# MemMachine/MemMachine

Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory storage and retrieval to streamline AI agent state management for next-generation autonomous systems.

Repository: https://github.com/MemMachine/MemMachine
Canonical: https://ross.abutalabs.com/products/memmachine
Homepage: https://memmachine.ai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai, memory, memory-management, python, agent, agentic-ai, agents, agents-sdk, ai-agents, conversational-agents, conversational-ai, llm, long-short-term-memory, persistent-memory, personalization, chatbots, genai, knowledge-graph, strands-agents
Last push: 2026-08-26T22:07:26+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 84, longevity 27
- inputs: {"age_days": 383, "days_push": 7, "days_rel": 108, "gap_med": 7, "n_releases_24m": 28}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3201, forks 207 (observed 2026-08-28T04:07:48.522064+00:00)

## What it is
MemMachine is an open-source memory layer for AI agents and LLM applications, providing episodic, profile, and working memory that persists across sessions, agents, and models. It runs as a server (self-hosted or cloud) with a Python client SDK for storing and retrieving conversational context and user preferences.

## Use cases
- give my ai agent persistent memory across sessions
- store and recall user preferences in a chatbot
- add long-term memory to llm applications
- personalize ai assistant responses based on past conversations
- manage agent state that survives restarts
- build context-aware conversational agents in python

## When to choose
- you need drop-in persistent memory for AI agents with a simple client SDK
- you want episodic, profile, and working memory abstractions out of the box
- you need memory that persists across sessions, agents, and model changes
- you prefer self-hosting via Docker or using a managed platform

## When to avoid
- you only need simple in-process state that a database or vector store already covers
- you require a memory solution in a language other than Python
- you cannot run an additional server component alongside your application
- you need fully offline operation without any server dependency

## Facets
- artifact type: service
- maturity: active
- function: rag, agent-framework, vector-database, chatbot, llm-inference
- domain: artificial-intelligence, large-language-models, chatbots, developer-tools
- platform: python, self-hosted, cross-platform
- tags: agent-memory, long-term-memory, episodic-memory, knowledge-graph, personalization, memory-layer, conversational-ai, state-management, ai-agents, retrieval-augmented-generation, docker, web-server

## Member repositories
- MemMachine/MemMachine (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:48.522064+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:24:48.658496+00:00, confidence not recorded.
  - readme: https://github.com/MemMachine/MemMachine (fetched 2026-08-28T04:07:48.522064+00:00, sha 749c32894ce8)
  - homepage: https://memmachine.ai (fetched 2026-08-29T09:38:28.670528+00:00, sha 02e593ebd35f)
  - site_page: https://docs.memmachine.ai (fetched 2026-08-29T09:38:28.679852+00:00, sha a52c31028267)
- Data as of 2026-08-30T08:39:29.467469+00:00.