Auto backup: 2026-02-17 18:00

2026-02-17 18:00:21 +00:00
parent 8902a93add
commit ebd2f70af7
9 changed files with 768 additions and 3 deletions
--- a/automations/ai-newsletter-digest/README.md
+++ b/automations/ai-newsletter-digest/README.md
@@ -0,0 +1,58 @@
+# AI Newsletter Digest Automation
+
+Automatically consolidates AI-related newsletters into a single, deduplicated daily digest.
+
+## Schedule
+- **When:** Daily at 7:30 AM (Australia/Perth timezone)
+- **Delivery:** Via Telegram
+
+## What It Does
+1. Scans unread emails from the last 24 hours
+2. Identifies AI-related newsletters
+3. **Excludes:** Notion, Platformer, WSJ, WIRED Daily (per Anthony's request)
+4. Fetches full content from remaining newsletters
+5. Uses LLM to analyze and create consolidated digest:
+   - Top AI News (deduplicated across sources)
+   - Product Launches
+   - Research Highlights
+   - Industry Trends
+   - Notable Quotes
+
+## Files
+- `daily-digest.sh` - Main script that fetches newsletters
+- `digest.py` - Python analysis tool (alternative approach)
+- `list-newsletters.py` - Quick check of what newsletters are in inbox
+
+## Manual Run
+```bash
+cd /home/openclaw/.openclaw/workspace/automations/ai-newsletter-digest
+./daily-digest.sh
+```
+
+This outputs a file path. You can then ask me to analyze it.
+
+## Cron Job
+- **Job ID:** `faaed154-8320-468f-a597-21b6a92eed39`
+- **Check status:** `openclaw cron list`
+- **Disable:** `openclaw cron remove <job-id>`
+
+## Newsletter Sources Included
+- AI Valley
+- The Information (Applied AI)
+- Wall Street Journal (AI coverage)
+- The Deep View
+- WIRED Daily
+- And other AI-related emails
+
+## How to Modify
+
+**Change the schedule:**
+```bash
+openclaw cron update <job-id> --schedule "0 8 * * *"  # 8am instead
+```
+
+**Add more exclusions:**
+Edit `daily-digest.sh` and add more `grep -v "pattern"` lines
+
+**Change lookback period:**
+Edit the `--recent 24h` parameter in `daily-digest.sh`
--- a/automations/ai-newsletter-digest/analyze.sh
+++ b/automations/ai-newsletter-digest/analyze.sh
@@ -0,0 +1,47 @@
+#!/bin/bash
+# AI Newsletter Digest - Fetch and analyze
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+EMAIL_SKILL="$SCRIPT_DIR/../../skills/imap-smtp-email"
+
+echo "🤖 AI Newsletter Digest Generator" >&2
+echo "============================================================" >&2
+
+# Fetch AI-related emails from last 7 days
+echo "📧 Fetching AI newsletters from last 7 days..." >&2
+
+python3 "$EMAIL_SKILL/scripts/imap-py.py" search \
+  --subject "AI" \
+  --recent 7d \
+  --limit 20 > /tmp/ai_emails_list.txt
+
+# Count how many we found
+EMAIL_COUNT=$(grep -c "^●" /tmp/ai_emails_list.txt || echo "0")
+echo "🎯 Found $EMAIL_COUNT AI-related emails" >&2
+
+if [ "$EMAIL_COUNT" = "0" ]; then
+  echo "No AI newsletters found in the last 7 days."
+  exit 0
+fi
+
+# Extract UIDs
+UIDS=$(grep "UID:" /tmp/ai_emails_list.txt | awk '{print $3}' | head -10)
+
+echo "📖 Fetching content from top 10 newsletters..." >&2
+echo "" > /tmp/ai_newsletters_content.txt
+
+for uid in $UIDS; do
+  echo "  • Fetching email $uid..." >&2
+  python3 "$EMAIL_SKILL/scripts/imap-py.py" fetch "$uid" >> /tmp/ai_newsletters_content.txt 2>/dev/null || true
+  echo -e "\n\n========================================\n\n" >> /tmp/ai_newsletters_content.txt
+done
+
+echo "✅ Content fetched!" >&2
+echo "" >&2
+echo "📋 Newsletter sources:" >&2
+grep "^From:" /tmp/ai_newsletters_content.txt | sort -u | head -10 >&2
+echo "" >&2
+
+# Output the file path for the agent to analyze
+echo "/tmp/ai_newsletters_content.txt"
--- a/automations/ai-newsletter-digest/daily-digest.sh
+++ b/automations/ai-newsletter-digest/daily-digest.sh
@@ -0,0 +1,38 @@
+#!/bin/bash
+# Daily AI Newsletter Digest - Fast Reliable Version
+set -e
+
+EMAIL_SKILL="/home/openclaw/.openclaw/workspace/skills/imap-smtp-email"
+OUTPUT_FILE="/tmp/ai-newsletter-emails.json"
+
+echo "🤖 Daily AI Newsletter Digest" >&2
+echo "============================================================" >&2
+echo "$(date)" >&2
+echo "" >&2
+
+echo "🔍 Searching for AI newsletters from last 48 hours..." >&2
+
+# Single search for all recent emails, then filter locally
+cd "$EMAIL_SKILL"
+
+# Get recent emails and filter for AI newsletters (expanded to 48h and more sources)
+ALL_EMAILS=$(node scripts/imap.js search --recent 48h --limit 100 2>/dev/null | jq '[.[] | select(.from | test("AI Valley|AI Secret|DeepView|Deep View|The Rundown|TLDR|Benedict|aivalley|aisecret|deepview|therundown|tldr|benedict"; "i"))]' 2>/dev/null || echo "[]")
+
+# Save results
+echo "$ALL_EMAILS" > "$OUTPUT_FILE"
+
+EMAIL_COUNT=$(echo "$ALL_EMAILS" | jq '. | length')
+echo "" >&2
+echo "🎯 Found $EMAIL_COUNT AI-related emails" >&2
+
+if [ "$EMAIL_COUNT" -eq 0 ]; then
+  echo "No new AI newsletters in the last 24 hours." >&2
+  echo "[]"
+  exit 0
+fi
+
+echo "" >&2
+echo "📧 Ready to process $EMAIL_COUNT newsletters" >&2
+
+# Output the emails
+cat "$OUTPUT_FILE"
--- a/automations/ai-newsletter-digest/digest.py
+++ b/automations/ai-newsletter-digest/digest.py
@@ -0,0 +1,206 @@
+#!/usr/bin/env python3
+"""
+AI Newsletter Digest
+Consolidates AI-related newsletters into a single, deduplicated summary
+"""
+import sys
+import os
+import json
+import subprocess
+from pathlib import Path
+from datetime import datetime
+import re
+
+# Add skills to path
+WORKSPACE = Path(__file__).parent.parent.parent
+EMAIL_SKILL = WORKSPACE / "skills" / "imap-smtp-email"
+
+# Newsletter keywords to look for in sender/subject
+AI_KEYWORDS = [
+    'ai', 'artificial intelligence', 'machine learning', 'ml', 'llm',
+    'gpt', 'claude', 'openai', 'anthropic', 'deepmind', 'neural',
+    'chatgpt', 'transformer', 'diffusion', 'generative', 'newsletter'
+]
+
+def log(msg):
+    """Log to stderr"""
+    print(msg, file=sys.stderr)
+
+def is_ai_newsletter(from_addr, subject):
+    """Check if email is likely an AI newsletter"""
+    text = f"{from_addr} {subject}".lower()
+    return any(keyword in text for keyword in AI_KEYWORDS)
+
+def fetch_unread_emails(limit=50):
+    """Fetch unread emails using the IMAP skill"""
+    log("📧 Fetching unread emails...")
+    
+    cmd = [
+        "python3",
+        str(EMAIL_SKILL / "scripts" / "imap-py.py"),
+        "search",
+        "--unseen",
+        "--limit", str(limit)
+    ]
+    
+    result = subprocess.run(cmd, capture_output=True, text=True)
+    
+    if result.returncode != 0:
+        log(f"Error fetching emails: {result.stderr}")
+        return []
+    
+    # Parse the output
+    emails = []
+    lines = result.stdout.strip().split('\n')
+    
+    current_email = {}
+    for line in lines:
+        line = line.strip()
+        
+        if line.startswith('●') or line.startswith(' '):
+            # Start of new email
+            if 'UID:' in line:
+                if current_email:
+                    emails.append(current_email)
+                uid = line.split('UID:')[1].strip().split()[0]
+                current_email = {'uid': uid}
+        elif line.startswith('From:'):
+            current_email['from'] = line.replace('From:', '').strip()
+        elif line.startswith('Subject:'):
+            current_email['subject'] = line.replace('Subject:', '').strip()
+        elif line.startswith('Date:'):
+            current_email['date'] = line.replace('Date:', '').strip()
+    
+    if current_email:
+        emails.append(current_email)
+    
+    return emails
+
+def fetch_email_body(uid):
+    """Fetch full email body"""
+    log(f"  Fetching email {uid}...")
+    
+    cmd = [
+        "python3",
+        str(EMAIL_SKILL / "scripts" / "imap-py.py"),
+        "fetch",
+        uid
+    ]
+    
+    result = subprocess.run(cmd, capture_output=True, text=True)
+    
+    if result.returncode != 0:
+        return None
+    
+    # Extract body (everything after the separator line)
+    parts = result.stdout.split('-' * 80)
+    if len(parts) > 1:
+        return parts[1].strip()
+    
+    return result.stdout.strip()
+
+def extract_key_points(newsletters):
+    """Use LLM to extract and deduplicate key points"""
+    log("🧠 Analyzing newsletters and extracting key points...")
+    
+    # Prepare newsletter content for analysis
+    newsletter_texts = []
+    for i, newsletter in enumerate(newsletters, 1):
+        text = f"NEWSLETTER {i} - {newsletter['from']}\nSubject: {newsletter['subject']}\n\n{newsletter['body'][:3000]}"
+        newsletter_texts.append(text)
+    
+    combined = "\n\n" + "="*80 + "\n\n".join(newsletter_texts)
+    
+    # Prompt for LLM
+    prompt = f"""You are analyzing {len(newsletters)} AI-related newsletters. Extract the key information and insights, removing duplicates and synthesizing similar news across sources.
+
+{combined}
+
+Please provide:
+1. **Top AI News** - The most important developments mentioned (deduplicated)
+2. **Product Launches** - New tools, models, or features announced
+3. **Research Highlights** - Notable papers or breakthroughs
+4. **Industry Trends** - Patterns or themes across multiple newsletters
+5. **Notable Quotes** - Interesting perspectives from thought leaders
+
+Format as markdown with clear sections. Be concise but informative. If the same news appears in multiple newsletters, mention it once and note it's widely covered."""
+    
+    # Call LLM via openclaw (assuming this is running within openclaw context)
+    # For now, create a temporary prompt file
+    prompt_file = Path("/tmp/digest_prompt.txt")
+    prompt_file.write_text(prompt)
+    
+    log("  Generating digest with LLM...")
+    log("  (This may take a moment...)")
+    
+    # Return a placeholder for now - in production this would call the LLM
+    # The agent running this will provide LLM access
+    return {
+        'prompt': prompt,
+        'needs_llm': True
+    }
+
+def create_digest(newsletters):
+    """Create the final digest"""
+    if not newsletters:
+        return "No AI newsletters found in unread emails."
+    
+    # For now, return structured data that the agent can analyze
+    digest = {
+        'count': len(newsletters),
+        'sources': [n['from'] for n in newsletters],
+        'newsletters': newsletters
+    }
+    
+    return digest
+
+def main():
+    log("🤖 AI Newsletter Digest Generator")
+    log("=" * 60)
+    
+    # Fetch unread emails
+    emails = fetch_unread_emails(limit=50)
+    
+    # Filter for AI newsletters
+    log(f"📊 Found {len(emails)} unread emails")
+    ai_newsletters = []
+    
+    for email in emails:
+        if is_ai_newsletter(email.get('from', ''), email.get('subject', '')):
+            ai_newsletters.append(email)
+    
+    log(f"🎯 Found {len(ai_newsletters)} AI-related newsletters")
+    
+    if not ai_newsletters:
+        print(json.dumps({'status': 'no_newsletters', 'message': 'No AI newsletters found'}))
+        return
+    
+    # Fetch full content for each
+    log("📖 Fetching full newsletter content...")
+    for newsletter in ai_newsletters[:10]:  # Limit to 10 to avoid overwhelming
+        body = fetch_email_body(newsletter['uid'])
+        if body:
+            newsletter['body'] = body
+    
+    # Filter out ones without body
+    ai_newsletters = [n for n in ai_newsletters if 'body' in n]
+    
+    log(f"✅ Successfully fetched {len(ai_newsletters)} newsletters")
+    
+    # Output structured data for the agent to analyze
+    result = {
+        'status': 'success',
+        'count': len(ai_newsletters),
+        'sources': list(set([n['from'] for n in ai_newsletters])),
+        'newsletters': ai_newsletters[:10]  # Limit to 10
+    }
+    
+    print(json.dumps(result, indent=2))
+    
+    # Log summary to stderr
+    log("\n📋 Newsletter Sources:")
+    for source in result['sources']:
+        log(f"  • {source}")
+
+if __name__ == '__main__':
+    main()
--- a/automations/ai-newsletter-digest/list-newsletters.py
+++ b/automations/ai-newsletter-digest/list-newsletters.py
@@ -0,0 +1,71 @@
+#!/usr/bin/env python3
+"""
+Quick list of AI newsletters in inbox
+"""
+import sys
+import subprocess
+from pathlib import Path
+
+WORKSPACE = Path(__file__).parent.parent.parent
+EMAIL_SKILL = WORKSPACE / "skills" / "imap-smtp-email"
+
+AI_KEYWORDS = [
+    'ai', 'artificial intelligence', 'machine learning', 'ml', 'llm',
+    'gpt', 'claude', 'openai', 'anthropic', 'deepmind', 'neural',
+    'chatgpt', 'transformer', 'diffusion', 'generative', 'newsletter'
+]
+
+def is_ai_newsletter(from_addr, subject):
+    text = f"{from_addr} {subject}".lower()
+    return any(keyword in text for keyword in AI_KEYWORDS)
+
+def main():
+    # Fetch unread emails
+    cmd = [
+        "python3",
+        str(EMAIL_SKILL / "scripts" / "imap-py.py"),
+        "search",
+        "--unseen",
+        "--limit", "50"
+    ]
+    
+    result = subprocess.run(cmd, capture_output=True, text=True)
+    
+    if result.returncode != 0:
+        print("Error fetching emails", file=sys.stderr)
+        sys.exit(1)
+    
+    # Parse output
+    emails = []
+    lines = result.stdout.strip().split('\n')
+    
+    current_email = {}
+    for line in lines:
+        line = line.strip()
+        
+        if 'UID:' in line:
+            if current_email:
+                emails.append(current_email)
+            uid = line.split('UID:')[1].strip().split()[0]
+            current_email = {'uid': uid}
+        elif line.startswith('From:'):
+            current_email['from'] = line.replace('From:', '').strip()
+        elif line.startswith('Subject:'):
+            current_email['subject'] = line.replace('Subject:', '').strip()
+    
+    if current_email:
+        emails.append(current_email)
+    
+    # Filter AI newsletters
+    ai_newsletters = [e for e in emails if is_ai_newsletter(e.get('from', ''), e.get('subject', ''))]
+    
+    print(f"Found {len(ai_newsletters)} AI newsletters out of {len(emails)} unread emails:\n")
+    
+    for n in ai_newsletters:
+        print(f"UID: {n['uid']}")
+        print(f"From: {n.get('from', 'Unknown')}")
+        print(f"Subject: {n.get('subject', 'No subject')}")
+        print()
+
+if __name__ == '__main__':
+    main()