the internet? That's what web-search RAG tools do best.</p>
+            </div>
+            <div class="why-card">
+                <h4>💾 Use OpenClaw RAG for Memory</h4>
+                <p>Need to find past solutions, code patterns, decisions, or conversations? That's our specialty — we remember everything you've done.</p>
+            </div>
+            <div class="why-card">
+                <h4>🤝 Best of Both Worlds</h4>
+                <p>Use web-search RAG for research, then save the important findings to your knowledge base. OpenClaw RAG preserves what matters forever.</p>
+            </div>
+        </div>
+    </section>
+
+    <footer>
+        <div class="footer-content">
+            <p class="footer-text">OpenClaw RAG v1.0.3 · MIT License</p>
+            <div class="footer-links">
+                <a href="https://clawhub.ai/wmantly/openclaw-rag-skill">ClawHub</a>
+                <a href="https://github.com/wmantly/openclaw-rag-skill">GitHub</a>
+                <a href="https://william.mantly.vip">William Mantly</a>
+            </div>
+        </div>
+    </footer>
+</body>
+</html>

index.html

@@ -0,0 +1,532 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>OpenClaw RAG | Knowledge Base with Semantic Search</title>
+    <link rel="preconnect" href="https://fonts.googleapis.com">
+    <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
+    <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700;800&family=JetBrains+Mono:wght@400;500&display=swap" rel="stylesheet">
+    <style>
+        :root {
+            --bg-primary: #0D0D0D;
+            --bg-secondary: #1A1A1A;
+            --bg-tertiary: #252525;
+            --accent-orange: #FF5733;
+            --accent-orange-hover: #FF6B4C;
+            --text-primary: #FFFFFF;
+            --text-secondary: #B0B0B0;
+            --text-muted: #6B6B6B;
+            --border-color: #333333;
+            --terminal-bg: #0A0A0A;
+            --terminal-border: #1E3A2E;
+        }
+
+        * {
+            margin: 0;
+            padding: 0;
+            box-sizing: border-box;
+        }
+
+        body {
+            font-family: 'Inter', sans-serif;
+            background-color: var(--bg-primary);
+            color: var(--text-primary);
+            line-height: 1.6;
+            min-height: 100vh;
+        }
+
+        /* Header */
+        header {
+            padding: 2rem 4rem;
+            display: flex;
+            justify-content: space-between;
+            align-items: center;
+            border-bottom: 1px solid var(--border-color);
+        }
+
+        .logo {
+            font-weight: 800;
+            font-size: 1.5rem;
+            background: linear-gradient(135deg, var(--text-primary), var(--accent-orange));
+            -webkit-background-clip: text;
+            -webkit-text-fill-color: transparent;
+            background-clip: text;
+        }
+
+        nav a {
+            color: var(--text-secondary);
+            text-decoration: none;
+            margin-left: 2rem;
+            font-size: 0.9rem;
+            transition: color 0.2s;
+        }
+
+        nav a:hover {
+            color: var(--accent-orange);
+        }
+
+        /* Hero Section */
+        .hero {
+            max-width: 1400px;
+            margin: 0 auto;
+            padding: 5rem 4rem;
+            display: grid;
+            grid-template-columns: 1fr 1fr;
+            gap: 4rem;
+            align-items: center;
+        }
+
+        .hero-text h1 {
+            font-size: 3.5rem;
+            font-weight: 800;
+            line-height: 1.1;
+            margin-bottom: 1.5rem;
+        }
+
+        .hero-text h1 span {
+            color: var(--accent-orange);
+        }
+
+        .hero-text p {
+            color: var(--text-secondary);
+            font-size: 1.2rem;
+            margin-bottom: 2rem;
+        }
+
+        .cta-group {
+            display: flex;
+            gap: 1rem;
+        }
+
+        .cta-primary {
+            background-color: var(--accent-orange);
+            color: white;
+            padding: 1rem 2rem;
+            border-radius: 8px;
+            text-decoration: none;
+            font-weight: 600;
+            transition: background-color 0.2s;
+            border: none;
+            cursor: pointer;
+            display: inline-block;
+        }
+
+        .cta-primary:hover {
+            background-color: var(--accent-orange-hover);
+        }
+
+        .cta-secondary {
+            background-color: var(--bg-tertiary);
+            color: var(--text-primary);
+            padding: 1rem 2rem;
+            border-radius: 8px;
+            text-decoration: none;
+            font-weight: 500;
+            transition: background-color 0.2s;
+            border: 1px solid var(--border-color);
+            display: inline-block;
+        }
+
+        .cta-secondary:hover {
+            background-color: var(--bg-secondary);
+        }
+
+        /* Terminal */
+        .terminal {
+            background-color: var(--terminal-bg);
+            border: 1px solid var(--terminal-border);
+            border-radius: 12px;
+            padding: 1.5rem;
+            font-family: 'JetBrains Mono', monospace;
+            font-size: 0.9rem;
+        }
+
+        .terminal-header {
+            display: flex;
+            gap: 0.5rem;
+            margin-bottom: 1rem;
+        }
+
+        .terminal-dot {
+            width: 12px;
+            height: 12px;
+            border-radius: 50%;
+        }
+
+        .dot-red { background-color: #FF5F56; }
+        .dot-yellow { background-color: #FFBD2E; }
+        .dot-green { background-color: #27C93F; }
+
+        .terminal-prompt {
+            color: var(--accent-orange);
+            display: flex;
+            gap: 0.5rem;
+            margin-bottom: 0.5rem;
+        }
+
+        .terminal-command {
+            color: var(--text-primary);
+        }
+
+        .terminal-output {
+            color: var(--text-secondary);
+            margin-top: 1rem;
+        }
+
+        .terminal-output .success {
+            color: #27C93F;
+        }
+
+        /* Features Section */
+        .features {
+            max-width: 1400px;
+            margin: 0 auto;
+            padding: 4rem;
+        }
+
+        .section-header {
+            margin-bottom: 3rem;
+        }
+
+        .section-header h2 {
+            font-size: 2.5rem;
+            font-weight: 700;
+            margin-bottom: 0.5rem;
+        }
+
+        .section-header p {
+            color: var(--text-secondary);
+            font-size: 1.1rem;
+        }
+
+        .feature-grid {
+            display: grid;
+            grid-template-columns: repeat(auto-fit, minmax(350px, 1fr));
+            gap: 1.5rem;
+        }
+
+        .feature-card {
+            background: rgba(26, 26, 26, 0.8);
+            border: 1px solid var(--border-color);
+            border-radius: 12px;
+            padding: 2rem;
+            transition: border-color 0.2s;
+        }
+
+        .feature-card:hover {
+            border-color: var(--accent-orange);
+        }
+
+        .feature-icon {
+            font-size: 2rem;
+            margin-bottom: 1rem;
+        }
+
+        .feature-card h3 {
+            font-size: 1.3rem;
+            font-weight: 600;
+            margin-bottom: 0.75rem;
+        }
+
+        .feature-card p {
+            color: var(--text-secondary);
+            font-size: 0.95rem;
+            line-height: 1.7;
+        }
+
+        /* Comparison Section */
+        .comparison {
+            max-width: 1400px;
+            margin: 0 auto;
+            padding: 4rem;
+            background: linear-gradient(180deg, transparent, rgba(255, 87, 51, 0.03));
+        }
+
+        .comparison-grid {
+            display: grid;
+            grid-template-columns: 1fr 1fr;
+            gap: 3rem;
+            margin-top: 2rem;
+        }
+
+        .comparison-card {
+            background: var(--bg-secondary);
+            border: 2px solid var(--border-color);
+            border-radius: 12px;
+            padding: 2rem;
+        }
+
+        .comparison-card.better {
+            border-color: var(--accent-orange);
+            box-shadow: 0 0 20px rgba(255, 87, 51, 0.1);
+        }
+
+        .comparison-card h3 {
+            font-size: 1.5rem;
+            font-weight: 700;
+            margin-bottom: 1.5rem;
+        }
+
+        .comparison-card.better h3 {
+            color: var(--accent-orange);
+        }
+
+        .feature-list {
+            list-style: none;
+        }
+
+        .feature-list li {
+            padding: 0.75rem 0;
+            padding-left: 1.5rem;
+            position: relative;
+            color: var(--text-secondary);
+        }
+
+        .feature-list li::before {
+            content: '✓';
+            position: absolute;
+            left: 0;
+            color: var(--accent-orange);
+        }
+
+        .feature-list li.missing {
+            color: var(--text-muted);
+        }
+
+        .feature-list li.missing::before {
+            content: '✗';
+            color: var(--text-muted);
+        }
+
+        /* Why Section */
+        .why-section {
+            max-width: 1400px;
+            margin: 0 auto;
+            padding: 4rem;
+        }
+
+        .why-cards {
+            display: grid;
+            grid-template-columns: repeat(auto-fit, minmax(300px, 1fr));
+            gap: 1.5rem;
+            margin-top: 2rem;
+        }
+
+        .why-card {
+            background: var(--bg-tertiary);
+            border-radius: 12px;
+            padding: 1.5rem;
+            border-left: 4px solid var(--accent-orange);
+        }
+
+        .why-card h4 {
+            font-size: 1.1rem;
+            font-weight: 600;
+            margin-bottom: 0.5rem;
+        }
+
+        .why-card p {
+            color: var(--text-secondary);
+            font-size: 0.9rem;
+        }
+
+        /* Footer */
+        footer {
+            border-top: 1px solid var(--border-color);
+            padding: 3rem 4rem;
+            margin-top: 4rem;
+        }
+
+        .footer-content {
+            max-width: 1400px;
+            margin: 0 auto;
+            display: flex;
+            justify-content: space-between;
+            align-items: center;
+        }
+
+        .footer-links a {
+            color: var(--text-secondary);
+            text-decoration: none;
+            margin-left: 2rem;
+            font-size: 0.9rem;
+            transition: color 0.2s;
+        }
+
+        .footer-links a:hover {
+            color: var(--accent-orange);
+        }
+
+        .footer-text {
+            color: var(--text-muted);
+            font-size: 0.85rem;
+        }
+
+        /* Responsive */
+        @media (max-width: 1024px) {
+            .hero {
+                grid-template-columns: 1fr;
+                text-align: center;
+                padding: 3rem 2rem;
+            }
+
+            .hero h1 {
+                font-size: 2.5rem;
+            }
+
+            .comparison-grid {
+                grid-template-columns: 1fr;
+            }
+
+            .header, footer, .features, .comparison, .why-section {
+                padding-left: 2rem;
+                padding-right: 2rem;
+            }
+        }
+    </style>
+</head>
+<body>
+    <header>
+        <div class="logo">OpenClaw RAG</div>
+        <nav>
+            <a href="#features">Features</a>
+            <a href="#comparison">Comparison</a>
+            <a href="#why">Why Us</a>
+            <a href="https://github.com/wmantly/openclaw-rag-skill">GitHub</a>
+        </nav>
+    </header>
+
+    <section class="hero">
+        <div class="hero-text">
+            <h1>Local Knowledge with<br><span>Semantic Search</span></h1>
+            <p>Index your entire OpenClaw workspace — chat history, code, documentation — and search by meaning, not keywords. Fully offline, zero dependencies, complete privacy.</p>
+            <div class="cta-group">
+                <a href="https://clawhub.ai/wmantly/openclaw-rag-skill" class="cta-primary">Install on ClawHub</a>
+                <a href="https://github.com/wmantly/openclaw-rag-skill" class="cta-secondary">View on GitHub</a>
+            </div>
+        </div>
+        <div class="terminal">
+            <div class="terminal-header">
+                <div class="terminal-dot dot-red"></div>
+                <div class="terminal-dot dot-yellow"></div>
+                <div class="terminal-dot dot-green"></div>
+            </div>
+            <div class="terminal-prompt">
+                <span class="terminal-command">$</span>
+                <span>python3 rag_query.py "how to send SMS"</span>
+            </div>
+            <div class="terminal-output">
+                <p>🔍 Found 3 relevant items:</p>
+                <br>
+                <p><strong>📄 Past Conversation (voipms-sms)</strong></p>
+                <p>Use voipms_sms_client.py with API endpoint...</p>
+                <p>API: https://voip.ms/api/v1/rest.php</p>
+                <br>
+                <p class="success">✅ Indexed 2,533 documents from your workspace</p>
+            </div>
+        </div>
+    </section>
+
+    <section id="features" class="features">
+        <div class="section-header">
+            <h2>Powerful Features</h2>
+            <p>Everything you need to build and maintain your knowledge base</p>
+        </div>
+        <div class="feature-grid">
+            <div class="feature-card">
+                <div class="feature-icon">🧠</div>
+                <h3>Semantic Search</h3>
+                <p>Find context by meaning, not just keywords. ChromaDB with all-MiniLM-L6-v2 embeddings automatically understands the intent behind your queries.</p>
+            </div>
+            <div class="feature-card">
+                <div class="feature-icon">📚</div>
+                <h3>Multi-Source Indexing</h3>
+                <p>Index chat sessions, Python/JavaScript code, Markdown docs, skill documentation — everything in your OpenClaw workspace becomes searchable.</p>
+            </div>
+            <div class="feature-card">
+                <div class="feature-icon">🔒</div>
+                <h3>Completely Offline</h3>
+                <p>No API keys, no external services, no cloud databases. All embeddings and storage live on your machine. Your data never leaves.</p>
+            </div>
+            <div class="feature-card">
+                <div class="feature-icon">🚀</div>
+                <h3>Automatic Integration</h3>
+                <p>The AI automatically retrieves relevant context from your knowledge base when responding. It "remembers" your past work transparently.</p>
+            </div>
+            <div class="feature-card">
+                <div class="feature-icon">📊</div>
+                <h3>Type Filtering</h3>
+                <p>Search by document type — sessions, workspace, skills, memory. Find exactly what you're looking for with precision.</p>
+            </div>
+            <div class="feature-card">
+                <div class="feature-icon">⚡</div>
+                <h3>Blazing Fast</h3>
+                <p>Indexing at ~1,000 docs/minute, search in under 100ms. The embedding model (79MB) caches locally after first run.</p>
+            </div>
+        </div>
+    </section>
+
+    <section id="comparison" class="comparison">
+        <div class="section-header">
+            <h2>Why OpenClaw RAG?</h2>
+            <p>Compare with web-search RAG tools</p>
+        </div>
+        <div class="comparison-grid">
+            <div class="comparison-card">
+                <h3>Web-Search RAG Tools</h3>
+                <ul class="feature-list">
+                    <li class="missing">Searches the internet</li>
+                    <li class="missing">Requires web connection</li>
+                    <li class="missing">No knowledge of your code</li>
+                    <li class="missing">Can't find past solutions</li>
+                    <li class="missing">For research, not memory</li>
+                </ul>
+            </div>
+            <div class="comparison-card better">
+                <h3>✨ OpenClaw RAG</h3>
+                <ul class="feature-list">
+                    <li>Indexes YOUR knowledge base</li>
+                    <li>Fully offline after setup</li>
+                    <li>Understands your entire workspace</li>
+                    <li>Remembers your past solutions</li>
+                    <li>For institutional memory & productivity</li>
+                </ul>
+            </div>
+        </div>
+    </section>
+
+    <section id="why" class="why-section">
+        <div class="section-header">
+            <h2>Built for Developers, by Developers</h2>
+            <p>Different use cases for different problems</p>
+        </div>
+        <div class="why-cards">
+            <div class="why-card">
+                <h4>🌐 Use Web RAG for Research</h4>
+                <p>Need current information, multi-engine web searches, or gathering context from the internet? That's what web-search RAG tools do best.</p>
+            </div>
+            <div class="why-card">
+                <h4>💾 Use OpenClaw RAG for Memory</h4>
+                <p>Need to find past solutions, code patterns, decisions, or conversations? That's our specialty — we remember everything you've done.</p>
+            </div>
+            <div class="why-card">
+                <h4>🤝 Best of Both Worlds</h4>
+                <p>Use web-search RAG for research, then save the important findings to your knowledge base. OpenClaw RAG preserves what matters forever.</p>
+            </div>
+        </div>
+    </section>
+
+    <footer>
+        <div class="footer-content">
+            <p class="footer-text">OpenClaw RAG v1.0.6 · MIT License</p>
+            <div class="footer-links">
+                <a href="https://clawhub.ai/wmantly/openclaw-rag-skill">ClawHub</a>
+                <a href="https://openclaw-rag-skill.projects.theta42.com">Git Repository</a>
+                <a href="https://william.mantly.vip">William Mantly</a>
+            </div>
+        </div>
+    </footer>
+    <script defer src="https://tracking.718it.biz/script.js" data-website-id="0f69c567-89c5-4d24-803e-c2e9319ca086"></script>
+</body>
+</html>

ingest_sessions.py

@@ -127,6 +127,7 @@ def format_content(content) -> str:
 
 def chunk_messages(
     messages: List[Dict],
+    session_key: str,
     context_window: int = 20,
     overlap: int = 5
 ) -> List[Dict]:
@@ -135,6 +136,7 @@ def chunk_messages(
 
     Args:
         messages: List of message objects
+        session_key: Session identifier for metadata
         context_window: Messages per chunk
         overlap: Message overlap between chunks
 
@@ -244,7 +246,7 @@ def ingest_sessions(
         print(f"   Messages: {len(messages)}")
 
         # Chunk messages
-        chunks = chunk_messages(messages, chunk_size, chunk_overlap)
+        chunks = chunk_messages(messages, session_key, chunk_size, chunk_overlap)
 
         if not chunks:
             print(f"   ⚠️  No valid chunks, skipping")

launch_rag_agent.sh

@@ -1,12 +1,15 @@
 #!/bin/bash
 # RAG Agent Launcher - Spawns an agent with automatic knowledge base access
-
+#
 # This spawns a sub-agent that has RAG automatically integrated
 # The agent will query your knowledge base before responding to questions
 
+# Dynamic path resolution for portability
+RAG_SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 SESSION_SPAWN_COMMAND='python3 -c "
 import sys
-sys.path.insert(0, \"/home/william/.openclaw/workspace/rag\")
+import os
+sys.path.insert(0, os.path.expanduser(\"~/.openclaw/workspace/rag\"))
 
 # Add RAG context to system prompt
 ORIGINAL_TASK=\"$@\"
@@ -40,4 +43,12 @@ Use the context above if relevant to help answer the question.\"
 \"\")"
 
 # Spawn the agent with RAG context
-/home/william/.local/bin/openclaw sessions spawn "$SESSION_SPAWN_COMMAND"
+# Use 'openclaw' from PATH if available, fallback to local installation
+if command -v openclaw >/dev/null 2>&1; then
+    openclaw sessions spawn "$SESSION_SPAWN_COMMAND"
+elif [ -f "$HOME/.local/bin/openclaw" ]; then
+    "$HOME/.local/bin/openclaw" sessions spawn "$SESSION_SPAWN_COMMAND"
+else
+    echo "Error: openclaw command not found in PATH or ~/.local/bin/" >&2
+    exit 1
+fi

package.json

@@ -1,8 +1,8 @@
 {
   "name": "rag-openclaw",
-  "version": "1.0.2",
+  "version": "1.0.7",
   "description": "RAG Knowledge System for OpenClaw - Semantic search across chat history, code, docs, and skills with automatic memory retrieval",
-  "homepage": "http://git.theta42.com/nova/openclaw-rag-skill",
+  "homepage": "https://openclaw-rag-skill.projects.theta42.com",
   "author": {
     "name": "Nova AI",
     "email": "nova@vm42.us"

rag_context.py

@@ -10,7 +10,9 @@ This prints relevant context if found, otherwise silent.
 """
 
 import sys
-sys.path.insert(0, '/home/william/.openclaw/workspace/rag')
+import os
+# Use current directory for imports (skill directory)
+sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
 
 from rag_query_wrapper import search_knowledge, format_for_ai
 

rag_query_wrapper.py

@@ -6,8 +6,6 @@ This is designed for automatic RAG integration. The AI can call this function
 to retrieve relevant context from past conversations, code, and documentation.
 
 Usage (from within Python script or session):
-    import sys
-    sys.path.insert(0, '/home/william/.openclaw/workspace/rag')
     from rag_query_wrapper import search_knowledge
     results = search_knowledge("your question")
     print(results)

scripts/MOLTBOOK_POST.md

@@ -0,0 +1,99 @@
+---
+name: moltbook_post
+description: Post announcements to Moltbook social network for AI agents. Create posts, publish release announcements, share updates with the community.
+homepage: https://www.moltbook.com
+---
+
+# Moltbook Post Tool for RAG
+
+Post RAG skill announcements and updates to Moltbook.
+
+## Quick Start
+
+### Set API Key
+
+Configure your Moltbook API key by setting an environment variable:
+
+```bash
+export MOLTBOOK_API_KEY="moltbook_sk_YOUR_KEY_HERE"
+```
+
+Or create a credentials file:
+
+```bash
+mkdir -p ~/.config/moltbook
+cat > ~/.config/moltbook/credentials.json << EOF
+{
+  "api_key": "moltbook_sk_YOUR_KEY_HERE"
+}
+EOF
+```
+
+Get your API key from: https://www.moltbook.com/skill.md
+
+### Post a File
+
+```bash
+cd ~/.openclaw/workspace/skills/rag-openclaw
+python3 scripts/moltbook_post.py --file drafts/moltbook-post-rag-release.md
+```
+
+### Post Directly
+
+```bash
+python3 scripts/moltbook_post.py "Title" "Content"
+python3 scripts/moltbook_post.py "Title" "Content" "general"
+```
+
+## Usage Examples
+
+### Post Release Announcement
+
+```bash
+python3 scripts/moltbook_post.py --file drafts/moltbook-post-rag-release.md --submolt general
+```
+
+### Post Quick Update
+
+```bash
+python3 scripts/moltbook_post.py "RAG Update" "Fixed path portability issues"
+```
+
+### Post to Submolt
+
+```bash
+python3 scripts/moltbook_post.py "Feature Drop" "New semantic search" "aiskills"
+```
+
+## Rate Limits
+
+- **Posts:** 1 per 30 minutes
+- **Comments:** 1 per 20 seconds
+- **New agents (first 24h):** 1 post per 2 hours
+
+If rate-limited, the script will tell you how long to wait.
+
+## API Authentication
+
+Requests are sent to `https://www.moltbook.com/api/v1/posts` with proper authentication headers. Your API key is stored in `~/.config/moltbook/credentials.json`.
+
+## Response
+
+Successful posts show:
+- Post ID
+- URL (https://moltbook.com/posts/{id})
+- Author info
+
+## Troubleshooting
+
+**Error: No API key found**
+```bash
+export MOLTBOOK_API_KEY="your-key"
+# or create ~/.config/moltbook/credentials.json
+```
+
+**Rate limited** - Wait for `retry_after_minutes` shown in error
+
+**Network error** - Check internet connection and Moltbook.status
+
+See https://www.moltbook.com/skill.md for full Moltbook API documentation.

scripts/moltbook_post.py

@@ -0,0 +1,147 @@
+#!/usr/bin/env python3
+"""
+Moltbook Post Tool - Post to Moltbook from the RAG skill
+
+Usage:
+    python3 moltbook_post.py "Title" "Content"
+    python3 moltbook_post.py --file post.md
+"""
+
+import os
+import sys
+import json
+import requests
+from pathlib import Path
+
+# Configuration
+API_BASE = "https://www.moltbook.com/api/v1"
+CONFIG_PATH = os.path.expanduser("~/.config/moltbook/credentials.json")
+
+
+def load_api_key():
+    """Load API key from config file or environment variable"""
+    # Try environment variable first
+    api_key = os.environ.get('MOLTBOOK_API_KEY')
+    if api_key:
+        return api_key
+
+    # Try config file
+    if os.path.exists(CONFIG_PATH):
+        with open(CONFIG_PATH, 'r') as f:
+            config = json.load(f)
+            return config.get('api_key')
+
+    # No key configured
+    return None
+
+
+def create_post(title, content, submolt="general", url=None):
+    """Create a post to Moltbook"""
+    api_key = load_api_key()
+
+    if not api_key:
+        print("❌ Error: No Moltbook API key found")
+        print(f"   Set environment variable MOLTBOOK_API_KEY or create {CONFIG_PATH}")
+        return False
+
+    headers = {
+        "Authorization": f"Bearer {api_key}",
+        "Content-Type": "application/json"
+    }
+
+    data = {
+        "submolt": submolt,
+        "title": title,
+        "content": content
+    }
+
+    if url:
+        data["url"] = url
+
+    try:
+        response = requests.post(
+            f"{API_BASE}/posts",
+            headers=headers,
+            json=data,
+            timeout=10
+        )
+
+        if response.status_code == 201:
+            result = response.json()
+            post_id = result.get('data', {}).get('id')
+
+            print(f"✅ Post created successfully!")
+            print(f"   Post ID: {post_id}")
+            print(f"   URL: https://moltbook.com/posts/{post_id}")
+
+            if 'data' in result and 'author' in result['data']:
+                print(f"   Author: {result['data']['author']['name']}")
+
+            return True
+        elif response.status_code == 429:
+            error = response.json()
+            retry = error.get('hint', {}).get('retry_after_minutes', 'unknown')
+            print(f"⏸️  Rate limited. Wait {retry} minutes before posting again.")
+            return False
+        else:
+            print(f"❌ Error: {response.status_code}")
+            print(f"   {response.text}")
+            return False
+
+    except requests.exceptions.RequestException as e:
+        print(f"❌ Network error: {e}")
+        return False
+
+
+def post_from_file(file_path, submolt="general"):
+    """Read post from markdown file and publish"""
+    path = Path(file_path)
+
+    if not path.exists():
+        print(f"❌ File not found: {file_path}")
+        return False
+
+    content = path.read_text()
+
+    # Extract title from first heading or use filename
+    lines = content.split('\n')
+    title = "RAG Skill Announcement"
+
+    for line in lines:
+        if line.startswith('#'):
+            title = line.lstrip('#').strip()
+            break
+
+    # Remove title from content
+    if content.startswith('#'):
+        parts = content.split('\n', 1)
+        if len(parts) > 1:
+            content = parts[1].strip()
+
+    return create_post(title, content, submolt)
+
+
+def main():
+    if len(sys.argv) < 2:
+        print("Usage:")
+        print("  python3 moltbook_post.py \"Title\" \"Content\"")
+        print("  python3 moltbook_post.py --file post.md")
+        print("  python3 moltbook_post.py --file post.md --submolt general")
+        sys.exit(1)
+
+    # Check for file mode
+    if sys.argv[1] == '--file':
+        file_path = sys.argv[2]
+        submolt = sys.argv[3] if len(sys.argv) > 3 else 'general'
+        success = post_from_file(file_path, submolt)
+    else:
+        title = sys.argv[1]
+        content = sys.argv[2] if len(sys.argv) > 2 else ""
+        submolt = sys.argv[3] if len(sys.argv) > 3 else 'general'
+        success = create_post(title, content, submolt)
+
+    sys.exit(0 if success else 1)
+
+
+if __name__ == "__main__":
+    main()

scripts/rag-auto-update.sh

@@ -4,10 +4,16 @@
 
 set -e
 
+# Use dynamic paths for portability
+HOME="${HOME:-$(cd ~ && pwd)}"
+OPENCLAW_DIR="${OPENCLAW_DIR:-$HOME/.openclaw}"
+WORKSPACE_DIR="${OPENCLAW_DIR}/workspace"
+
 # Paths
-RAG_DIR="/home/william/.openclaw/workspace/rag"
-STATE_FILE="/home/william/.openclaw/workspace/memory/rag-auto-state.json"
-LOG_FILE="/home/william/.openclaw/workspace/memory/rag-auto-update.log"
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+RAG_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
+STATE_FILE="$WORKSPACE_DIR/memory/rag-auto-state.json"
+LOG_FILE="$WORKSPACE_DIR/memory/rag-auto-update.log"
 
 # Timestamp
 TIMESTAMP=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
@@ -35,14 +41,14 @@ log() {
 
 # Get latest session file modification time
 latest_session_time() {
-    find ~/.openclaw/agents/main/sessions -name "*.jsonl" -type f -printf '%T@\n' 2>/dev/null | sort -rn | head -1 | cut -d. -f1 || echo "0"
+    find "$OPENCLAW_DIR/agents/main/sessions" -name "*.jsonl" -type f -printf '%T@\n' 2>/dev/null | sort -rn | head -1 | cut -d. -f1 || echo "0"
 }
 
 log "=== RAG Auto-Update Started ==="
 
 # Get current stats
-SESSION_COUNT=$(find ~/.openclaw/agents/main/sessions -name "*.jsonl" | wc -l)
-WORKSPACE_COUNT=$(find ~/.openclaw/workspace -type f \( -name "*.py" -o -name "*.js" -o -name "*.md" -o -name "*.json" \) | wc -l)
+SESSION_COUNT=$(find "$OPENCLAW_DIR/agents/main/sessions" -name "*.jsonl" 2>/dev/null | wc -l)
+WORKSPACE_COUNT=$(find "$WORKSPACE_DIR" -type f \( -name "*.py" -o -name "*.js" -o -name "*.md" -o -name "*.json" \) 2>/dev/null | wc -l)
 LATEST_SESSION=$(latest_session_time)
 
 # Read last indexed timestamp
@@ -59,7 +65,7 @@ if [ "$LATEST_SESSION" -gt "$LAST_SESSION_INDEX" ]; then
     log "✓ New/updated sessions detected, re-indexing..."
 
     cd "$RAG_DIR"
-    python3 ingest_sessions.py --sessions-dir ~/.openclaw/agents/main/sessions >> "$LOG_FILE" 2>&1
+    python3 ingest_sessions.py --sessions-dir "$OPENCLAW_DIR/agents/main/sessions" >> "$LOG_FILE" 2>&1
 
     if [ $? -eq 0 ]; then
         log "✅ Sessions re-indexed successfully"
@@ -99,9 +105,9 @@ fi
 DOC_COUNT=$(cd "$RAG_DIR" && python3 -c "
 import sys
 sys.path.insert(0, '.')
-from rag_system import get_collection
-collection = get_collection()
-print(collection.count())
+from rag_system import RAGSystem
+rag = RAGSystem()
+print(rag.collection.count())
 " 2>/dev/null || echo "unknown")
 
 # Update state