OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

Memmy

Memmy is a personal AI agent and local memory hub that gives supported AI agents shared, persistent context from collaboration history.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Memmy — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Memmy when working across supported AI agents and you want shared context to follow the work between tools.

Who it is for

  • People moving work between coding agents who want project context to carry over.
  • Users looking for a local memory service alongside an AI agent and CLI/TUI.

Documented uses

  • Share project background, preferences and progress across connected agents.
  • Resume unfinished work after switching AI tools.
  • Use a personal agent to organize information and continue tasks.
Before you choose

Requirements & limits

The README recommends the desktop app and directs users to the official website or GitHub Releases. Its Linux CLI installer requires x64 or arm64, Node.js 22 or newer, and an available systemd user session. Registration provides trial tokens for the agent runtime; when these run out, users can switch to BYOK and use their own model API.

  • The project lists support for Claude Code, Codex, OpenClaw, Hermes Agent, Cursor, OpenCode and Pi; detailed setup requirements vary and are not included here.
  • The Linux installer enables systemd user services bound to localhost; the README notes that it does not enable linger.
  • The README distinguishes the desktop app from the CLI/TUI and documents an OpenAI-compatible API for the CLI.
  • Memmy is MIT-licensed and written in TypeScript.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up Memmy’s CLI on supported Linux systems

Install the Memmy CLI and initialize its local memory and gateway services.

Before you start

  • Linux x64 or arm64
  • Node.js 22 or newer
  • An available systemd user session

Steps

  1. Run the command below.

    Documented command
    curl -fsSL https://raw.githubusercontent.com/MemTensor/memmy-agent/main/scripts/install.sh | bash

  2. Run memmy; on first use, follow the model setup wizard if prompted.

  3. Optionally check the services with systemctl --user status memmy-memory.service and systemctl --user status memmy-gateway.service.

  4. For interactive configuration, run memmy onboard; to initialize with defaults, run memmy onboard --defaults.

Expected outcome

The installer enables the local Memory Service. The first bare `memmy` invocation enables the gateway and enters the TUI after it is ready; the services are user-level and bound to localhost.

Guide limitations

  • This CLI installation procedure is specified for Linux x64 or arm64 with Node.js 22 or newer and a systemd user session.
  • The installer does not enable linger; services start again on later logins.
  • Installation alone does not configure integrations with Codex, Claude Code, Cursor, or other agents. Run memmy-memory init or memmy-memory init --agent to install the Memory Skill and supported agent Hook/plugin.
Documentation 1 ↗
Source-based practical guide

Start with the Memmy desktop app

Launch the desktop app and complete initial model setup.

Before you start

  • A macOS or Windows device
  • Either a Memmy account or an API key from a supported model provider

Steps

  1. Download Memmy from the official website or GitHub Releases.

  2. Launch the desktop app.

  3. Choose account mode or API Key mode and configure the primary model.

  4. Complete the connection test.

Expected outcome

The desktop app is set up with a configured primary model and a completed connection test; the documented next step is to send a first task from the main workbench.

Guide limitations

  • The desktop app prerequisites are macOS or Windows.
  • The sources do not provide detailed, platform-specific installation or onboarding controls.
Documentation 1 ↗Documentation 2 ↗
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
9 October 2026
Original website title
MemTensor/memmy-agent · Official homepage title · retained in its source language
How we review sourcesSuggest a correction