Git Product home page Git Product logo

stmemgpt's Introduction

A Programmable AI Assistant with infinite memory using Streamlit & MemGPT

Introduction

MapMentor is an assistant designed to help with learning and creation of Wardley Maps. More on this in several detailed blogs on how to build this with full source code coming soon.

Functions

Learn: Understand components of a Wardley Map. Create: Build your own map with guidance. Explain: Get detailed explanations of mapping concepts. Review: Test your comprehension with exam-style questions.

Interacting with MapMentor

Begin a conversation or ask a question about Wardley Mapping. For more assistance, type 'Help'.

Interaction Examples

User asks: 'What is the purpose of a Wardley Map?' MapMentor explains the purpose.
User requests: 'Help me create a Wardley Map.' MapMentor provides step-by-step guidance.

Personable Learning Experience

Remember, your interactions shape MapMentor! Your learning experience becomes more personalised as you engage and learn over time.

Technology and Memories

MapMentor, under the hood, is powered by advanced machine learning algorithms that enable it to dynamically learn from user interactions. It makes use of three types of memories:

Recall Memory: Stores conversation history for referencing past discussions.
Core Memory: Contains essential instructions and user-specific details updated through interactions.
Archival Memory: Serves as a long-term storage space for essential information.

These memories help in retaining and building upon the context of discussions, ensuring a continuous learning experience.

Powered by OpenAI & MemGPT

MapMentor employs OpenAI's Generative Pretrained Transformer models to process user inputs and generate appropriate responses. The use of such advanced AI technology enables MapMentor to conduct human-like, intelligent conversations with users.

MemGPT memory is divided into three parts: recall memory, core memory, and archival memory.

Recall Memory: This is my short-term memory where I keep recent interactions.
Core Memory: This is where I store key details about my persona and about you, the user. This gives me a 'personality' and allows for more personalized conversation.
Archival Memory: This is my long-term memory where I store information that doesn't fit into core memory but is essential to remember. It's infinite in size, and I usually page through it to find answers to your questions.

These parts work together to help me remember prior engagements, learn from them, and refer back when needed.

stmemgpt's People

Contributors

tractorjuice avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.