English Français العربية

gjalla

Official registry AI and agents

Self-curating shared memory that keeps your agents working like a high-performing team

Website

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

PYPI package gjalla
Claude Code 
claude mcp add gjalla -e 'GJALLA_API_KEY=<your gjalla_api_key>' -- uvx gjalla==0.10.0 mcp serve
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "gjalla": {
            "command": "uvx",
            "args": [
                "gjalla==0.10.0",
                "mcp",
                "serve"
            ],
            "env": {
                "GJALLA_API_KEY": "<your gjalla_api_key>"
            }
        }
    }
}

Environment variables

  • GJALLA_API_KEY secret Your gjalla API key. Required for Startup and Custom tiers (MCP/CLI agent integration). Get one at https://gjalla.io.

Frequently asked questions

What is gjalla?

Self-curating shared memory that keeps your agents working like a high-performing team

How do I install gjalla?

It runs on your machine. In Claude Code: claude mcp add gjalla -e 'GJALLA_API_KEY=<your gjalla_api_key>' -- uvx gjalla==0.10.0 mcp serve. For other clients, paste the JSON configuration from this page into their MCP settings.

Does gjalla need an API key?

Yes. It expects GJALLA_API_KEY, which you set in its configuration.

Who maintains gjalla?

It is published by io.gjalla. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.