← Back to Quantum-Floor AI
MIT License - Free Forever

Connection-Core
Persistent Memory for AI

Our gift to the AI community. Give any AI the ability to remember.

<100KB Footprint
<50ms Retrieval
Any LLM Compatible
MIT License

Why Connection-Core?

Most AI assistants forget everything between sessions. We fixed that.

💾

SQLite-Based Storage

No external dependencies. Just a single file database that travels with your application. Simple, portable, reliable.

Lightning Fast Retrieval

Full-text search with FTS5. Retrieve relevant memories in under 50ms, even with thousands of entries.

📈

Importance Ranking

Not all memories are equal. Assign importance scores and let the system prioritize what matters most.

🏷

Tag Organization

Organize memories with tags. Filter and search by categories to find exactly what you need.

🕐

Natural Decay

Memories fade over time, just like human memory. Old, unused memories gracefully decay in importance.

🖥

Export & Import

Full JSON export and import. Backup, migrate, or share memory databases with ease.

Simple, Powerful API

Get started in 3 lines of code

💡 Quick Start
from connection_core import MemoryEngine

# Initialize
memory = MemoryEngine()

# Add memories
memory.add("User's name is Alice")
memory.add("User prefers dark mode", importance=0.8)

# Recall relevant memories
results = memory.recall("What is the user's name?")
print(results[0].content)  # "User's name is Alice"
💬 Chatbot Memory
from connection_core import MemoryEngine
from connection_core.memory_engine import ConversationMemory

engine = MemoryEngine()
conversation = ConversationMemory(engine)

# Store conversation turns
conversation.add_turn("user", "My name is Alice")
conversation.add_turn("assistant", "Nice to meet you!")

# Later session - recall history
history = conversation.get_recent(10)
💻 Coding Assistant
from connection_core.memory_engine import SemanticMemory

semantic = SemanticMemory(engine)

# Store project knowledge
semantic.add_concept("project.framework", "FastAPI")
semantic.add_concept("project.database", "PostgreSQL")
semantic.add_concept("project.style", "PEP8 compliant")

# Retrieve context
framework = semantic.get_concept("project.framework")
📚 Research Helper
# Store findings with tags
engine.add(
    "Finding: X improves Y by 50%",
    importance=0.9,
    tags=["research", "results"],
    metadata={"paper": "arxiv:2024.12345"}
)

# Recall by topic
findings = engine.recall(
    "research findings about X",
    tags=["research"]
)

Built For Every Use Case

From chatbots to enterprise applications

Chatbots That Remember

Build chatbots that truly know their users. Remember names, preferences, past conversations, and context across sessions.

  • Remember user names and preferences
  • Track conversation history
  • Personalize responses over time
  • Maintain context across sessions
💬 Chatbot Example
# Remember user context
memory.add(f"User {name} joined")
memory.add(f"User asked about: {topic}")

# Personalize response
context = memory.recall(user_message)
response = llm.generate(
    prompt=user_message,
    context=context
)

Intelligent Assistants

Create AI assistants that learn your workflow, remember your projects, and provide contextual help based on your history.

  • Learn coding patterns and preferences
  • Remember project structures
  • Track todo items and tasks
  • Provide contextual suggestions
💻 Assistant Example
# Store project context
memory.add("Project uses TypeScript")
memory.add("Prefer functional components")
memory.add("Use Tailwind for styling")

# Generate contextual code
prefs = memory.recall("coding preferences")
code = generate_with_context(prefs)

Research & Knowledge Tools

Build tools that accumulate knowledge, track findings, and surface relevant information when you need it.

  • Store and retrieve research findings
  • Tag and categorize knowledge
  • Surface relevant prior work
  • Build institutional memory
📚 Research Example
# Store research findings
memory.add(
    "Paper X shows 40% improvement",
    tags=["ml", "performance"],
    importance=0.9
)

# Find related work
related = memory.recall(
    "performance improvements",
    tags=["ml"]
)

Games & NPC Memory

Create NPCs that remember player interactions, build relationships, and respond based on shared history.

  • NPCs remember player actions
  • Build relationship systems
  • Track quest progress
  • Dynamic story adaptation
🎮 Game NPC Example
# NPC remembers player
npc_memory.add(
    f"Player helped defeat dragon",
    tags=["quest", "heroic"],
    importance=0.95
)

# Generate contextual dialogue
history = npc_memory.recall("player")
dialogue = generate_npc_response(history)

Complete API Reference

Everything you need to build with Connection-Core

add(content, ...)

Add a new memory to the engine

memory.add("fact", importance=0.8, tags=["tag1"])

recall(query, ...)

Retrieve relevant memories

results = memory.recall("search term", limit=5)

get(id)

Get a specific memory by ID

mem = memory.get("abc123")

update(id, ...)

Update an existing memory

memory.update(id, content="new content")

delete(id)

Remove a memory

memory.delete("abc123")

get_stats()

Get engine statistics

stats = memory.get_stats()

export(path)

Export all memories to JSON

memory.export("backup.json")

decay_importance()

Apply natural memory decay

updated = memory.decay_importance()

Built for Performance

Lightweight yet powerful

Operation Latency
OperationLatency
Add Memory2ms
Recall (search)15ms
Get by ID1ms
Update2ms
Delete1ms
Storage Efficiency
Memory CountDB Size
1,000 memories95KB
10,000 memories850KB
100,000 memories8.2MB
1,000,000 memories~80MB

Try It Live

Experience Connection-Core in your browser

User's name is Alice 0.85
Prefers dark mode interface 0.70
Python developer, 5 years experience 0.65
Working on machine learning project 0.60
4
Memories
12KB
DB Size
<15ms
Recall Time

Start Building with Memory

One command. Infinite possibilities.

pip install connection-core