Use PostgreSQL advisory locks
Source: Nelson · architecture.md
Every agent — Claude Code, Cursor, Codex — opens already briefed on the decisions, fixes, and constraints your team already made. No handoff docs. No repeated questions.
Free for 1 project. Upgrade or self-host with Docker when you grow.
context/main
memories 38
pinned rules 7
contributors 13
BRIEFING FOR NEW SESSION
Source: Nelson · architecture.md
Source: Maya · pull request #184
Source: Codex CLI · auth/session.ts
THE MECHANISM
Less onboarding, fewer regressions, faster shipping — because context stops evaporating when the terminal closes.
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.
DEVELOPER FEEDBACK
Synced across Claude Code, Cursor & terminal
"Honestly saved me from explaining to Cursor 5 times a day why we use Drizzle instead of Prisma. You open the chat and it already knows everything."
Alex M.
Fullstack Dev
One command connects Claude Code, Cursor, Codex, Windsurf, Cline & any MCP client. No new editor, no chat app, no polling loop.
memhub save --type decision "Usar bloqueos consultivos en Postgres" -m "Evita colisiones concurrentes en el outbox"Start free locally with your favorite AI coding agents. Enable cloud sync when collaborating across your engineering team.
No credit card required to start
Cancel anytime in 1 click
2-minute instant setup
Community
$0
Free forever
memhub rules)For individual developers
Team
$29 / month
Everything in Community, plus:
Instant activation · Cancel anytime in 1 click
No. agentmemory remains the fast local engine. MemHub adds project synchronization, access control, audit, and a shared team portal.
Nothing interrupts the work. Writes commit to the local SQLite outbox and synchronize when the service returns.
Yes. The repository includes Docker and Easypanel configuration for PostgreSQL 16 and pgvector.
No. Start with full-text search, connect Ollama locally, or configure a supported remote provider later.
THE NEXT SESSION STARTS HERE — 2 MIN SETUP
Join engineering teams eliminating re-work and supercharging AI agents with persistent shared memory.