gjalla is answering right now. Last checked 9 min ago. Last commit 20 Sep 2026.
Hosted 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
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 9 min ago.
claude mcp add mcp --transport http https://gjalla.io/mcp/stream{
"mcpServers": {
"mcp": {
"url": "https://gjalla.io/mcp/stream"
}
}
}[mcp_servers.mcp]
url = "https://gjalla.io/mcp/stream"{
"mcpServers": {
"mcp": {
"url": "https://gjalla.io/mcp/stream"
}
}
}{
"mcpServers": {
"mcp": {
"url": "https://gjalla.io/mcp/stream"
}
}
}This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://gjalla.io/mcp/stream | streamable-http | sign-in | 516 ms | 9 min ago |
Alternatives to gjalla
same job, measured the same waySelf-curating shared memory that keeps your agents working like a high-performing team
Self-hosted shared memory for a team of AI agents. Rooms, L0-L3 depth, no LLM on the read path.
Shared project memory that keeps teammates and AI agents aligned across sessions.
One shared brain for your AI coding agents: team memory, agent Q&A, tasks, and file claims.
Self-hosted AI memory server. Persistent memory on your hardware, not the cloud.
Code-pinned team memory for AI coding agents — typed artifacts, MCP-native, self-host.
Shared, git-tracked working memory for AI agents on the same codebase.
Hosted MCP memory for coding agents: persistent across sessions, editable markdown, team sharing.
gjalla — questions
Answers built from our own checks of this server.