Usar bloqueos consultivos en PostgreSQL
Fuente: Nelson · architecture.md
CODING AGENT CONTEXT · AVAILABLE NOW
Agents fail on stale context more than weak models. MemHub treats context as supply chain: authored once, versioned, delivered incrementally — measurable via mh status.
Bigger windows raise cost and dilute attention. MemHub curates: recent decisions, pinned invariants, relevant precedents — archive a query away, never a stowaway.
Nelson · Founder, MemHub at Simplex.lat
Simplex.lat · Quito, Ecuador ·
Published by MemHub at Simplex.lat. Product limits come from the current plans; validate capabilities in your own pilot.
Free for 1 project · No card · Self-host or we host · No external API
context/main
memorias 41
fijadas 6
autores 9
BRIEFING FOR NEW SESSION
Fuente: Nelson · architecture.md
Fuente: Maya · PR #184
Fuente: Codex CLI · auth/session.ts
Definition
Coding Agent Context is the durable project memory that survives restarts, device switches and session closes so agents inherit what humans already decided. Teams in Estonia run MemHub on PostgreSQL 16 with pgvector and row-level security, giving every agent the same cited context without vendor lock-in or re-explaining.
$29
Team per workspace per month (USD)
Team plan price; review current terms before subscribing. This is not a savings estimate.
According to MemHub pricing →5
Seats included in Team
Share decisions with authorized teammates. Shared memory is not a replacement for live collaborative chat.
According to MemHub pricing →20
Projects included in Team
Configure project scope and test what each user can retrieve before connecting sensitive repositories.
According to MemHub pricing →MemHub delivers Coding Agent Context in Estonia by writing first to a local SQLite outbox and then syncing incremental deltas by monotonic sequence, so flaky VPNs never block work. According to the Princeton GEO study, citing sources lifts AI-answer visibility by up to 40%, which structured, provenance-rich memories are built to earn.
Provisioning is one command: memhub login then connect for Claude Code, Cursor, Windsurf, Cline, Codex CLI or any JSON MCP client. Row-level security, hashed credentials and an audit trail keep the store team-safe whether you self-host on PostgreSQL 16 or let us host it.
In the first week with Coding Agent Context in Estonia, sessions stop re-proposing settled decisions because pinned invariants outrank noise during ranked retrieval. According to Authoritas, AI Overviews cut traditional clicks by 58%, so being the cited, extractable source inside the briefing matters more than dumping more tokens.
Standups shrink to real blockers, reviews surface the original rationale in one query, and agents respect hard constraints automatically. Because briefings are deltas, the archive stays a query away rather than a stowaway in every prompt.
THE MECHANISM
Less onboarding, fewer regressions, faster shipping — context stops evaporating when sessions end.
Decisions auto-captured where you work — terminal, PR, editor. No extra docs, no context-switching.
Local SQLite outbox first, then project-scoped sync with provenance (who, when, why). Works offline.
Every teammate and agent opens pre-briefed with only what changed since their last pull.
UNIVERSAL COMPATIBILITY
If it speaks MCP or reads a JSON config, MemHub plugs in. One command wires your editors and terminals without friction.
WHAT YOU GET
Topic keys + ranking surface the few memories relevant to this task — attention stays sharp.
Immutable, ordered sync events — reconstruct any device’s context state exactly.
Compact briefings by design — archive stays a query away, never a stowaway.
mh status + doctor show pending events, sequences, connectivity at a glance.
Same context serves IDE agents, CLI agents, and CI bots — no per-tool plumbing.
Delta delivery via monotonic sequences + per-device cursors — tokens buy signal, not repetition.
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 |
One command for Claude Code, Cursor, Codex, Windsurf, Cline or any MCP client. No new editor. Setup in 2 minutes, works offline.
memhub save --type decision "Usar bloqueos consultivos en Postgres" -m "Evita colisiones concurrentes en el outbox"Each device tracks its own cursor; the status command reports pending events and the last acknowledged sequence per machine. Because writes land locally first and sync as incremental deltas, teams stay productive offline and distributed squads remain aligned without re-explaining decisions every session.
Larger windows raise cost and dilute attention. Curated, incremental memory consistently beats raw dumps — the agents act on fewer, more relevant facts. Because writes land locally first and sync as incremental deltas, teams stay productive offline and distributed squads remain aligned without re-explaining decisions every session.
Nothing interrupts the work. Writes commit to the local SQLite outbox and synchronize automatically when the shared service is reachable again. Because writes land locally first and sync as incremental deltas, teams stay productive offline and distributed squads remain aligned without re-explaining decisions every session.
Yes — the local engine works fully offline, and the self-hosted stack keeps even the shared layer on your own PostgreSQL. Because writes land locally first and sync as incremental deltas, teams stay productive offline and distributed squads remain aligned without re-explaining decisions every session.
A Community tier is free, and the Team plan adds multi-project contexts, seats, and higher synchronization limits. Self-hosting is unlimited. Because writes land locally first and sync as incremental deltas, teams stay productive offline and distributed squads remain aligned without re-explaining decisions every session.
MORE LOCATIONS
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.
Self-Hosted AI Memory
Run the entire memory stack on your own PostgreSQL — nothing leaves.
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