repowiserepowise

Command-line tool

mem0ai / mem0

Universal memory layer for AI Agents

★ 69,014stars on GitHubPythonApache-2.0

This connects Repowise to mem0ai/mem0's code. It does not install mem0.

Repowise maps public repos from their source. Not affiliated with mem0ai. What is Repowise?

github.com/mem0ai/mem0Indexed at 001c235

What is mem0?

mem0 is a universal memory layer for AI agents, used to give assistants and agents memory of user preferences and past interactions. It stores memories from what users and agents provide and retrieves the relevant ones later, so responses can be personalized and adapt over time. The main language is Python, and the repository also includes a TypeScript SDK and a Node command line tool. To install it, run git clone https://github.com/mem0ai/mem0.git and follow the steps below. Its code health is 7.1 out of 10 (Good), ranked #128 of 4,000+ indexed repos. The last commit to mem0 was on Aug 14, 2026, and 120 people have contributed.

As of commit 001c235, indexed Aug 18, 2026. What it is comes from a model reading the README; the rest is measured from the source and git history, not from the maintainer.

For agentsmem0.md

Repo facts: type, license, health, rank, contributors
mem0 facts
TypeCommand-line tool
LicenseApache-2.0
Code health7.1 / 10 (Good)
Health rank#128 of 4,000+ indexed repos
Last commitAug 14, 2026
Contributors120
Bus factor1
Size1,491 files, 228,481 lines

Install mem0

Commands copied from the README

  1. 1Clone the mem0 repository.
    git clone https://github.com/mem0ai/mem0.git
  2. 2Move into the mem0 folder.
    cd mem0
  3. 3Install the Python library
    pip install mem0ai
  4. 4Install the TypeScript SDK
    npm install mem0ai
  5. 5Start the self-hosted server, create an admin, and issue the first API key
    cd server && make bootstrap

Releases on GitHub (latest ts-v3.3.1, Sep 25, 2026)

Full install notes on GitHub

Explore mem0

Ask about this code in your agent

This connects Repowise to mem0's code. It does not install mem0. To install mem0, use the install steps.

Useful if you want to change or fork mem0: your agent can ask how it is put together and get answers that cite its files.

How to use mem0

  1. 1Initialize the mem0 command line tool
    mem0 init

Ask about mem0

Answers come from mem0's README and source, with the files they cite. Two free answers a day without an account.

Want this for your own codebase? Map your repo free

About this page

Get a page like this for your own codebase

Repowise built this map of mem0ai/mem0 from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.

Free for 2 public repos, with a page like this one. No card. See how Repowise works

Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed. Star Repowise on GitHub

mem0ai/mem0 FAQ

What is mem0?

mem0 is a universal memory layer for AI agents that lets assistants remember user preferences and adapt to individual needs. It is aimed at customer support chatbots, AI assistants, and autonomous systems.

How does mem0 work?

mem0 extracts memories from the input it receives and stores them, then retrieves relevant ones using semantic, keyword, and entity matching. It uses gpt-5-mini from OpenAI as the default LLM and text-embedding-3-small as the default embedding model.

How do I install mem0?

mem0 can be installed as a Python library with pip install mem0ai or as an npm package with npm install mem0ai. A self-hosted server can be started with cd server && make bootstrap. See the install steps

What language is mem0 written in?

mem0 is primarily written in Python. The repository also includes a TypeScript SDK and a Node command line tool.

How is the mem0 code organized?

The repository is split into top-level directories such as mem0 for the Python package, mem0-ts for the TypeScript SDK, server for the self-hosted stack, cli for the command line tool, and integrations for integration code.

Who is mem0 for?

mem0 is for developers building AI assistants, customer support chatbots, and autonomous systems that need to personalize responses. It offers a library for testing, a self-hosted server for teams, and a managed cloud platform.

What license does mem0 use?

mem0 is licensed under Apache-2.0.

Code health

7.1out of 10Good

Hotspots average 4.3, the place fixes pay off most.

On the leaderboards:#2 of 4 Agent memory layers#33 of 67 Python repos

Key features of mem0

  • Multi-level memory that retains User, Session, and Agent state with adaptive personalization.
  • Single-pass ADD-only extraction that stores new memories without overwriting earlier ones.
  • Multi-signal retrieval that combines semantic search, BM25 keyword matching, and entity matching.
  • Temporal reasoning that ranks the right dated memory for queries about current state, past events, and upcoming plans.
  • A command line tool for adding and searching memories from the terminal, with memories tied to a user ID.

How mem0ai/mem0 works

Input enters through the Python library, where mem0/memory/main.py, a hotspot file in the mem0 package, holds the central memory logic. The TypeScript SDK has a matching memory module at mem0-ts/src/oss/src/memory/index.ts. The server directory contains the self-hosted stack, which is started with make bootstrap or Docker Compose and then configured through a browser setup wizard. The cli directory provides the mem0 command line tool, with cli/python/src/mem0_cli/app.py and cli/node/src/index.ts as its entry points for commands such as add and search. The integrations directory, the largest module by file count, contains the integration code.

The codebase has 1,491 files and 8,251 symbols in 11 modules, mostly Python by code size, with the most files in TypeScript. Code health is 7.1 out of 10, rated good.