01
decision2m
Usar bloqueos consultivos en PostgreSQL
Fuente: Nelson · architecture.md
AI AGENT MEMORY · AVAILABLE NOW
AI Agent Memory for engineering teams
Stop losing hours re-teaching AI agents your codebase. MemHub turns every decision and fix into persistent AI agent memory briefed in 2 minutes — free for one project, no external API, works offline.
N
Nelson · Founder, MemHub at Simplex.lat
Simplex.lat · Quito, Ecuador ·
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/ai-agent-memory
synchronizedcontext/main
memorias 41
reglas fijadas 6
colaboradores 9
BRIEFING FOR NEW SESSION
What changed since your last pull
02
pattern18m
Los errores de API siguen RFC 9457
Fuente: Maya · PR #184
03
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.
01
You keep coding
Decisions auto-captured where you work — terminal, PR, editor. No extra docs, no context-switching.
02
MemHub does the plumbing
Local SQLite outbox first, then project-scoped sync with provenance (who, when, why). Works offline.
03
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
AI Agent Memory: specific benefits for your team
01
New session, same context
Stop re-explaining decisions. Memories survive restarts and device switches via local outbox + cloud sync — next session starts briefed.
02
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.
03
Works offline, syncs later
Entries commit locally first. On a plane or flaky VPN, you keep working; sync happens when you are back.
04
Trust what you read
Every memory carries author, source file/PR, and version history — verify before an agent acts on it. No folklore.
05
One proxy, every agent
Single stdio proxy for any MCP client — Claude Code, Cursor, Codex, Windsurf. No workflow change.
06
Find it in seconds
Full-text search today, optional semantic via Ollama/pgvector tomorrow. No external API required to start.
The honest comparison.
No feature-matrix gymnastics — just what changes the week you adopt MemHub.
| 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.
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 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. 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 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. 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
AI Agent Memory across United StatesAI Agent Memory across CanadaAI Agent Memory across United KingdomAI Agent Memory across IrelandAI Agent Memory across GermanyAI Agent Memory across FranceAI Agent Memory across SpainAI Agent Memory across PortugalAI Agent Memory across ItalyAI Agent Memory across NetherlandsAI Agent Memory across BelgiumAI Agent Memory across SwitzerlandAI Agent Memory across AustriaAI Agent Memory across SwedenAI Agent Memory across NorwayAI Agent Memory across DenmarkAI Agent Memory across FinlandAI Agent Memory across EstoniaAI Agent Memory across PolandAI Agent Memory across CzechiaAI Agent Memory across RomaniaAI Agent Memory across MexicoAI Agent Memory across BrazilAI Agent Memory across ArgentinaAI Agent Memory across ChileAI Agent Memory across ColombiaAI Agent Memory across PeruAI Agent Memory across UruguayAI Agent Memory across Costa RicaAI Agent Memory across EcuadorAI Agent Memory across PanamaAI Agent Memory across GuatemalaAI Agent Memory across El SalvadorAI Agent Memory across Dominican RepublicAI Agent Memory across ParaguayAI Agent Memory across AustraliaAI Agent Memory across New ZealandAI Agent Memory across JapanAI Agent Memory across South KoreaAI Agent Memory across SingaporeAI Agent Memory across IndiaAI Agent Memory across United Arab EmiratesAI Agent Memory across IsraelAI Agent Memory across South AfricaAI Agent Memory across NigeriaAI Agent Memory across KenyaAI Agent Memory across PhilippinesAI Agent Memory across VietnamAI Agent Memory across England
US STATES · Regional Deployments
AI Agent Memory in CaliforniaAI Agent Memory in TexasAI Agent Memory in New York StateAI Agent Memory in FloridaAI Agent Memory in Washington StateAI Agent Memory in MassachusettsAI Agent Memory in ColoradoAI Agent Memory in IllinoisAI Agent Memory in GeorgiaAI Agent Memory in ArizonaAI Agent Memory in North CarolinaAI Agent Memory in UtahAI Agent Memory in OregonAI Agent Memory in VirginiaAI Agent Memory in New JerseyAI Agent Memory in PennsylvaniaAI Agent Memory in MichiganAI Agent Memory in TennesseeAI Agent Memory in MinnesotaAI Agent Memory in OhioAI Agent Memory in NevadaAI Agent Memory in Maryland
PROVINCES & REGIONS · Regional Deployments
CITIES & TECH HUBS · Regional Deployments
AI Agent Memory in San FranciscoAI Agent Memory in New York CityAI Agent Memory in AustinAI Agent Memory in SeattleAI Agent Memory in BostonAI Agent Memory in ChicagoAI Agent Memory in DenverAI Agent Memory in Los AngelesAI Agent Memory in AtlantaAI Agent Memory in MiamiAI Agent Memory in DallasAI Agent Memory in San DiegoAI Agent Memory in PortlandAI Agent Memory in PhoenixAI Agent Memory in PhiladelphiaAI Agent Memory in NashvilleAI Agent Memory in MinneapolisAI Agent Memory in RaleighAI Agent Memory in Salt Lake CityAI Agent Memory in DetroitAI Agent Memory in TorontoAI Agent Memory in VancouverAI Agent Memory in MontrealAI Agent Memory in LondonAI Agent Memory in ManchesterAI Agent Memory in EdinburghAI Agent Memory in DublinAI Agent Memory in BerlinAI Agent Memory in MunichAI Agent Memory in HamburgAI Agent Memory in ZurichAI Agent Memory in GenevaAI Agent Memory in ViennaAI Agent Memory in ParisAI Agent Memory in LyonAI Agent Memory in AmsterdamAI Agent Memory in RotterdamAI Agent Memory in BrusselsAI Agent Memory in MadridAI Agent Memory in BarcelonaAI Agent Memory in ValenciaAI Agent Memory in MálagaAI Agent Memory in SevilleAI Agent Memory in BilbaoAI Agent Memory in ZaragozaAI Agent Memory in MurciaAI Agent Memory in Palma de MallorcaAI Agent Memory in Las Palmas de Gran CanariaAI Agent Memory in LisbonAI Agent Memory in PortoAI Agent Memory in MilanAI Agent Memory in RomeAI Agent Memory in StockholmAI Agent Memory in CopenhagenAI Agent Memory in OsloAI Agent Memory in HelsinkiAI Agent Memory in TallinnAI Agent Memory in WarsawAI Agent Memory in KrakówAI Agent Memory in PragueAI Agent Memory in BucharestAI Agent Memory in Mexico CityAI Agent Memory in GuadalajaraAI Agent Memory in MonterreyAI Agent Memory in QuerétaroAI Agent Memory in PueblaAI Agent Memory in TijuanaAI Agent Memory in MéridaAI Agent Memory in São PauloAI Agent Memory in Rio de JaneiroAI Agent Memory in Buenos AiresAI Agent Memory in CórdobaAI Agent Memory in RosarioAI Agent Memory in MendozaAI Agent Memory in SantiagoAI Agent Memory in ValparaísoAI Agent Memory in ConcepciónAI Agent Memory in BogotáAI Agent Memory in MedellínAI Agent Memory in CaliAI Agent Memory in BarranquillaAI Agent Memory in QuitoAI Agent Memory in GuayaquilAI Agent Memory in LimaAI Agent Memory in ArequipaAI Agent Memory in MontevideoAI Agent Memory in AsunciónAI Agent Memory in San JoséAI Agent Memory in Panama CityAI Agent Memory in Guatemala CityAI Agent Memory in San SalvadorAI Agent Memory in Santo DomingoAI Agent Memory in SydneyAI Agent Memory in MelbourneAI Agent Memory in BrisbaneAI Agent Memory in PerthAI Agent Memory in AucklandAI Agent Memory in TokyoAI Agent Memory in OsakaAI Agent Memory in SeoulAI Agent Memory in SingaporeAI Agent Memory in BengaluruAI Agent Memory in HyderabadAI Agent Memory in PuneAI Agent Memory in MumbaiAI Agent Memory in Delhi NCRAI Agent Memory in DubaiAI Agent Memory in Tel AvivAI Agent Memory in ManilaAI Agent Memory in Ho Chi Minh CityAI Agent Memory in Hong KongAI Agent Memory in TaipeiAI Agent Memory in Kuala LumpurAI Agent Memory in JakartaAI Agent Memory in BangkokAI Agent Memory in JohannesburgAI Agent Memory in Cape TownAI Agent Memory in LagosAI Agent Memory in Nairobi
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 requiredGuided demo20 min · see your repo rememberedSelf-host it myselfDocker + pgvector · you own the data
THE NEXT SESSION STARTS HERE — 2 MIN SETUP