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

Yourmemory

YourMemory is a Python library and MCP-connected memory service for AI agents. It stores information across sessions, consolidates related facts, links entities, and applies Ebbinghaus-style decay so less-used memories fade over time. It supports local DuckDB storage by default and documents PostgreSQL with pgvector as a shared or production backend.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Yourmemory — 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 an agent needs persistent context across conversations and you want memory management that includes consolidation and age-based decay, rather than only a basic store. Consider its local DuckDB route for a simple local setup or the documented PostgreSQL/pgvector route for shared storage.

Who it is for

  • Developers building AI agents that need to retain useful context between sessions.
  • Teams exploring a shared agent-memory backend using PostgreSQL and pgvector.
  • Builders integrating persistent memory through MCP-compatible clients.

Documented uses

  • Retain durable facts and preferences across agent sessions.
  • Consolidate related memories and reduce accumulated near-duplicates.
  • Retrieve context through a combination of vector search, BM25 and entity links.
  • Set up a local memory store or configure a PostgreSQL-backed shared store.
  • Expose memory to agent clients through the documented MCP integration.
Before you choose

Requirements & limits

The 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.

  • The README specifies Python 3.11–3.14 for package installation; standalone binaries are described for macOS, Linux and Windows.
  • DuckDB is the default local backend and requires no separate database setup; PostgreSQL requires a DATABASE_URL and the pgvector extension.
  • Built-in heuristics are available for extraction; Ollama is an optional local model-based extraction route, and Anthropic can be selected as a cloud extraction backend.
  • The project documents MCP integrations and setup detection for Claude Code, Claude Desktop, Cursor, Windsurf and Cline; client-specific compatibility should be assessed in the intended environment.
  • The README reports results on LoCoMo, LongMemEval and HotpotQA; benchmark figures are project-published and may not predict results for a specific application.

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

Install YourMemory and configure a local memory backend

Set up the Python package and select DuckDB as its local storage backend.

Before you start

  • Python 3.11–3.14
  • An account token obtained by entering an email on the project website and verifying a six-digit code

Steps

  1. Install the package with the command below.

    Documented command
    pip install yourmemory

  2. Run yourmemory-register with the token obtained from the project website.

  3. Run yourmemory-setup and select DuckDB, the documented default local backend.

Expected outcome

The package is set up to store memory locally using DuckDB.

Guide limitations

  • The README describes setup and backend selection, but these steps do not cover configuring an agent to use memory or verifying retrieval.
  • The documentation says setup detects and wires up named agent clients; client-specific results are not independently established.
Documentation 1 ↗
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
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.
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
ContextatlasIndex a repository and find relevant implementation details using a natural-language question.CLI, ServerThe project is open source under the MIT license. Its documented requirements include Node.js 20 or later and embedding and reranking API credentials and settings.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
sachitrafa/YourMemory · Official homepage title · retained in its source language
How we review sourcesSuggest a correction