Open to AI Engineer roles — available immediately, no notice period to serve
Back to projects

MnemOS

Open source · solo-built

A universal, persistent memory layer for AI assistants — designed, built, and open-sourced solo.

AI assistants forget everything between sessions. MnemOS solves that by extracting facts from conversations via LLM, embedding them with bge-m3, and injecting relevant context before each new message — invisibly, across ChatGPT and Claude. Memories are stored per-user rather than per-platform, so context follows the person across tools instead of resetting every session.

0.65 cosineRetrieval threshold
0.88 cosineDedup threshold
FastAPIPostgreSQLpgvectorOllamabge-m3Chrome Extension (MV3)MCP
View source

01 / Onboarding

This is the actual setup wizard, rebuilt as a working component with synthetic data — click through it below. Check the server, pick an engine, download a model, and finish setup.

Live demo · synthetic data · try it
MnemOS

Universal Memory for AI — set up in 2 minutes

1
Connect
2
Engine
3
Done

Connect to MnemOS Server

MnemOS needs a local server running on your machine to store and retrieve memories.

Checking server...

Looking for MnemOS at localhost:8765

02 / Extension popup

The Chrome extension popup — remove a memory, switch the extraction model, and apply it.

Live demo · synthetic data · try it
MnemOS

Memories 5

User wants to learn Rust for inference coding

skill

User wants to learn paragliding

goal

User prefers VS Code for development

preference

User will install Rust using rustup

workflow

User needs to understand ownership and borrowing in Rust

learning

Extraction Model

🦙 Ollama (local)
qwen2.5:7bHigh quality
↻ Dashboard◎ Sessions

03 / Dashboard

Overview, Memories, Sessions, and Settings — all four tabs are live. Search and delete memories, switch tabs, download a model.

Live demo · synthetic data · try it
MnemOSlocalhost:8765

Total Memories

13

Sessions

7

Semantic

52

Episodic

6

By Application

bench 33test 16chatgpt-sim 13

Recent Memories

User wants to learn paragliding

semanticchatgpt-sim · Apr 4, 2026 · 95%

User wants to learn Rust for inference coding

semanticchatgpt-sim · Apr 4, 2026 · 95%

User needs to understand ownership and borrowing in Rust

semanticchatgpt-sim · Apr 4, 2026 · 95%

User will install Rust using rustup

proceduralchatgpt-sim · Apr 4, 2026 · 80%