Atlaso

io.github.imashishkh21Published by GitHub account imashishkh21v0.1.0a6Updated Oct 25, 2026

Open-source memory for AI agents. Conflict-flagging recall, scope-bag dispersion, local SQLite.

The publisher's own server: Atlaso Memory

VerifiedSTDIODesktop onlyDatabasesKnowledge & Memory

Overview

AI-generated overview

Atlaso is a local, open-source memory server that gives an AI assistant persistent recall stored in a local SQLite database.

What you can do
Store and recall agent memory backed by a local SQLite database, kept in a project-level .atlaso store directory rather than a remote service. Recall memories with conflict flagging, so the assistant can see when stored items disagree. Use scope-bag dispersion to spread and organize memories across scopes. Locate the store automatically by walking up from the working directory to an existing .atlaso folder or a project marker, or point to it explicitly.
When to use it
Useful when you want an assistant to remember context across sessions on your own machine, especially per project, and want conflicting memories surfaced rather than silently overwritten. A fit for local, open-source setups where memory should stay on disk instead of a hosted service.
Requirements
Runs as a local stdio process, installed from PyPI as atlaso and launched with uvx, so a Python/uv environment is needed. No authentication is declared. Optionally set ATLASO_PATH to an absolute path for the .atlaso store; otherwise it is discovered by walking up from the current working directory to an existing .atlaso folder or a project marker such as pyproject.toml, package.json or .git.
Before you install
It writes memory data to a local .atlaso store on disk, so stored content persists and should be treated as sensitive. The store location is inferred from the working directory, so running it in the wrong project could read or write the wrong memory store. No authentication is declared, so anyone with access to the machine and store path can read it.

Installation

In SourceWeft

  1. Open Atlaso in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

This repository has no README.

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0a6LatestSep 16, 2026

Score

25% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.

Other Atlaso integrations