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

Memora

Memora is a Python MCP memory layer for AI agents, with persistent structured storage, semantic retrieval, graph relations and source-backed context across sessions.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Memora — 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 Memora when an MCP-connected agent needs durable cross-session context and topic-based retrieval from structured, linked memories.

Who it is for

  • Developers integrating persistent memory into MCP-connected AI agents.
  • Agent workflow builders who need searchable knowledge, TODOs, issues and related memories to carry across sessions.

Documented uses

  • Absorb agent facts into durable memory while identifying duplicates, updates, contradictions and related information.
  • Retrieve topic-relevant memories, open TODOs or issues, graph edges and source IDs together.
  • Search stored knowledge using semantic, full-text or hybrid queries and filters.
  • Represent relationships between memories as typed graph edges and retain supersession history.
Before you choose

Requirements & limits

The repository is public and lists an MIT license. The README documents a pip installation for a local stdio process and a container option for an HTTP service.

  • The primary integration model is MCP; the README shows the local process being spawned by an MCP client.
  • SQLite is the stated core storage, with optional cloud sync or storage options including S3, R2 and D1.
  • Embedding choices include TF-IDF, sentence-transformers and OpenAI; local embeddings use an optional package extra.
  • The documented default container runtime is Apple’s container CLI, which requires an Apple-silicon Mac running macOS 26.
  • Absorb supports a dry-run preview, while supersession lineage preserves older knowledge rather than deleting it.

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 Memora locally with pip

Install Memora as a local stdio MCP server for a client to spawn.

Before you start

  • Python package installer pip.
  • An MCP client configured to spawn the server; the README points to .mcp.json configuration.

Steps

  1. Install the package with the command below.

    Documented command
    pip install memora-mcp

  2. Configure the MCP client to spawn memora-server from .mcp.json.

Expected outcome

Memora is installed locally and configured as an MCP server process for the client to launch.

Guide limitations

  • This path is a local stdio child process, not the detached HTTP container service.
  • The README refers to a separate Configuration section for the .mcp.json details.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
9 October 2026
Original website title
agentic-box/memora · Official homepage title · retained in its source language
How we review sourcesSuggest a correction