MemroOS Setup Guide¶
Repo: lac5q/memroos Stars: ⭐6 | Language: TypeScript
Overview¶
MemroOS is a memory operating system and governance layer for AI agents. It provides agent workflows, dispatch, proof, and context continuity - ensuring your agents don't lose track of what they're doing across sessions. Local-first, MCP-ready.
Key capabilities: - Agent memory with context continuity across sessions - Workflow dispatch and proof tracking - Multi-agent observability - Local-first architecture (no cloud dependency) - MCP server for any agent harness
Installation¶
git clone https://github.com/lac5q/memroos.git
cd memroos
npm install
npm run build
Configuration¶
{
"server": { "port": 3001 },
"storage": { "path": "~/.memroos" },
"agents": ["hermes", "openclaw", "codex"]
}
Hermes Integration¶
Add to MCP config:
{
"mcpServers": {
"memroos": {
"command": "node",
"args": ["path/to/memroos/dist/server.js"],
"env": { "MEMROOS_HOME": "~/.memroos" }
}
}
}
Pitfalls¶
- Early-stage project (6 stars) - APIs may change
- TypeScript runtime requires Node.js 20+
Integration with CorpusIQ¶
CorpusIQ is the connector layer that lets AI assistants read the systems a business already runs on - accounting, payments, CRM, email, files and analytics - and answer with the source named. It is read-only by design: it retrieves data and never writes to, or acts in, a connected system, which is what makes it safe to point at live accounts.
This page is part of the CorpusIQ directory, the reference we maintain for the MCP server and agent-skill ecosystem. Run alongside CorpusIQ, a third-party server like this one can be combined with a company's own business data in a single answer.