built in publicrecognition livefederation connectedrecall 0 msnpm 0.30.0

Memory that feels like being known.

Ask most AI tools about something you told them last week and you get a pause, a database lookup, and a reply that sounds like a search result. Bourdon works the way human memory does: it recognizes you instantly, starts responding, and pulls the details up in the background. One memory, shared by all your agents. What you tell one, the others already know.

$ pipx install bourdonv0.30.0$ npm i -g bourdonv0.30.0

Self-hosting stays free. Test in a temporary sandbox with bourdon demo. Managed private instances at app.bourdon.ai: 7-day free trial, card required, cancel any time. Team is five seats.

the problem · today’s memory

Today’s AI memory is a filing cabinet. Yours isn’t.

When you see a familiar face you don’t freeze while you search your memories. You know them first, and the details arrive while you’re already saying hello. Today’s AI does the opposite: silence, search, then a reply. Bourdon puts the steps back in human order: recognition first, hydration second, archive descent third.

human: speaks.       human: speaks again.
   |                    |
   v                    v
(silence, retrieval, search...)
   |                    |
   v                    v
ai: replies.         ai: replies.
federation · 30 agents · 38 surfaces

What you tell one, they all know.

Every agent you use writes to one shared memory, and every other agent recognizes it on its next turn. Coding agents, both kinds of Copilot, app builders, bots, assistants, even your meetings and CAD.

30 agents, one memoryreads its storeOAuthbot familyquarantinedpreviewdrag to spin
Coding agents

Terminal and editor agents, read from their own session stores and hooks.

Copilot, both kinds

GitHub Copilot and Microsoft Copilot share a name, not a memory. Copilot CLI and Copilot in VS Code don't share one either.

App builders

Cloud builders, read from their project and session exports.

Bots & teammates

Bot families with one peer per bot, and autonomous agents.

Chat assistants

Desktop and browser assistants, connected locally or over OAuth.

Meetings & CAD

What people decided, and what the hardware actually is.

Your agents

Anything that speaks MCP, or a participant module of your own.

evidence · field tests

Evidence

Three field tests on live agents against real work.

how bourdon differs · positioning
run it your way · pricing

Self-host free. Or let us run the box.

Self-hosting is the default and it is the whole engine, cross-agent federation included. Managed hosting is live at app.bourdon.ai as a private instance on its own machine and volume, solo or with a team of five. The free to paid line is operations, never engine capability: you pay for uptime, not for features.

Federation is never gated. Cross-agent memory is the product, not an upsell. It is here at the free tier and it stays here.
the family · one instrument

Bourdon is one organ of a fleet instrument. Its sibling Positif is the cross-agent routing: what the fleet is allowed to do. Bourdon is the cross-agent memory: what the fleet knows. Tremulant is the conductor, for when the fleet acts on its own. And Prestant is the console in front of them all. Each with its own brand; one instrument.

get in touch
Stay tuned

Follow tagged releases and notes without sharing an email address.

Follow releases on GitLab

Email signups are paused for this release.

Partner with us

Building on agent memory, integrating a participant, or licensing Bourdon? Contact the team directly.

Email [email protected]

This opens your email client; the site stores nothing.

get started

One memory, shared by all your agents.

Self-host the engine on your own machine, or let us run a private instance with its own encrypted volume.

$ npm i -g bourdonv0.30.0$ pipx install bourdonv0.30.0