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

Sibyl Memory

Sibyl Memory is a Python library and set of companion tools for giving AI agents durable, file-based long-term memory. Its SQLite and FTS5-backed store is available through an SDK, CLI, MCP server, Hermes adapter and LangGraph BaseStore integration.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Sibyl Memory — 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 Sibyl Memory when an agent needs persistent, file-based storage and you want an integration matching its stack—direct Python SDK, MCP, Hermes or LangGraph—without adding a vector database or embedding model.

Who it is for

  • Python developers adding persistent memory to an AI agent.
  • Teams connecting local agent memory to MCP-compatible clients.
  • Developers building with LangGraph or Hermes Agent.

Documented uses

  • Store and retrieve durable agent memory using the Python SDK.
  • Expose the memory store to an MCP-compatible client.
  • Use a LangGraph BaseStore for long-term, cross-thread persistence.
  • Connect memory to a Hermes Agent through its adapter.
  • Inspect or manage memory tiers with the CLI.
Before you choose

Requirements & limits

The project documents a free tier by default and browser-based account activation through `sibyl init`. It supports Linux and macOS, plus Windows through WSL2; native Windows is not supported.

  • The memory store is SQLite-backed and uses FTS5 search, rather than a vector database and embeddings.
  • Each integration has a separate package: SDK, CLI, MCP server, Hermes adapter and LangGraph BaseStore.
  • The documented platform requirements are Python 3.10+ and Linux, macOS or Windows through WSL2.
  • The README says tier verification may contact the service when an activated account writes beyond its tier cap.

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 CLI and activate Sibyl Memory

Install the command-line package and start account activation.

Before you start

  • Python 3.10 or later.
  • Linux, macOS, or Windows through WSL2; native Windows is not supported.

Steps

  1. Install the CLI with the command below.

    Documented command
    pip install sibyl-memory-cli

  2. Run sibyl init.

  3. Complete the browser-based activation flow.

Expected outcome

The CLI setup flow begins account activation and writes credentials to `~/.sibyl-memory/credentials.json`.

Guide limitations

  • The README says free tier is the default and that higher tiers are managed through the CLI.
  • This describes the documented setup flow, not an independently tested installation.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
Sibyl-Labs/Sibyl-Memory · Official homepage title · retained in its source language
How we review sourcesSuggest a correction