SELF-HOSTED AI MEMORY · AVAILABLE NOW

Self-Hosted AI Memory for engineering teams

Stop shipping code context to a black box. MemHub is self-hosted AI memory on your PostgreSQL 16 + pgvector — Docker or Easypanel, you run the migrations, you own the data.

Nelson · Founder, MemHub at Simplex.lat

Simplex.lat · Quito, Ecuador · Last updated: August 15, 2026

Written and verified by Nelson at Simplex.lat (Quito, Ecuador) — sources checked August 2026.

Local-first · Offline readySincronización multiagenteSetup en 2 min

Start free — get briefed in 2 min

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

acme/self-hosted-ai-memory

synchronized

context/main

memorias 41

reglas fijadas 6

colaboradores 9

BRIEFING FOR NEW SESSION

What changed since your last pull

3 new

decision2m

Usar bloqueos consultivos en PostgreSQL

Fuente: Nelson · architecture.md

pattern18m

Los errores de API siguen RFC 9457

Fuente: Maya · PR #184

bugfix1h

Los refresh tokens rotan atómicamente

Fuente: Codex CLI · auth/session.ts

Claude Code

Cursor

Codex CLI

THE MECHANISM

Write once. Every session remembers.

Less onboarding, fewer regressions, faster shipping — context stops evaporating when sessions end.

You keep coding

Decisions auto-captured where you work — terminal, PR, editor. No extra docs, no context-switching.

MemHub does the plumbing

Local SQLite outbox first, then project-scoped sync with provenance (who, when, why). Works offline.

Next session starts ahead

Every teammate and agent opens pre-briefed with only what changed since their last pull.

UNIVERSAL COMPATIBILITY

Plugs into any CLI, IDE, or AI coding agent.

If it speaks MCP or reads a JSON config, MemHub plugs in. One command wires your editors and terminals without friction.

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: specific benefits for your team

Stay inside your boundary

One Docker Compose / Easypanel file — database never phones home, data never leaves.

Production posture day one

RLS policies, NOBYPASSRLS roles, transaction-local tenants — in the migrations, not a todo.

Answer the auditor fast

Append-only audit table with actor/reason/metadata — demos that bore the DPO (in a good way).

AI without the API bill

Start with FTS; flip on local Ollama for vectors — no external embedding vendor needed.

Backups you already run

Plain PostgreSQL — pg_dump, replicas, PITR fit your existing continuity plan.

Move without rewriting

Hosted and self-hosted speak identical MCP/REST — switch is config, not code.

The honest comparison.

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

Start free — 2 min Talk to the team

Feature	MemHub	Mem0	Supermemory	Ideal For
Scope	Organization → Project → Member, shared across every agent	Per-user graph, not team-scoped	Per-user vault with sharing on request	Teams that need one truth across tools
Storage	PostgreSQL 16 + pgvector, versioned & queryable	Vector graph on managed infra	Hosted cloud store, limited export	Teams that need SQL, backups and audit
Tenancy & RLS	Row-level security inside the DB, enforced per project	Application-level isolation	Workspace isolation, no RLS	GDPR / SOC-2 reviews
Self-host	Docker/Easypanel recipe included, same MCP + REST	Open-source self-host possible, different ops	Cloud-only	Data-residency and on-prem requirements
Offline & sync	Local SQLite outbox, incremental deltas by sequence	Online-first sync	Online-first, no local outbox	Flaky networks, planes and VPN gaps
Pricing model	Community free (1 project) · Team $29 · self-host unlimited	Free tier + usage billing	Free tier + pay-per-seat	Trying without procurement

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.

Start free — 2 min Talk to the team

memhub-cli · preview

Click tabs to simulateSimulate CLI

$memhub save --type decision "Usar bloqueos consultivos en Postgres" -m "Evita colisiones concurrentes en el outbox"

stdout · [mem_save]12ms

[detect] Contexto resuelto: acme/payments-api

[sqlite] Guardando en outbox local (~/.memhub/outbox.db)...

✓ tipo: decision

✓ título: "Usar bloqueos consultivos en Postgres"

✓ autor: nelson@simplex.lat · git:main (5fc80ea)

[cloud] Sincronizado con MemHub Cloud (org: acme-team)

✓ Registrado con ID: mem_849201_dec

SQLite Outbox + Cloud SyncMCP v1.0

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. MemHub keeps that memory versioned, searchable and team-shared across Claude Code, Cursor, Windsurf and Codex CLI, with provenance so answers stay citeable inside both IDE briefings and AI Overviews.

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. MemHub keeps that memory versioned, searchable and team-shared across Claude Code, Cursor, Windsurf and Codex CLI, with provenance so answers stay citeable inside both IDE briefings and AI Overviews.

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. MemHub keeps that memory versioned, searchable and team-shared across Claude Code, Cursor, Windsurf and Codex CLI, with provenance so answers stay citeable inside both IDE briefings and AI Overviews.

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. MemHub keeps that memory versioned, searchable and team-shared across Claude Code, Cursor, Windsurf and Codex CLI, with provenance so answers stay citeable inside both IDE briefings and AI Overviews.

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. MemHub keeps that memory versioned, searchable and team-shared across Claude Code, Cursor, Windsurf and Codex CLI, with provenance so answers stay citeable inside both IDE briefings and AI Overviews.

COUNTRIES · Regional Deployments

PROVINCES & REGIONS · Regional Deployments

Self-Hosted AI Memory in Ontario Self-Hosted AI Memory in British Columbia Self-Hosted AI Memory in Quebec Self-Hosted AI Memory in Alberta

CITIES & TECH HUBS · Regional Deployments

GUIDES, COMPARISONS & PLAYBOOKS

Mem0 Alternative for Teams — MemHub

Best MCP Memory Servers for Teams (2026)

CLAUDE.md vs Shared Team Memory — When You Need Both

How to Share AI Coding Context Across Your Team

Agent Memory Playbook for Agile Teams (2026)

Mem0 vs MemHub: Team AI Memory Compared Guide

Supermemory vs MemHub: Team AI Memory Compared Guide

Letta vs MemHub: Team AI Memory Compared Guide

Cognee vs MemHub: Team AI Memory Compared Guide

Zep vs MemHub: Team AI Memory Compared Guide

Start free — 2 min1 project free · no card required Guided demo20 min · see your repo remembered Self-host it myselfDocker + pgvector · you own the data

THE NEXT SESSION STARTS HERE — 2 MIN SETUP

Stop rebuilding context.
Start shipping faster.

Create workspace — free