Self-Hosted AI Memory in · shared project memory

Self-Hosted AI Memory in Las Palmas de Gran Canaria

Regulated teams can’t ship code context to a black box. MemHub is open about its stack: Docker Compose or Easypanel, PostgreSQL 16, pgvector, and migrations you run — the memory layer lives wherever your compliance boundary does.

Self-hosting an AI memory layer should mean more than downloading a tarball. MemHub brings row-level security, restricted runtime roles, audit trails, and backup-friendly schemas — production posture from day one.

Create your shared memory

Free Community tier. Self-hosted or hosted. No external embedding API required.

acme/self-hosted-ai-memory

synchronized

context/main

memories 41

pinned 6

contributors 9

BRIEFING FOR NEW SESSION

What changed since your last pull

3 new

decision

Standardize on idempotent write endpoints

Source: architecture.md

pattern

Repository layer owns every database transaction

Source: pull request #214

bugfix

Refresh tokens rotate atomically under load

Source: auth/session.ts

Claude Code

Cursor

Windsurf

LOCAL FIT

Why Las Palmas de Gran Canaria engineering teams choose MemHub

In Las Palmas de Gran Canaria, software teams ship faster when their tools share one memory instead of three silos. Mixed toolchains stop fragmenting knowledge across vendor-specific stores.

Every entry carries authorship and version history, which keeps both humans and auditors comfortable.

Built for Las Palmas de Gran Canaria: a growing digital-nomad and remote-work hub.
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.

Start freeFree workspace in 2 minutes Guided demo20 min with the founding team Self-host it myselfDocker + PostgreSQL on your infra

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

Self-Hosted AI Memory in Las Palmas de Gran Canaria, without the trade-offs.

Auditable by default

Administrative actions append to an audit table with actor, reason, and metadata.

Optional embeddings

Start with pure full-text search; enable Ollama locally if you want vectors without external APIs.

Standard backups

Everything important is plain PostgreSQL — pg_dump fits your existing continuity plan.

Same protocol, anywhere

Hosted and self-hosted speak identical MCP and REST interfaces, so moving between them is configuration, not code.

Your infrastructure

Single Docker Compose file or Easypanel template; the database never phones home.

Defense in depth

RLS policies, transaction-local tenant context, and NOBYPASSRLS application roles built into migrations.

The honest comparison.

No feature-matrix gymnastics — just what changes the week you adopt MemHub.

Start free Talk to the team

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.

Start free Talk to the team

repository terminal

$ npm install --global @simplexlat/memhub

$ memhub login

✓ project resolved · context ready · memory synchronized

Questions, answered straight.

What do I need to self-host?

A host with Docker (or Easypanel) and a PostgreSQL 16 database with the pgvector extension. Migrations and seeds are one command each.

Is the hosted option still private?

Hosted memory is isolated per organization with row-level security, encrypted transport, and hashed credentials — but self-hosting remains the strongest guarantee because no third party operates the storage.

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

Self-Hosted AI Memory in Madrid Self-Hosted AI Memory in Barcelona Self-Hosted AI Memory in Valencia Self-Hosted AI Memory in Málaga Self-Hosted AI Memory in Seville Self-Hosted AI Memory in Bilbao Self-Hosted AI Memory in Zaragoza Self-Hosted AI Memory in Murcia Self-Hosted AI Memory in Palma de Mallorca Self-Hosted AI Memory in San Francisco Self-Hosted AI Memory in New York City Self-Hosted AI 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.

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.

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

Stop rebuilding context.
Start building the product.

Create workspace