Codex CLI Memory in · shared project memory — local-first · offline-ready

Codex CLI Memory in San Francisco

Fix it once, remember forever. Every constraint and workaround Codex learns becomes team-wide recall in seconds — works on the plane, syncs later.

Stop starting Codex CLI with fresh eyes. MemHub gives Codex persistent context — decisions committed this morning brief tonight’s session automatically. Shell closes, memory doesn’t.

Start free — get briefed in 2 min

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

acme/codex-cli-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 San Francisco engineering teams choose MemHub

In San Francisco, 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 San Francisco: the Bay Area AI engineering scene.
  • 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

Codex CLI Memory in San Francisco, without the trade-offs.

01

Keep working on the plane

SQLite outbox queues writes offline and flushes safely later — no work hostage to VPN.

02

Verify before you act

Every entry has author, source, and version — trust but check before the agent runs.

03

Wired in one line

memhub connect --ide codex + mh login — configured securely in seconds.

04

Shell closes, memory doesn’t

Each Codex invocation inherits what changed since last pull — incremental briefing, not amnesia.

05

Take it to any machine

Memory follows you across laptops/containers — not just the current checkout.

06

One insight, whole team

A fix found on your box is on every teammate’s next Codex session — automatically.

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.

Where does my data live?

Locally first — the outbox database sits in ~/.memhub. Cloud copies go to your MemHub organization’s PostgreSQL instance, or to your own hardware if you self-host.

Does Codex CLI support MCP memory?

Yes. Codex CLI consumes MCP servers, and MemHub’s proxy exposes memory, search, and sync status over stdio with no extra daemons.

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