memryapi 1.0.0

Official Python SDK for MemryAPI — Memory-as-a-Service for AI Applications.

MemryAPI Python SDK

The Sovereign Persistence Layer for AI Agents.

Installation

pip install memryapi

Quick Start

from memryapi import MemryAPI

client = MemryAPI("your-api-key")

# Store a memory
client.remember("user-123", "Prefers dark chocolate over milk chocolate")

# Recall memories by semantic similarity
result = client.recall("user-123", "What chocolate do they like?")
print(result.results[0].content)
# → "Prefers dark chocolate over milk chocolate"

Session Helper

Avoid repeating user_id on every call:

session = client.session("user-123")

session.remember("Has a golden retriever named Max")
session.remember("Works remotely from Austin, TX")

memories = session.recall("pets")
summary = session.summarize()

LLM Wrapper (Experimental)

Automatically inject memory context into your LLM calls:

from openai import OpenAI

openai = OpenAI()

def ask(context: str) -> str:
    response = openai.chat.completions.create(
        model="gpt-4",
        messages=[
            {"role": "system", "content": f"User context:\n{context}"},
            {"role": "user", "content": "What should I get them for their birthday?"},
        ],
    )
    return response.choices[0].message.content

# Recalls memories, passes as context, saves the AI response
answer = client.wrap("user-123", ask, query="preferences interests")

Context Manager

with MemryAPI("your-api-key") as client:
    client.remember("user-123", "Some fact")
    result = client.recall("user-123", "query")
# HTTP client is automatically closed

API Reference

Method	Description
remember(user_id, text, metadata)	Store a memory
recall(user_id, query, top_k, threshold, time_weight)	Semantic recall
forget(memory_id)	Delete a specific memory
forget_all(user_id)	Delete all user memories
summarize(user_id, limit, save_as_memory)	AI-powered summary
session(user_id)	Session-scoped client
wrap(user_id, fn, query)	Auto memory-augmented LLM calls

License

MIT