Skip to content
Mnemosyne logo

Mnemosyne

Stores and recalls agent memories in a local SQLite file, using vector and full-text search for retrieval.

Actively maintained

At a glanceswept Oct 18, 2026

≈ 3visits/mo

Established · estimate, read Oct 18, 2026

For
Developers building AI agents who need persistent, local, private memory without running servers.
Activity
Actively maintainedrelease 4 days ago
Runs as
SDK
Used for
  • store user preferences as memories for an agent
  • recall relevant past context before an agent responds
  • keep agent memory offline in a local SQLite file
Worth knowingcomputed from what we read · each with its source
  • 3,461 stars on GitHubGitHub ↗
  • 33,765 installs a month on pypipublic registry
  • Publishes llms.txt, a file written for AI assistantsmnemosyne.site ↗
  • Launched on Product Hunt on Jun 1, 2026Product Hunt ↗
Alternatives in Developer toolsby use, among tools still maintained

Figure and bar: visits/mo, estimate · year: online since

Compare Mnemosyne with

Pick up to two.

All 10 alternatives to Mnemosyne →

All Developer tools tools →

Not it? Say what you need

beta

Three tools from the Atlas for the job you describe, each with what fits and what does not.

From people who use itnot part of the reading

No notes yet. What do you use Mnemosyne for?

Sign in to leave a note
Questions this page answers
  • What is Mnemosyne?

    Stores and recalls agent memories in a local SQLite file, using vector and full-text search for retrieval. It is listed in the Atlas under Developer tools.

  • Who is Mnemosyne for?

    Developers building AI agents who need persistent, local, private memory without running servers.

  • Do people use Mnemosyne?

    Established: ≈ 3 visits/mo · estimate, 2026-10 · 33.8k installs/mo (pypi).

  • Is Mnemosyne still maintained?

    Actively maintained: release 4 days ago.

  • What are alternatives to Mnemosyne?

    In Developer tools, by use: Paragon, Axiom, Mem0, Hindsight, Cosmic, Tavily.

How we read a tool

No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.

  • Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
  • Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
  • Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
  • The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.

How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.

How we read every tool → · By INITE Atlas Desk