01
decision
Standardize on idempotent write endpoints
Source: architecture.md
Claude Code Memory in · shared project memory
Claude Code Memory in Miami
When a Claude Code session ends, its context usually dies with it. MemHub persists what mattered — pinned invariants, rejected approaches, environment quirks — and re-briefs the next session automatically, in this checkout or any other.
Auto-memory helps a single developer on a single machine. Teams need more: shared recall across laptops, provenance for every note, and access control per project. MemHub provides exactly that over MCP, which Claude Code speaks natively.
Create your shared memory
Free Community tier. Self-hosted or hosted. No external embedding API required.
acme/claude-code-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 Miami engineering teams choose MemHub
In Miami, 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 Miami: the East Coast bridge to Latin American markets.
- 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
Claude Code Memory in Miami, without the trade-offs.
01
Session briefing
Each new session pulls only what changed since its last sequence — no repeated boilerplate in your context window.
02
Team recall
What one developer teaches Claude Code, every teammate’s Claude Code knows on the next run.
03
Pinned invariants
Pin the non-negotiables so they outrank newer, noisier memories during retrieval.
04
Local-first safety net
If the service is unreachable, the proxy keeps serving and queueing locally until sync resumes.
05
One-command setup
`memhub connect` injects the correct Claude Code configuration without hand-editing JSON.
06
Beyond CLAUDE.md
Structured memories with types, topics, and versions instead of one ever-growing markdown file.
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.
Will my context window fill up with old memories?
No. Briefings are incremental — sessions receive the delta since their last known sequence, and retrieval is ranked rather than bulk-dumped.
Does this replace Claude Code auto memory?
No. Auto memory stays useful for personal preferences. MemHub adds the shared, project-scoped layer: cross-machine recall, provenance, and team-wide search.
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
Claude Code Memory in CaliforniaClaude Code Memory in TexasClaude Code Memory in New York StateClaude Code Memory in FloridaClaude Code Memory in Washington StateClaude Code Memory in MassachusettsClaude Code Memory in ColoradoClaude Code Memory in IllinoisClaude Code Memory in GeorgiaClaude Code Memory in ArizonaClaude Code Memory in North CarolinaClaude Code Memory in Utah
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.
Cursor Memory
Carry Cursor context across sessions, machines, and teammates.
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