01
decision
Standardize on idempotent write endpoints
Source: architecture.md
AI Agent Memory across · shared project memory — local-first · offline-ready
AI Agent Memory across Ireland
Sprints end, context evaporates, bugs return. MemHub keeps what mattered — why that abstraction exists, which retry won — searchable and auto-briefed to the next session.
New hires and new agents ramp in days, not weeks. Every session — Claude Code, Cursor, Codex — opens pre-briefed with only what changed since last pull. Local-first, self-hostable.
Start free — get briefed in 2 min
Free for 1 project · No card · Self-host or we host · No external API
acme/ai-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
WHY IT MATTERS HERE
Why Ireland engineering teams choose MemHub
Across Ireland, 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.
Teams operating under GDPR can point at a concrete architecture instead of promises.
- Built for Ireland: an EU headquarters for many global engineering organizations.
- Data residency you control — run MemHub on infrastructure inside Ireland or let us host it.
- 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
AI Agent Memory across Ireland, without the trade-offs.
01
Trust what you read
Every memory carries author, source file/PR, and version history — verify before an agent acts on it. No folklore.
02
One proxy, every agent
Single stdio proxy for any MCP client — Claude Code, Cursor, Codex, Windsurf. No workflow change.
03
Find it in seconds
Full-text search today, optional semantic via Ollama/pgvector tomorrow. No external API required to start.
04
New session, same context
Stop re-explaining decisions. Memories survive restarts and device switches via local outbox + cloud sync — next session starts briefed.
05
Only your project sees it
Org/project boundaries enforced at the API layer. Agents read only what they are authorized to — contractors see one repo, not all.
06
Works offline, syncs later
Entries commit locally first. On a plane or flaky VPN, you keep working; sync happens when you are back.
The honest comparison.
No feature-matrix gymnastics — just what changes the week you adopt MemHub.
| Without MemHub | With MemHub |
|---|---|
| Context lives in heads and DMs → onboarding takes days | Structured, searchable memory → new dev/agent productive in minutes |
| Every agent re-learns the repo from scratch | Sessions open pre-briefed with only what changed — zero re-explaining |
| Rules files cap out at ~2k tokens | Unbounded versioned history stays one query away — never cap again |
| Decisions re-litigated, bugs re-introduced | Pinned 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.
How is it different from a rules file like CLAUDE.md?
Rules files hold short-lived instructions inside one repo and one tool. A memory layer holds versioned, searchable, team-wide knowledge that travels across repositories, tools, and months of history.
What is AI agent memory?
It is a persistent store of decisions, constraints, fixes, and preferences that AI coding agents read at the start of every session instead of rediscovering — or hallucinating — them from scratch.
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
AI Agent Memory across the United StatesAI Agent Memory across CanadaAI Agent Memory across the United KingdomAI Agent Memory across GermanyAI Agent Memory across FranceAI Agent Memory across SpainAI Agent Memory across PortugalAI Agent Memory across ItalyAI Agent Memory across the NetherlandsAI Agent Memory across BelgiumAI Agent Memory across SwitzerlandAI Agent Memory across Austria
EXPLORE OTHER USE CASES
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.
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 — 2 MIN SETUP