Setup guide

See it work in two commands.

A local memory layer for agents, with every command, expected result, and recovery path.

Do the full install See the current release

Python 3.11+ PostgreSQL 18 via Docker Windows · macOS · Linux Runs offline

ATM-Bench Recall@10 92.89 vs 79.09 best published (limits) MTRAG correct refusals second of ten (limits) Zero memory-layer LLM calls to build memory (limits)

What you are installing

A memory that would rather say nothing than guess.

RE-call stores notes, decisions, and project history, then searches them by meaning.

When nothing matches with enough confidence, it abstains instead of handing you the nearest note.

The middle question recall quickstart asks

Output

[ABSTAIN GAP] query='penguins on Mars?'
  reason: no confident match in this corpus
  evidence: rate-limits.md · confidence 0.30

A low-confidence match is shown as evidence, not presented as an answer.

You need: Python 3.11+3.12 to 3.14 also supported
And: Docker DesktopRuns the database for you
Your data: Stays localThe default embedder runs on your machine
Licence: PolyForm NoncommercialPersonal and research use

The moving parts

Three things, and only one of them is RE-call.

Most of the confusion in a first install comes from not knowing which piece a command is talking to. There are only three.

Piece	What it does	You touch it
A PostgreSQL database	Stores your notes and their vector embeddings.	Once, during setup.
The RE-call package	Indexes markdown and decides whether a result is safe to use.	Every query.
The MCP server	Lets Claude Code query your local memory.	Optional.

Windows, macOS and Linux

The current release installs from PyPI on every supported platform.

Install the 0.14.0 package with Python and follow the setup guide. Docker supplies the PostgreSQL database, and the same guided flow configures your corpus and agent integration.

The current GitHub release does not include a standalone Windows installer. The release page explains the available package files and the supported install path.

Install from PyPI

What you need

Python 3.11 or newer and Docker Desktop are the supported prerequisites. The package is source available under the PolyForm Noncommercial License.

The current release page links to PyPI and GitHub, and the full install guide walks through the setup.

The rest of this site

Four pages you will want after the install, and not before.

Start at step one.

Install two things, then verify each step as you go.

Start the install