Standardize on idempotent write endpoints
Source: architecture.md
Antigravity & Gemini Memory · shared project memory
The agentic future is multi-model. Whatever Google ships next, your project memory stays put — versioned, permission-checked, and reachable through standard MCP rather than a vendor format.
Google Antigravity and Gemini CLI bring Gemini-grade reasoning to your repository — with the same amnesia as every other agent. MemHub supplies the durable memory layer over MCP that makes their output consistent week over week.
Free Community tier. Self-hosted or hosted. No external embedding API required.
context/main
memories 41
pinned 6
contributors 9
BRIEFING FOR NEW SESSION
Source: architecture.md
Source: pull request #214
Source: auth/session.ts
LOCAL FIT
Across the Dominican Republic, software teams ship faster when their tools share one memory instead of three silos. Mixed toolchains stop fragmenting knowledge across vendor-specific stores.
Teams operating under Law 172-13 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
Per-project keys with roles and instant revocation.
Antigravity and Gemini CLI consume Model Context Protocol servers; MemHub plugs straight in.
The same memory serves Gemini, Claude, GPT, and local models without duplication.
Sessions receive deltas since their last sequence — never a stale dump.
Authorship and source links keep agent context accountable.
Local SQLite queues writes through connectivity gaps and syncs safely after.
No feature-matrix gymnastics — just what changes the week you adopt MemHub.
| Status quo | With MemHub |
|---|---|
| Context lives in heads and DMs | Memory is structured, shared, and searchable |
| Every agent re-learns the repo | Sessions open pre-briefed with only what changed |
| Rules files cap out at ~2k tokens | Unbounded versioned history stays one query away |
One command injects configuration for Claude Code, Cursor, Codex CLI, Google Antigravity, Windsurf, Cline, or any JSON MCP client.
$ npm install --global @simplexlat/memhub
$ memhub login
✓ project resolved · context ready · memory synchronized
Gemini CLI reads the same JSON MCP config shape; the connect command writes it for you, or select it as an “other” JSON client.
Yes — Antigravity is built around the Model Context Protocol. Point its MCP configuration at the memhub proxy and restart.
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.
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.
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.
THE NEXT SESSION STARTS HERE