RichmondAlake/memorizz

MemoRizz: A Python library serving as a memory layer for AI applications. Leverages popular databases and storage solutions to optimize memory usage. Provides utility classes and methods for efficient data management.

53
/ 100
Established

Implements five distinct memory subsystems (episodic, semantic, procedural, short-term, shared) with pluggable backends including Oracle, MongoDB, and local FAISS, enabling persistent cross-session context and semantic retrieval via embeddings. Provides preset application modes (`assistant`, `workflow`, `deep_research`) that auto-configure memory stacks, plus optional integrations for internet search (Tavily), sandboxed code execution (E2B/Daytona), and scheduled automations with delivery hooks. Built on a builder pattern with automatic tool registration and multi-agent orchestration via shared blackboard memory.

692 stars. Actively maintained with 1 commit in the last 30 days.

No Package No Dependents
Maintenance 16 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 18 / 25

How are scores calculated?

Stars

692

Forks

76

Language

Python

License

Last pushed

Mar 10, 2026

Commits (30d)

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/RichmondAlake/memorizz"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.