memorizz

MemoRizz: A Python library serving as a memory layer for AI applications. Leverages popular databases and storage solutions to optimize memory usage. Provides u

What is 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.

Overview of memorizz

What it is

MemoRizz is a Python framework that connects persistent memory, models, prompts, and reasoning so agents can recall what matters, reuse experience, and make better decisions across sessions. It serves as a memory layer for AI applications, leveraging popular databases and storage solutions to optimize memory usage.

Key features

  • Memory management with five types: episodic, semantic, procedural, short-term, and shared memory.
  • Persist and isolate memory by agent, user, and conversation; supports local filesystem, MongoDB, Oracle, and Notion with separate vector storage.
  • Ingest and retrieve: turn files and folders into a knowledge base with configurable chunking, embeddings, and semantic or hybrid search.
  • Agent framework with MemAgent and MemAgentBuilder supporting assistant, workflow, and deep_research modes.
  • MetaHarness runs tasks through Codex, Claude Code, OpenHands, DeepSeek, pi, Hermes, or native MemAgent workers, with memory scope and learning evidence across harnesses.
  • Plugin for Codex and Claude Code, sharing memory locally or via a hosted MCP server.
  • Continual learning loop that captures tool workflows, distills successful procedures into reusable skills, and fine-tunes small models (embedding and decision models) on user memories.

Use cases

  • Building persistent AI agents that retain and recall context across sessions.
  • Creating knowledge bases from files and folders for semantic or hybrid search.
  • Delegating work to specialist agents and coordinating multi-agent workflows.
  • Using MemoRizz as a plugin for Codex and Claude Code to provide project memory and session history.
  • Running tasks on external harnesses (Codex, Claude Code, etc.) with memory grounding and approval controls.

Getting started

Requires Python 3.10+. Install and launch the CLI with a cloud model: bash python -m pip install memorizz export OPENAI_API_KEY='your-key' memorizz For a fully local setup, use Ollama. Save credentials and configure memory: bash memorizz config set OPENAI_API_KEY memorizz memory configure memorizz notion connect Build a memory-first agent in Python: python from memorizz import MemAgentBuilder agent = ( MemAgentBuilder() .with_instruction('Remember useful context and use it to help the user.') .with_llm_config({'provider': 'openai', 'model': 'gpt-4o-mini'}) .with_memory_ids('my-assistant') .build_and_save() ) scope = {'memory_id': 'my-assistant', 'user_id': 'alice', 'thread_id': 'intro'} with agent.lifecycle(close_memory_provider=True): agent.run('I work on payments systems.', **scope) print(agent.run('What did I tell you about my work?', **scope))

License and pricing

Source available under PolyForm Noncommercial 1.0.0. See NOTICE. The project is open source with a noncommercial license.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/richmondalakememorizz.svg)](https://yunodb.com/tools/richmondalakememorizz?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/richmondalakememorizz?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/richmondalakememorizz.svg" alt="Featured on YunoDB" height="20"></a>