Skip to content

Latest commit

 

History

24 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

AI Memory Infrastructure Platform

A centralized memory service for AI applications. The platform provides persistent, shared, and governable memory that multiple AI systems can read from and write to through a unified API.

The platform is infrastructure, not an application. It stores, organizes, retrieves, secures, and manages memory on behalf of AI systems.

Status

The platform provides memory CRUD, hybrid search, lifecycle governance, and an operations console. See docs/features.md for the complete feature catalog. For a local Ollama/Qwen chat that stores and recalls AMIP memory, see examples/ollama-chat.

Prerequisites

Tool Version Required for
Docker Desktop recent Backend stack (recommended path)
Node.js 20+ Admin console development
.NET SDK 8.0 Backend development and tests
Python 3.12+ Embedding worker; Ollama reference chat example

Docker alone is enough to run the backend stack. Node.js, .NET, and Python are needed for active development and tests.

Quick start

Important

Before starting, open Docker Desktop or ensure the Docker daemon is running.

git clone <repository-url>
cd ai-memory-infrastructure-platform

# Create .env files and verify Docker
./setup.sh

# Install dependencies
make setup-dev

# Start backend stack and admin console
make dev

Open http://localhost:5173 and sign in at /login with a pre-seeded development account:

Role Email Password
Admin admin@example.com Admin123!
Standard user@example.com User12345!

You can also register a new account at /signup.

Project structure

ai-memory-infrastructure-platform/
├── src/                      Backend services (.NET 8)
├── tests/                    Backend unit and integration tests
├── services/                 Supporting services (embedding worker)
├── examples/                 Reference clients (Ollama chat demo)
├── frontend/                 React admin console (Vite)
├── docs/                     Documentation
├── infra/                    Reserved for observability assets
├── docker-compose.yml        Backend and infrastructure stack
├── .env.example              Environment variable reference
├── setup.sh                  First-time bootstrap
└── Makefile                  Common development commands

Documentation

Document Description
docs/README.md Full documentation index
docs/features.md Feature catalog (start here)
docs/architecture.md System design and memory lifecycle
docs/configuration.md Settings and environment variables
docs/development-guide.md Local setup and coding conventions

Development workflow

make setup-dev    # Install dependencies and create .env files
make dev          # Start backend stack and admin console
make test         # Run backend and frontend tests
make down         # Stop backend stack

License

MIT. See LICENSE.

About

Multi-tenant memory infrastructure for AI systems - versioned storage, hybrid search, and lifecycle governance behind a unified API, with an operations console for namespaces, retrieval, and admin.

Topics

Resources

Security policy

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages