Cross-Agent Memory in Dublin · shared project memory — local-first · offline-ready

Cross-Agent Memory in Dublin

Stop teaching the same lesson to three agents. One MemHub memory behind Claude Code, Cursor, Codex and Antigravity — a constraint taught once constrains them all. Start free in 2 minutes.

Cross-agent memory is architecture, not a hack: neutral store, project-scoped, MCP-native, incremental briefings. Teams stay in agreement instead of vendor drift.

Start free — get briefed in 2 min

Free for 1 project · No card · Self-host or we host · No external API

acme/cross-agent-memory
synchronized

context/main

memories 41

pinned 6

contributors 9

BRIEFING FOR NEW SESSION

What changed since your last pull

3 new
01
decision

Standardize on idempotent write endpoints

Source: architecture.md

02
pattern

Repository layer owns every database transaction

Source: pull request #214

03
bugfix

Refresh tokens rotate atomically under load

Source: auth/session.ts

Claude Code
Cursor
Windsurf

WHY IT MATTERS HERE

Why Dublin engineering teams choose MemHub

In Dublin, software teams ship faster when their tools share one memory instead of three silos. Distributed squads stay aligned because every session opens with the same briefing.

MemHub runs hosted or fully self-hosted, so the storage boundary follows your compliance requirements rather than dictating them.

  • Built for Dublin: the EMEA engineering hub for many US platforms.
  • Local-first writes keep sessions productive through outages and travel.
  • One command onboards the whole team: memhub login, then connect for Claude Code, Cursor, Windsurf, Cline, Codex CLI, or any JSON client.

UNIVERSAL COMPATIBILITY

Plugs into any CLI or development tool you use.

If it speaks MCP or reads a JSON config, MemHub plugs in. One command wires the majors; everything else joins as a generic client.

  • Claude Code
  • Cursor
  • Windsurf
  • Cline
  • Codex CLI (GPT)
  • GitHub Copilot
  • Google Antigravity
  • Gemini CLI
  • Aider
  • OpenCode
  • CI bots via REST

WHAT YOU GET

Cross-Agent Memory in Dublin, without the trade-offs.

01

One memory, every agent

Vendor-neutral store — a constraint taught to Claude Code constrains Cursor and Codex too.

02

All agents agree

Every client gets same incremental delta — no drift between tools on same repo.

03

Trace, don’t overwrite

Versioned entries show how a decision evolved — no silent overwrites, no lost rationale.

04

One search, every lesson

Single query surface across everything any agent learned on any machine — find in seconds.

05

Roll out in minutes

Interactive installer wires all supported clients at once — or pick just two.

06

Adopt the next agent free

Standard MCP on the wire — adding Antigravity or Gemini next month needs zero migration.

The honest comparison.

No feature-matrix gymnastics — just what changes the week you adopt MemHub.

Without MemHubWith MemHub
Context lives in heads and DMs → onboarding takes daysStructured, searchable memory → new dev/agent productive in minutes
Every agent re-learns the repo from scratchSessions open pre-briefed with only what changed — zero re-explaining
Rules files cap out at ~2k tokensUnbounded versioned history stays one query away — never cap again
Decisions re-litigated, bugs re-introducedPinned invariants prevent regressions — agents respect past calls

Keep your stack. Add shared memory.

One command for Claude Code, Cursor, Codex, Windsurf, Cline or any MCP client. No new editor. Setup in 2 minutes, works offline.

repository terminal

$ npm install --global @simplexlat/memhub

$ memhub login

✓ project resolved · context ready · memory synchronized

Questions, answered straight.

Which tools share the memory?

Anything that speaks MCP: Claude Code, Cursor, Codex CLI, Google Antigravity, Cline, Windsurf, or a generic JSON-configured client.

Do all agents get write access?

Credentials are scoped per project and role. You decide which machines can read, write, or administer shared memory.

What happens when our connection drops?

Nothing interrupts the work. Writes commit to the local SQLite outbox and synchronize automatically when the shared service is reachable again.

Can we try it without sending data anywhere?

Yes — the local engine works fully offline, and the self-hosted stack keeps even the shared layer on your own PostgreSQL.

How much does it cost?

A Community tier is free, and the Team plan adds multi-project contexts, seats, and higher synchronization limits. Self-hosting is unlimited.

MORE LOCATIONS

EXPLORE OTHER USE CASES

THE NEXT SESSION STARTS HERE — 2 MIN SETUP

Stop rebuilding context.
Start shipping faster.

Create workspace — free