OpenViSTAI · Agents · Blockchain · Crypto
Menu
Agent Memory & RAG

AI Memory Vault

AI Memory Vault is an open-source system of scripts and templates that turns an Obsidian vault of Markdown files into persistent working memory for terminal-based AI tools. It organizes project notes, daily records, user information and recurring-task instructions so an assistant can retrieve relevant context across sessions without a vector database.

Independent OpenViST project profile, based on linked sources.

AI Memory Vault — 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 it when configuring a terminal AI assistant to retain and retrieve working context from Markdown files across sessions, especially when you want task-specific notes organized in an Obsidian vault.

Who it is for

  • Claude Code users who want an assistant to retain project and personal working context between sessions.
  • People organizing task-specific notes so an AI can consult relevant information before generating an output.
  • Builders exploring a file-based memory workflow for terminal AI tools that read and write files.

Documented uses

  • Build a structured Obsidian vault for an AI assistant's working memory.
  • Keep startup instructions separate from vault notes and direct Claude Code to the vault.
  • Organize daily notes, project context and a profile that can be updated as the AI learns.
  • Prime an assistant for a recurring task by having it read the appropriate notes first.
Before you choose

Requirements & limits

The repository describes the system as free and open, and identifies its license as CC BY-SA 4.0. Claude Code is the documented and tested environment. The README says other terminal AI tools that can read and write files may work with rough edges.

  • The documented workflow depends on Markdown files and an Obsidian vault.
  • The build script can check for Obsidian and install it if it is not present.
  • Claude Code's boot configuration is kept in the working directory, while the vault contains notes and its index.
  • The README says adaptations may be used commercially if attribution is given and adapted versions use the same license.

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 an Obsidian memory vault with Claude Code

Use the repository's build script in Claude Code to create a configured vault and its supporting files.

Before you start

  • Claude Code; the README says the system was built and tested on it.
  • The AI Memory Vault repository and its build script.
  • Obsidian, which the script checks for and can install if it is missing.

Steps

  1. In a Claude Code session, ask to set up the system and provide https://github.com/jaredrhod/ai-memory-vault.git.

  2. Work through the build script's interview and let it check for Obsidian.

  3. Use the generated boot configuration and vault structure, including the profile, daily notes and recurring-task Jobs.

Expected outcome

A configured Obsidian Markdown vault that Claude Code can use as persistent working memory, with startup instructions and organized notes.

Guide limitations

  • The README says other terminal AI tools that read and write files may work with rough edges.
  • The build process is documented for Claude Code; this guide does not establish successful execution.
COMPARE OPTIONS

Compare options for Vector search

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
AI Memory VaultBuild a structured Obsidian vault for an AI assistant's working memory.CLI, Self-hostedThe repository describes the system as free and open, and identifies its license as CC BY-SA 4.0. Claude Code is the documented and tested environment. The README says other terminal AI tools that can read and write files may work with rough edges.
Engram MemoryPersist agent memories across sessions.Linux, macOS, Self-hosted, WindowsThe repository README identifies a BSL 1.1 license. It describes the Community edition as free for internal use, research and self-hosted deployments; commercial or SaaS use requires a license, and each version converts to Apache 2.0 after four years. The self-hosted setup requires Docker, 4 GB or more of RAM and 10 GB or more of storage. Python 3.10 or later is needed only to run the stdio MCP server or CLI tools di
YourmemoryRetain durable facts and preferences across agent sessions.CLI, Self-hosted, ServerThe Python package setup requires obtaining a token through the project website by entering an email and verifying a six-digit code. The README also describes standalone binaries for macOS, Linux and Windows.
Evidence and transparency

Sources & review

Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
jaredrhod/ai-memory-vault · Official homepage title · retained in its source language