Standardize on idempotent write endpoints
Source: architecture.md
Claude Code Memory across · shared project memory — local-first · offline-ready
Stop babysitting a 2,000-token CLAUDE.md. MemHub gives Claude Code real memory — decisions and fixes persist as structured, versioned memories the whole team shares. Setup in one command.
Claude Code sessions die with their context. MemHub doesn’t — pinned invariants, rejected approaches, env quirks are re-briefed to the next session automatically, any checkout.
Free for 1 project · No card · Self-host or we host · No external API
context/main
memories 41
pinned 6
contributors 9
BRIEFING FOR NEW SESSION
Source: architecture.md
Source: pull request #214
Source: auth/session.ts
WHY IT MATTERS HERE
Across South Africa, software teams ship faster when their tools share one memory instead of three silos. Distributed squads stay aligned because every session opens with the same briefing.
Teams operating under POPIA can point at a concrete architecture instead of promises.
UNIVERSAL COMPATIBILITY
If it speaks MCP or reads a JSON config, MemHub plugs in. One command wires the majors; everything else joins as a generic client.
WHAT YOU GET
Structured memories with types/topics/versions — not one markdown file growing forever past 2k tokens.
Each session gets only the delta since its last sequence — no repeated boilerplate in your context window.
What one dev tells Claude Code, every teammate’s Claude Code knows on next run. No forwarding needed.
Pin invariants so they outrank newer, noisier memories — agents respect past calls.
Local-first outbox queues writes when offline — syncs safely after. Keep coding.
memhub connect writes your Claude Code JSON — no hand-edits, no docs to skim.
No feature-matrix gymnastics — just what changes the week you adopt MemHub.
| Without MemHub | With MemHub |
|---|---|
| Context lives in heads and DMs → onboarding takes days | Structured, searchable memory → new dev/agent productive in minutes |
| Every agent re-learns the repo from scratch | Sessions open pre-briefed with only what changed — zero re-explaining |
| Rules files cap out at ~2k tokens | Unbounded versioned history stays one query away — never cap again |
| Decisions re-litigated, bugs re-introduced | Pinned invariants prevent regressions — agents respect past calls |
One command for Claude Code, Cursor, Codex, Windsurf, Cline or any MCP client. No new editor. Setup in 2 minutes, works offline.
$ npm install --global @simplexlat/memhub
$ memhub login
✓ project resolved · context ready · memory synchronized
No. Auto memory stays useful for personal preferences. MemHub adds the shared, project-scoped layer: cross-machine recall, provenance, and team-wide search.
No. Briefings are incremental — sessions receive the delta since their last known sequence, and retrieval is ranked rather than bulk-dumped.
Nothing interrupts the work. Writes commit to the local SQLite outbox and synchronize automatically when the shared service is reachable again.
Yes — the local engine works fully offline, and the self-hosted stack keeps even the shared layer on your own PostgreSQL.
A Community tier is free, and the Team plan adds multi-project contexts, seats, and higher synchronization limits. Self-hosting is unlimited.
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.
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.
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 — 2 MIN SETUP