# Giljo HQ

Giljo HQ keeps product context available to connected coding agents and helps organize project missions. Use it when you want separate agent sessions to share accumulated project knowledge.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: giljoai
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/giljoai/giljo-hq
- Updated: 2026-10-22
- HTML: https://affpapa.org/en/nevibecode/mcp/giljo-hq

## What it does

Store a product description, its architecture, tech stack, and testing strategy in Giljo HQ. The server builds a project kickoff prompt from that context and the project brief. Once a project finishes, it adds an entry to 360 Memory for later work.

Giljo HQ connects over MCP and coordinates multi-agent workflows. It does not generate code or make calls to AI models; your connected coding tool handles the reasoning and implementation with your own subscription. That distinction matters: Giljo HQ supplies context, not an AI coding model.

A local setup requires Python 3.12+, PostgreSQL 18+, and Node.js 22.23.3+. To connect it to Codex over HTTP, run `codex mcp add giljo-hq --url https://app.giljo.ai/mcp`.

## Requirements
- Remote server: `https://app.giljo.ai/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http hq https://app.giljo.ai/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add giljo-hq --url https://app.giljo.ai/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "giljo-hq": {
            "url": "https://app.giljo.ai/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "giljo-hq": {
            "type": "http",
            "url": "https://app.giljo.ai/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http giljo-hq https://app.giljo.ai/mcp
```

## When to use it
- keep product architecture and stack details in shared context
- build a kickoff prompt from a project brief
- carry completed-project knowledge into later work
- track agent mission progress

## Example prompts
- Build a kickoff prompt for this project from the saved product context.
- Create a project mission and prepare it for the agents.
- Find the product context relevant to this project.

## Similar
- [Atono](https://affpapa.org/en/nevibecode/mcp/atono.md) — MCP server
- [FairMind Project Context](https://affpapa.org/en/nevibecode/mcp/fairmind-project-context.md) — MCP server
- [pm](https://affpapa.org/en/nevibecode/skills/pm.md) — skill · ★ 23912
- [Asana Automation](https://affpapa.org/en/nevibecode/skills/asana-automation.md) — skill · 6900 installs
- [event-planning-timeline](https://affpapa.org/en/nevibecode/skills/event-planning-timeline.md) — skill · 4900 installs
- [Monday.com Automation](https://affpapa.org/en/nevibecode/skills/mondaycom-automation.md) — skill · 4600 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md