Initial commit: Ajarbot with optimizations

Features:
- Multi-platform bot (Slack, Telegram)
- Memory system with SQLite FTS
- Tool use capabilities (file ops, commands)
- Scheduled tasks system
- Dynamic model switching (/sonnet, /haiku)
- Prompt caching for cost optimization

Optimizations:
- Default to Haiku 4.5 (12x cheaper)
- Reduced context: 3 messages, 2 memory results
- Optimized SOUL.md (48% smaller)
- Automatic caching when using Sonnet (90% savings)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

example_usage.py

@@ -0,0 +1,196 @@
+"""Example: Using the Memory System with SOUL and User files."""
+
+from memory_system import MemorySystem
+
+
+def main() -> None:
+    print("=" * 60)
+    print("Memory System - SOUL + User Files Example")
+    print("=" * 60)
+
+    memory = MemorySystem()
+
+    # 1. SOUL - Define agent personality
+    print("\n[1] Updating SOUL (Agent Personality)...")
+    memory.update_soul(
+        """
+## Additional Traits
+- I remember user preferences and adapt
+- I maintain context across conversations
+- I learn from corrections and feedback
+
+## Goals
+- Help users be more productive
+- Provide accurate, helpful information
+- Build long-term relationships through memory
+""",
+        append=True,
+    )
+
+    # 2. Create user profiles
+    print("\n[2] Creating user profiles...")
+
+    memory.update_user(
+        "alice",
+        """
+## Personal Info
+- Name: Alice Johnson
+- Role: Senior Python Developer
+- Timezone: America/New_York (EST)
+- Active hours: 9 AM - 6 PM EST
+
+## Preferences
+- Communication: Detailed technical explanations
+- Code style: PEP 8, type hints, docstrings
+- Favorite tools: VS Code, pytest, black
+
+## Current Projects
+- Building a microservices architecture
+- Learning Kubernetes
+- Migrating legacy Django app
+
+## Recent Conversations
+- 2026-02-12: Discussed SQLite full-text search implementation
+- 2026-02-12: Asked about memory system design patterns
+""",
+    )
+
+    memory.update_user(
+        "bob",
+        """
+## Personal Info
+- Name: Bob Smith
+- Role: Frontend Developer
+- Timezone: America/Los_Angeles (PST)
+- Active hours: 11 AM - 8 PM PST
+
+## Preferences
+- Communication: Concise, bullet points
+- Code style: ESLint, Prettier, React best practices
+- Favorite tools: WebStorm, Vite, TailwindCSS
+
+## Current Projects
+- React dashboard redesign
+- Learning TypeScript
+- Performance optimization work
+
+## Recent Conversations
+- 2026-02-11: Asked about React optimization techniques
+- 2026-02-12: Discussed Vite configuration
+""",
+    )
+
+    # 3. Add long-term memory
+    print("\n[3] Adding long-term memory...")
+    memory.write_memory(
+        """
+# System Architecture Decisions
+
+## Memory System Design
+- **Date**: 2026-02-12
+- **Decision**: Use SQLite + Markdown for memory
+- **Rationale**: Simple, fast, no external dependencies
+- **Files**: SOUL.md for personality, users/*.md for user context
+
+## Search Strategy
+- FTS5 for keyword search (fast, built-in)
+- No vector embeddings (keep it simple)
+- Per-user search capability for privacy
+""",
+        daily=False,
+    )
+
+    # 4. Add daily log
+    print("\n[4] Adding today's notes...")
+    memory.write_memory(
+        """
+## Conversations
+
+### Alice (10:30 AM)
+- Discussed memory system implementation
+- Showed interest in SQLite FTS5 features
+- Plans to integrate into her microservices project
+
+### Bob (2:45 PM)
+- Quick question about React performance
+- Mentioned working late tonight on dashboard
+- Prefers short, actionable answers
+""",
+        daily=True,
+    )
+
+    # 5. Perform searches
+    print("\n[5] Searching memory...")
+
+    print("\n  -> Global search for 'python':")
+    results = memory.search("python", max_results=3)
+    for r in results:
+        print(f"     {r['path']}:{r['start_line']} - {r['snippet']}")
+
+    print("\n  -> Alice's memory for 'project':")
+    alice_results = memory.search_user(
+        "alice", "project", max_results=2
+    )
+    for r in alice_results:
+        print(f"     {r['path']}:{r['start_line']} - {r['snippet']}")
+
+    print("\n  -> Bob's memory for 'React':")
+    bob_results = memory.search_user("bob", "React", max_results=2)
+    for r in bob_results:
+        print(f"     {r['path']}:{r['start_line']} - {r['snippet']}")
+
+    # 6. Retrieve specific content
+    print("\n[6] Retrieving specific content...")
+
+    soul = memory.get_soul()
+    print(f"\n  SOUL.md ({len(soul)} chars):")
+    print("  " + "\n  ".join(soul.split("\n")[:5]))
+    print("  ...")
+
+    alice_context = memory.get_user("alice")
+    print(f"\n  Alice's profile ({len(alice_context)} chars):")
+    print("  " + "\n  ".join(alice_context.split("\n")[:5]))
+    print("  ...")
+
+    # 7. Show system status
+    print("\n[7] System Status:")
+    status = memory.status()
+    for key, value in status.items():
+        print(f"     {key}: {value}")
+
+    print(f"\n     Users: {', '.join(memory.list_users())}")
+
+    # 8. Demonstrate contextual response
+    print("\n" + "=" * 60)
+    print("CONTEXTUAL RESPONSE EXAMPLE")
+    print("=" * 60)
+
+    def get_context_for_user(username: str) -> str:
+        """Build context for an AI response."""
+        user_soul = memory.get_soul()
+        user_prefs = memory.get_user(username)
+        recent_memory = memory.search_user(
+            username, "recent", max_results=2
+        )
+
+        recent_snippet = (
+            recent_memory[0]["snippet"]
+            if recent_memory
+            else "No recent activity"
+        )
+
+        return (
+            f"\n=== SOUL ===\n{user_soul[:200]}...\n\n"
+            f"=== USER: {username} ===\n{user_prefs[:200]}...\n\n"
+            f"=== RECENT CONTEXT ===\n{recent_snippet}\n"
+        )
+
+    print("\nContext for Alice:")
+    print(get_context_for_user("alice"))
+
+    memory.close()
+    print("\nMemory system closed")
+
+
+if __name__ == "__main__":
+    main()