Mnemosyne
PulseGate's liveness check found it on 7 Oct 2026; it is registered on GitHub and has been in the index since 29 Jun 2026. How this is checked
Mnemosyne is a native AI memory system for Hermes Agent and other AI agents. It is described as a universal memory layer for AI agents that need fast, reliable, persistent memory, and it is built around SQLite with a zero-dependency design.
Inferred · not functionally tested
Overview
6 featuresPurpose: Providing fast, local, dependency-free memory storage for AI agents and applications.
Inferred · not functionally tested
Audience: AI developers and agent framework builders
Inferred · not functionally tested
Functions: rag
Inferred · not functionally tested
Interfaces: API: indicated (inferred, not tested) · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)
Recorded constraints: pricing: open_source · license: MIT · platforms: CLI, WEB · deployment: browser, cli, self_hosted
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: mnemosyne.site · github.com. These links do not verify the individual claims.
Mnemosyne sits in PulseGate's Memory & skills category. Inferred · not functionally tested: It focuses on providing fast, local, dependency-free memory storage for AI agents and applications. Inferred · not functionally tested: Mnemosyne is an open-source project aimed at AI developers and agent framework builders. Basis unknown · not verified: Mnemosyne is open source under the MIT license. Basis unknown · not verified: It runs on the web and the command line, and it can be self-hosted.
It is developed by Mnemosyne Maintainers, and it first shipped in 2026. The project is developed in the open on GitHub with 1.3k stars and 747 commits in the last 90 days. Inferred · not functionally tested: Key capabilities include sub-millisecond memory, SQLite backend, and zero dependencies. Inferred · not functionally tested: Catalogued interfaces include a public API.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Sub-millisecond memory
- SQLite backend
- Zero dependencies
- Offline mode
- Python integration
- Open source
Topics: Inferred · not functionally tested
Built with & integrations
- Next.js
- /_next/static/ in the HTML · __next_f in the HTML
- Vercel
- x-vercel-id header · x-vercel-cache header
- Cloudflare
- cf-ray header · cf-cache-status header
Trust & compliance
Indexing history
What PulseGate has recorded for this listing
Frequently asked questions about Mnemosyne
- What does Mnemosyne do?
- Inferred · not functionally tested: Mnemosyne focuses on providing fast, local, dependency-free memory storage for AI agents and applications. It is catalogued under Memory & skills on PulseGate.
- Who should use Mnemosyne?
- Inferred · not functionally tested: Mnemosyne is an open-source project built for AI developers and agent framework builders.
- Is Mnemosyne free?
- Basis unknown · not verified: Yes — Mnemosyne is open source under the MIT license and free to use.
- What platforms does Mnemosyne run on?
- Basis unknown · not verified: Mnemosyne runs on the web and the command line. It can also be self-hosted.
- Is Mnemosyne still active?
- PulseGate's liveness check found it on 7 Oct 2026. Its GitHub repository shows 747 commits in the last 90 days.
- What projects are similar to Mnemosyne?
- Similar projects tracked by PulseGate include mnemosyne-os, mnemosyne-hermes, and Mnemosyne OS.mnemosyne-osmnemosyne-hermesMnemosyne OS
- Who develops Mnemosyne?
- Mnemosyne is developed by Mnemosyne Maintainers.
- When did Mnemosyne launch?
- Mnemosyne first shipped in 2026.
Similar projects
Closest matches by what these projects do