Skip to content
Back to the index

mnemosyne-os

PyPIInfrastructure

PulseGate's liveness check found it on 3 Oct 2026; it is registered on GitHub and PyPI and has been in the index since 24 Aug 2026. How this is checked

mnemosyne-os is a zero-dependency Python package that provides local memory and lexical retrieval for AI agents. It is designed for developers who need token-efficient agent memory without relying on hosted infrastructure.

Inferred · not functionally tested

Open SourceMITCLISelf-hosted
Visit PyPI
8stars
1fork
1alternative
6features
2026since

Overview

6 features

Purpose: Giving AI agents local, token-efficient memory and retrieval without external services.

Inferred · not functionally tested

Audience: AI developers building agent systems

Inferred · not functionally tested

Functions: Unknown

Interfaces: API: unknown · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: pypi.org · github.com. These links do not verify the individual claims.

mnemosyne-os sits in PulseGate's Memory & skills category. Inferred · not functionally tested: It focuses on giving AI agents local, token-efficient memory and retrieval without external services. Inferred · not functionally tested: mnemosyne-os is an open-source project aimed at AI developers building agent systems. Basis unknown · not verified: The project is open source (MIT). Basis unknown · not verified: It runs on the command line, and it can be self-hosted.

Behind mnemosyne-os is FrankHu-HK, and it first shipped in 2026. The project is developed in the open on GitHub with 45 commits in the last 90 days. Inferred · not functionally tested: Among its 6 catalogued features are lexical cache, agent memory, and local retrieval.

Summary written by a language model from the project’s public pages.

Tasks: Inferred · not functionally tested

  • Lexical cache
  • Agent memory
  • Local retrieval
  • Token optimization
  • Zero dependencies
  • Local-first operation

Topics: Inferred · not functionally tested

Tags
agent-memorylexical-cachelocal-first-aitoken-optimization
AI capabilities
TextStructured
Inference: Local

JSON profile · Text profile · Access guide

Built with & integrations

Runs on
CLISelf-hosted

Trust & compliance

License
MIT
Public signals
HTTPSOpen SourceGitHub · ★ 8Active maintenance

Indexing history

1

What PulseGate has recorded for this listing

  1. Indexed24 Aug · 11:20 UTC
    mnemosyne-os seen via PyPI Bulk Enumerator
    Source: PyPI Bulk Enumerator · Open

Frequently asked questions about mnemosyne-os

What is mnemosyne-os?
Inferred · not functionally tested: Mnemosyne-os focuses on giving AI agents local, token-efficient memory and retrieval without external services. It is catalogued under Memory & skills on PulseGate.
Who should use mnemosyne-os?
Inferred · not functionally tested: mnemosyne-os is an open-source project built for AI developers building agent systems.
Does mnemosyne-os have a free plan?
Basis unknown · not verified: Yes — mnemosyne-os is open source under the MIT license and free to use.
What platforms does mnemosyne-os run on?
Basis unknown · not verified: mnemosyne-os runs on the command line. It can also be self-hosted.
Is mnemosyne-os still active?
PulseGate's liveness check found it on 3 Oct 2026. Its GitHub repository shows 45 commits in the last 90 days.
What projects are similar to mnemosyne-os?
Similar projects tracked by PulseGate include Mnemosyne, mnemosyne-hermes, and Mnemosyne OS.Mnemosynemnemosyne-hermesMnemosyne OS
Who makes mnemosyne-os?
mnemosyne-os is developed by FrankHu-HK.
How long has mnemosyne-os been around?
mnemosyne-os first shipped in 2026.

Similar projects

Closest matches by what these projects do