Agent Cowork Memory runs on your own machine — the client starts it, so there is no endpoint to ping. 310 installs a week from pypi. Last commit 6 Oct 2026.
Shared memory and delegation for Codex, Cursor, Claude Code, and OpenCode.
We read the source, 4 d ago · rules ccca72095570
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
deps.spawn(_headless(kind, prompt, folder, answer), folder, out, log, exit_file)
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
этот файл ставится пользователю, но в репозитории его нет
proc = subprocess.run(
const child = spawn(cmd, argv, { ...opts, stdio: [stdin, out, log], windowsHide: true });
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
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 agent-cowork-memory -- npx -y agent-cowork-memory
{
"mcpServers": {
"agent-cowork-memory": {
"args": [
"-y",
"agent-cowork-memory"
],
"command": "npx"
}
}
}
[mcp_servers.agent-cowork-memory]
command = "npx"
args = ["-y", "agent-cowork-memory"]
{
"mcpServers": {
"agent-cowork-memory": {
"args": [
"-y",
"agent-cowork-memory"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"agent-cowork-memory": {
"args": [
"-y",
"agent-cowork-memory"
],
"command": "npx"
}
}
}
Shared memory across devices, sessions, and agents for OpenClaw, Claude Code, and Codex.
Shared work memory for Claude Code, Codex, Cursor and chat, scoped to each repository.
Shared memory for AI coding agents. Save once, reuse from Cursor, Claude Code, Codex.
One memory for you and your AI agents, shared by ChatGPT, Claude, Gemini, Grok, Codex and Cursor.
Delegate from Claude Code to Gemini, Codex, Copilot, Cursor and opencode CLIs as sub-agents.
Route coding work across Claude Code, Codex, Cursor, and OpenCode with shared context.
Local long-term memory MCP server (SQLite) for AI coding agents — OpenCode, Claude Code, Cursor
Shared, project-aware memory for Claude Code, Codex, and other agents with human review.
Answers built from our own checks of this server.