01
decision
Standardize on idempotent write endpoints
Source: architecture.md
Cross-Agent Memory in Seville · shared project memory
Cross-Agent Memory in Seville
Teams don’t use one AI tool — they use three, and each one forgets alone. MemHub puts a single synchronized memory behind all of them, so a constraint explained to Claude Code constrains Cursor and Codex too.
Cross-agent memory is an architecture choice: keep knowledge outside the agents, in a neutral store they all read. MemHub implements that pattern with MCP compatibility, project scoping, and incremental session briefings.
Create your shared memory
Free Community tier. Self-hosted or hosted. No external embedding API required.
acme/cross-agent-memory
synchronizedcontext/main
memories 41
pinned 6
contributors 9
BRIEFING FOR NEW SESSION
What changed since your last pull
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
LOCAL FIT
Why Seville engineering teams choose MemHub
In Seville, 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.
- Seville: connect Claude Code, Cursor, Windsurf, Cline, Codex CLI, or Antigravity to one shared memory. It also plugs into any CLI that speaks MCP or reads a JSON config.
- 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 Seville, without the trade-offs.
01
Vendor-neutral store
Memory lives in your MemHub project — not inside any single tool’s proprietary format.
02
Consistent briefings
Every client receives the same incremental delta, keeping agents in agreement about project reality.
03
Conflict-friendly history
Versioned entries let teams trace how a decision evolved instead of silently overwriting it.
04
Unified search
One query surface spans everything any agent ever learned on any machine.
05
Simple rollout
Interactive installer targets every supported client in one pass — or comma-select just some.
06
No lock-in
Standard MCP on the wire means adopting another agent tomorrow requires zero migration.
The honest comparison.
No feature-matrix gymnastics — just what changes the week you adopt MemHub.
| Status quo | With MemHub |
|---|---|
| Context lives in heads and DMs | Memory is structured, shared, and searchable |
| Every agent re-learns the repo | Sessions open pre-briefed with only what changed |
| Rules files cap out at ~2k tokens | Unbounded versioned history stays one query away |
Connect the tools already in your repository.
One command injects configuration for Claude Code, Cursor, Codex CLI, Google Antigravity, Windsurf, Cline, or any JSON MCP client.
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
Cross-Agent Memory in MadridCross-Agent Memory in BarcelonaCross-Agent Memory in ValenciaCross-Agent Memory in MálagaCross-Agent Memory in BilbaoCross-Agent Memory in ZaragozaCross-Agent Memory in MurciaCross-Agent Memory in Palma de MallorcaCross-Agent Memory in Las Palmas de Gran CanariaCross-Agent Memory in San FranciscoCross-Agent Memory in New York CityCross-Agent Memory in Austin
EXPLORE OTHER USE CASES
AI Agent Memory
Give every AI coding agent a persistent, team-wide memory.
MCP Memory Server
A hosted MCP memory server your whole team connects to in one command.
Claude Code Memory
Claude Code memory that survives sessions and reaches the whole team.
Cursor Memory
Carry Cursor context across sessions, machines, and teammates.
Codex CLI Memory
Persistent context for Codex CLI — personal today, shared tomorrow.
Developer Knowledge Base
A living knowledge base that writes itself while your team codes.
Self-Hosted AI Memory
Run the entire memory stack on your own PostgreSQL — nothing leaves.
Coding Agent Context
Context engineering for coding agents — brief, don’t dump.
Engineering Decision Log
An ADR habit your team will actually keep — logged by the agents doing the work.
Agent Memory Database
A real database behind agent memory — PostgreSQL, pgvector, row-level security.
Windsurf Memory
Persistent Windsurf context shared with every other agent on the team.
Cline Memory
Give Cline a memory that survives tasks, machines, and teammates.
Copilot Team Memory
What Copilot’s custom instructions can’t hold, MemHub remembers.
Antigravity & Gemini Memory
Persistent context for Google Antigravity, Gemini CLI, and the agents around them.
THE NEXT SESSION STARTS HERE