railtech-mme 0.0.1

Railtech MME — Python SDK (placeholder; full release coming soon at https://github.com/gokulJinu01/railtech-mme-python).

railtech-mme

Placeholder release. Full SDK lands as v0.1.0. Watch the repo: https://github.com/gokulJinu01/railtech-mme-python

railtech-mme is the official Python SDK for MME (Modular Memory Engine) — tag-graph memory for LLMs by Rail Tech.

What MME does

MME does not use vector embeddings. It uses a bounded tag-graph that learns from pack accept/reject events:

1. Extract seed tags from the prompt
2. Spread activation across the tag graph (bounded depth, beam width, decay)
3. Score memories (activation + recency + importance + status − diversity penalty)
4. Pack into a hard token budget greedily

Every pack respects the budget exactly. Every retrieval is explainable.

Coming in v0.1.0

from railtech_mme import MME

mme = MME(api_key="mme_live_...")
mme.save("I prefer dark chocolate over milk.")
pack = mme.inject("What do I like to eat?")
for item in pack.items:
    print(item.title, item.excerpt, item.score.total)
mme.feedback(pack_id=pack.pack_id, accepted=True)

Plus async (AsyncMME) and LangChain integration (pip install "railtech-mme[langchain]").

Get an API key

https://mme.railtech.io → API Key

License

Apache-2.0