ZIDAN MUBARAKBANDA ACEH, ID
Loading portfolio
Loading
ZIDAN MUBARAK

Open source

Memory Vault AI

A model-agnostic memory layer that gives any LLM persistent, user-scoped context, shipped as a Python package, REST API, CLI and MCP server.

Role
Solo, library, API, CLI and docs
Year
2026
Stack
Python · FastAPI · ChromaDB · MCP · Docker · PyPI
Reading time
Project note
Team
Solo project
Memory Vault AI documentation site with the four integration modes.
Fig. 01 · Live captureThe Memory Vault AI documentation site, captured from GitHub Pages.

01 · Overview

What it is

A model-agnostic memory layer that gives any LLM persistent, user-scoped context, shipped as a Python package, REST API, CLI and MCP server.

Memory Vault sits between an application and any LLM: it classifies what is worth remembering, compresses what is stale, and injects only the relevant memories into the next prompt. It runs locally against ChromaDB, so the default deployment costs nothing and never sends memory to a vendor.

02 · Highlights

Highlights

  1. 01

    Four memory types (episodic, semantic, working, procedural) with vector retrieval.

  2. 02

    Token-budget-aware recall; old memories are compressed instead of deleted.

  3. 03

    Local-first: ChromaDB and local embeddings, no vendor required.

  4. 04

    MCP-compatible with Claude Desktop and Cursor.

  5. 05

    Published on PyPI as `memory-vault`.

03 · Stack

Stack

  • Python
  • FastAPI
  • ChromaDB
  • MCP
  • Docker
  • PyPI

Sources