Mneme

Context

AI assistants forget. Mneme fixes that: it indexes email, calendar, chat, and files into an entity graph, then retrieves memories the way research says works best, using the HippoRAG-2 algorithm reimplemented in pure Python. Feed the same Brain to Claude, GPT, Gemini, or a local model: you are never locked to one lab.

What we built

We built the product end to end: the retrieval engine, a CLI developers actually enjoy, and the public site. Local-first by default, no GPU required, hosted cloud optional. Install is one line: pipx install mneme, with a wizard that gets you from command to first answer in under two minutes.

Four kinds of memory

The site explains the product the way the engine actually thinks: people (who matters, and why), promises (what you said you'd do), threads (the shape of a conversation), and context (the thing under the thing). The demo questions say it best: who's waiting on me, what did we decide about pricing, who introduced me to Maya.

One import, any model

For developers, build_context returns ranked, deduplicated, cited context sized to a token budget, and why traces any answer back to its source. Python today, TypeScript next, and mneme mcp serves a Brain straight to Claude Desktop or Cursor. The principles read like a manifesto: local-first, model-agnostic, open source under Apache 2.0, and forget and export are built-in verbs, not support tickets.

Dark, quiet, typographic

The page leads with one sentence, 'Give your AI a brain', set over a slow bloom of petals, and everything else stays out of the way.

Under the hood

The engine is pure Python, with every answer traceable back to its sources. The site is Next.js with Tailwind and Framer Motion.

Outcome

The result is memory infrastructure you can benchmark, with reproducible comparisons against the usual suspects on personal corpora.