Infinite Memory for AI.
Locally.

A local-first vector memory engine for Python. No API keys. No cloud bills. Just high-performance, offline RAG for your LLM agents.

Read The Docs

bash — 80x24

█

System Capabilities

⚡

O(1) Semantic Cache

Why search vectors twice? MemLoop hashes queries to intercept repeated questions instantly. Improves latency by 99% for recurring topics.

🔒

100% Offline

Your data never leaves localhost. We use ChromaDB and lightweight SentenceTransformers that run on your CPU. Perfect for sensitive contracts, medical data, or PII.

📂

Universal Ingestion

Point to a folder of .pdf, .csv, or .txt files. MemLoop handles the ETL pipeline automatically.

🔖

Page-Level Citations

Hallucination killer. Every retrieval comes with source metadata: {source: "manual.pdf", page: 42}.

Developer documentation

Install and run your first agent in under 30 seconds.

# 1. Install via pip
pip install memloop

# 2. Create a python script
from memloop import MemLoop

brain = MemLoop()
print("Ingesting Knowledge...")

# Learn from the web
brain.learn_url("https://docs.python.org/3/")

# Ask a question
answer = brain.recall("How do decorators work?")
print(answer)
                        

The main interface for integrating with LLMs.

class MemLoop:
    def __init__(self, db_path="./memloop_data"):
        """Initialize local vector store"""
        pass

    def learn_local(self, folder_path):
        """Ingest PDFs, CSVs, and TXT files recursively"""
        pass

    def recall(self, query, n_results=3):
        """Returns context string with citations"""
        pass
                        

Use the terminal for quick testing and data management.

$ memloop [SYSTEM]: Initializing Neural Link... > /learn https://en.wikipedia.org/wiki/Artificial_intelligence [SYSTEM]: Absorbed 45 chunks. > What is the history of AI? [MEMLOOP]: "AI history began in antiquity..." (Source: Wikipedia)

Infinite Memory for AI. Locally.

Data Flow Architecture