Skip to content

♻️💾 Yet Another Memory Layer, inspired by Cognitive Science, designed for Cyber Waifu

License

Notifications You must be signed in to change notification settings

moeru-ai/plast-mem

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

153 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Plast Mem

Yet Another Memory Layer, inspired by Cognitive Science, designed for Cyber Waifu

Core Design

These are the design goals for Plast Mem, some of which may not yet been implemented. See docs/ARCHITECTURE.md for implementation details.

Self-hosted first

Plast Mem is built around self-hosting and does not try to steer you towards a website with a 'Pricing' tab.

Written in Rust, it is packaged as a single binary (or Docker image) and requires only a connection to an LLM service (such as llama.cpp) and a ParadeDB database to work.

Event Segmentation Theory

Conversations flow continuously, but human memory segments them into discrete episodes. Plast Mem uses Event Segmentation Theory to detect natural boundaries—topic shifts, time gaps, or message accumulation—and creates episodic memories at these boundaries.

FSRS

By introducing FSRS (Free Spaced Repetition Scheduler), we can determine when a memory should be forgotten.

Retrieval records candidate memories for review; when the conversation is later segmented, An LLM evaluates each memory's relevance (Again/Hard/Good/Easy) and updates FSRS parameters accordingly.

FAQ

What is the current status of this project?

We have not yet released version 0.1.0 because the core functionality is incomplete. However, you are welcome to join us in developing it! See CONTRIBUTING.md for guidelines.

Is it related to Project AIRI's Alaya?

No, but I might draw inspiration from some of it - or I might not.

Which model should I use?

For locally running embedding models, we recommend Qwen3-Embedding-0.6B - its dimensionality meets requirements and delivers high-quality embeddings.

For other embedding models, simply ensure they can output vectors of 1024 dimensions or higher and support MRL, like OpenAI's text-embedding-3-small.

For chat models, no recommendations are currently available, as further testing is still required.

License

MIT

Acknowledgments

This project is inspired by the design of:

About

♻️💾 Yet Another Memory Layer, inspired by Cognitive Science, designed for Cyber Waifu

Resources

License

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •