01
decision
Standardize on idempotent write endpoints
Source: architecture.md
Cursor Memory in Paris · shared project memory
Cursor Memory in Paris
Re-typing context after every “New Chat” is the tax nobody budgets for. MemHub pays it for you: project memory synchronizes continuously, so a fresh Cursor chat opens already briefed on the latest architecture decisions.
Rules files tell Cursor what to do; MemHub remembers why. Rejected libraries, migration constraints, incident lessons — the reasoning that makes suggestions correct — persist beyond any single editor session.
Create your shared memory
Free Community tier. Self-hosted or hosted. No external embedding API required.
acme/cursor-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 Paris engineering teams choose MemHub
In Paris, software teams ship faster when their tools share one memory instead of three silos. New engineers ramp in days because precedent is searchable, not oral history.
Because writes land locally first and synchronize later, flaky connections never block the work.
- Built for Paris: la French Tech’s engineering density.
- 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
Cursor Memory in Paris, without the trade-offs.
01
Cross-session continuity
Context written yesterday is briefed today — across chats, worktrees, and machines.
02
Cross-tool parity
The same memory feeds Claude Code and Codex CLI, keeping mixed-tool teams consistent.
03
Ranked retrieval
Agents pull relevant memories by topic and recency instead of swallowing the full history.
04
Access control
Per-project credentials ensure contractors and new hires see exactly the projects they should.
05
Web portal
Browse, pin, edit, and audit the same memories from a clean dashboard — no lock-in to one editor.
06
Complements .cursor/rules
Keep tactical rules in-repo; move durable decisions and rationale into shared memory both humans and agents query.
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.
How does Cursor connect to it?
Through the Model Context Protocol: add the memhub entry to your MCP configuration once (the connect command does it for you) and restart Cursor.
Does MemHub replace .cursorrules?
No. Rules remain the right place for always-on steering. MemHub holds versioned team knowledge — decisions, constraints, postmortems — that rules files were never shaped to carry.
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
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.
Codex CLI Memory
Persistent context for Codex CLI — personal today, shared tomorrow.
Cross-Agent Memory
One memory behind Claude Code, Cursor, Codex CLI, and Antigravity.
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