gjalla MCP Server

by gjalla Your server? Claim it

local only

gjalla runs on your own machine — the client starts it, so there is no endpoint to ping. 3 685 installs a week from pypi.

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

Installs per day peak 2 146 · avg 658 · -33% w/w

a month agotoday

3 685

Installs / week

pypi · gjalla

—

Stars

on GitHub

—

Last commit

0 releases in 90 days

—

License

language unknown

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 Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add mcp-server -- uvx gjalla

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "mcp-server": {
      "args": [
        "gjalla"
      ],
      "command": "uvx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.mcp-server]
command = "uvx"
args = ["gjalla"]

.cursor/mcp.json

{
  "mcpServers": {
    "mcp-server": {
      "args": [
        "gjalla"
      ],
      "command": "uvx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "mcp-server": {
      "args": [
        "gjalla"
      ],
      "command": "uvx"
    }
  }
}

This one needs environment variables set before it will start: GJALLA_API_KEY (Your gjalla API key. Required for Startup and Custom tiers (MCP/CLI agent integration). Get one at https://gjalla.io.). The author declared them in the registry entry; get the values from the project itself.

Alternatives to gjalla

same job, measured the same way

gjalla

by gjalla

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

answering

Vibsync

by vibsync

One shared brain for your AI coding agents: team memory, agent Q&A, tasks, and file claims.

answering

Repo Memory

by yubinkim444

Shared, git-tracked working memory for AI agents on the same codebase.

99 installs/wk local only

TeamShared

by xhad

Shared memory for coding agents. Stop re-explaining your codebase every session.

92 tools answering

RCLL

by rcll

Self-hosted shared memory for a team of AI agents. Rooms, L0-L3 depth, no LLM on the read path.

39 installs/wk local only

memsprout

by memsprout

shared AI-context layer for teams — persistent memory your agents search and update over MCP

answering

Memory

by cortex-mem

Shared, persistent memory for AI agents — works with Claude, Kiro, Cursor, or any MCP client.

51 installs/wk local only

Continuum

by pouyahasanamreji

Shared memory + orchestration for your coding agents. Local-first MCP, vector RAG.

local only

gjalla — questions

Answers built from our own checks of this server.

Why is there no uptime for gjalla?

gjalla runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package gjalla was installed 3 685 times last week.

How do I connect gjalla?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls gjalla straight from pypi; nothing to host, nothing to sign up for.

How many people use gjalla?

The pypi package gjalla was installed 3 685 times in the last week. Week over week that is -33%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.