AsterMem is a self-hosted memory service that stores your data locally in Markdown, SQLite, and a vector index, designed for personal use and AI agents with hybrid search and offline capability.

Stars

35

7-day growth

No data

Forks

3

Open issues

0

License

AGPL-3.0

Last updated

2026-07-29

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It offers a complete, local-first memory system with zero telemetry, hybrid keyword and semantic search, support for 24 model providers (including local ones like LM Studio and Ollama), and a sleek multilingual web UI—all in a single process that can be deployed with one command or Docker.

Who it is for

  • Developers building AI agents that need persistent, private memory
  • Privacy-conscious individuals who want full control over their personal data
  • Self-hosting enthusiasts looking for an easy-to-deploy memory service
  • Users of Cursor or Claude Code who want to integrate a local memory backend

Use cases

  • Provide long-term memory for AI coding assistants like Cursor and Claude Code
  • Store and search personal notes, bookmarks, or journal entries with both keyword and semantic retrieval
  • Run an offline knowledge base for local AI agents without any cloud dependency
  • Quickly set up a private memory service on a home server or laptop using Docker

Strengths

  • Local-first: all data stays in a single folder (data/) with no cloud sync or telemetry
  • Hybrid search combines Whoosh keyword search and Chroma semantic search with paragraph-level retrieval
  • Works offline—no runtime network calls except to the chosen model provider, and local models keep everything offline
  • One-command setup via start.sh/start.bat or Docker, with idempotent launch and useful flags

Considerations

  • Single-user by design, with only one admin account and no multi-user support
  • Requires Python 3.11+ and Node.js 18+ for non-Docker setup, which may be a barrier for some users
  • Semantic search depends on an embedding provider (local or cloud), so full offline semantic search requires a local model

README quick start

Quick start

Description

Self-hosted memory service for AI assistants

Related repositories

Similar projects matched by category, topics, and programming language.

makecindy
Featured
makecindy GitHub avatar

cindy

Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.

AI & Machine LearningLarge Language Models
958
uzairansaruzi
Featured
uzairansaruzi GitHub avatar

hermex

Hermex is a native SwiftUI iPhone app that lets you control a self-hosted Hermes AI agent directly from your phone, with no subscriptions, tracking, or third-party relay.

AI & Machine LearningLarge Language Models
941
hahhforest
Featured
hahhforest GitHub avatar

pi-textbook

A hands-on course that walks through building a Pi-style coding agent from scratch across 15 checkpoints, starting from an offline agent trajectory.

AI & Machine LearningLarge Language Models
625