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

Memanto

Memanto is an open-source companion memory agent that manages knowledge used by other AI agents, including what to retain, how to handle conflicting or expired memories, and which agents should receive relevant context.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Memanto — 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 Memanto when multiple agents need a curated, shared memory that can be reconciled and pruned over time, rather than relying only on separate stores or archived transcripts.

Who it is for

  • Developers building applications with multiple AI agents.
  • Teams that want agents to share decisions and durable knowledge across separate interactions.
  • Practitioners evaluating a memory-management layer that can export or migrate memory estates.

Documented uses

  • Extract durable facts, decisions, preferences and failures from agent interactions.
  • Consolidate duplicate or fragmented memories into a canonical collection.
  • Reconcile contradictions while retaining what was believed at different times.
  • Apply decay, expiry or deletion policies to stale information.
  • Brief an agent with a relevant subset of stored knowledge before it acts.
Before you choose

Requirements & limits

The repository is public and specifies an MIT license. The README documents a Python CLI installation and describes local Docker-and-Ollama, cloud and self-hosted setup options; it also lists JavaScript and Go packages.

  • Memanto is described as a companion agent with lifecycle-management responsibilities, not merely a place to store memories.
  • Its documented functions include extraction, consolidation, conflict reconciliation, forgetting, agent briefing and memory export.
  • The README provides package installation paths for Python, JavaScript and Go.
  • The documented local mode uses Docker and Ollama; the README also describes cloud and self-hosted modes.
  • The README names migration sources including Mem0, Letta, Supermemory, Zep and Hindsight, as well as OKF bundles.

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 the Memanto CLI and connect an agent

Follow the README’s documented quick-start stages to install Memanto and connect a named agent tool.

Before you start

  • Python package installer, for the documented pip path.
  • A supported agent tool named in the README, such as Claude Code, Cursor, Codex, Windsurf, Cline, Goose or Copilot.
  • Choose the documented On-Prem or Cloud setup when starting Memanto; the README describes On-Prem as Docker-based and Cloud as using a free key.

Steps

  1. Install the package with the command below.

    Documented command
    pip install memanto

  2. Start Memanto with memanto and select the On-Prem or Cloud setup described in the README.

  3. Connect an agent tool with memanto connect claude-code, substituting another named tool where appropriate.

Expected outcome

The documented flow is intended to connect an agent tool to a Memanto-managed memory estate.

Guide limitations

  • The listed platforms and integrations are project claims, not compatibility guarantees.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
10 October 2026
Original website title
moorcheh-ai/memanto · Official homepage title · retained in its source language
How we review sourcesSuggest a correction