gjalla runs on your own machine — the client starts it, so there is no endpoint to ping. 3 002 installs a week from pypi.
Self-curating shared memory that keeps your agents working like a high-performing team
Nothing serious here today
Today is the operative word: we check gjalla every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp-server -- uvx gjalla{
"mcpServers": {
"mcp-server": {
"command": "uvx",
"args": [
"gjalla"
]
}
}
}[mcp_servers.mcp-server]
command = "uvx"
args = ["gjalla"]{
"mcpServers": {
"mcp-server": {
"command": "uvx",
"args": [
"gjalla"
]
}
}
}{
"servers": {
"mcp-server": {
"type": "stdio",
"command": "uvx",
"args": [
"gjalla"
]
}
}
}Optional settings from the registry entry, left out of the block above:
GJALLA_API_KEY (Your gjalla API key. Required for Startup and Custom tiers (MCP/CLI agent integration). Get one at https://gjalla.io).
Alternatives to gjalla
same job, measured the same wayHosted self-curating shared memory that keeps your agents working like a high-performing team
A living map of all your work that keeps you, your team, and your agents on the same page
Local long-term memory shared by all your AI agents, kept word for word on your own PC.
The second brain your AI agents share. It builds itself from your work and keeps itself current.
Local long-term memory shared by all your AI agents, kept word for word on your own PC.
Shared long-term memory for a team's AI agents. What one agent learns, the others can find.
Shared project memory that keeps teammates and AI agents aligned across sessions.
Your shared chats, calendar, Drive, groups and memory, so a team's agents stay in step.
gjalla — questions
Answers built from our own checks of this server.