lore-context-middleware 0.1.0

SDK middleware for Lore Context — auto-inject memory pre-LLM-call and auto-retain post-LLM-call across OpenAI/Anthropic SDKs.

lore-context-middleware

Python SDK middleware for Lore Context — wraps openai.OpenAI / anthropic.Anthropic clients to auto-inject memory pre-LLM-call and auto-retain post-LLM-call without requiring the AI to call an MCP tool.

Install

pip install lore-context-middleware lore-context openai

Quick start

import os
from openai import OpenAI
from lore_context import LoreContextApiClient
from lore_context_middleware import with_memory_hooks

lore = LoreContextApiClient(token=os.environ["LORE_API_KEY"])
openai_client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

client = with_memory_hooks(openai_client, lore, mode="hybrid")

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "What was that Postgres dump command?"}],
)

Modes

Mode	inject	retain	tools exposed
hybrid (default)	✅	✅	✅
context	✅	✅	❌
tools	❌	❌	✅

See docs/sdk/middleware-modes.md in the lore-cloud repo for full mode semantics.

License

MIT