Sno Station
Sno Station은 AI 에이전트를 하나의 팀으로 묶는 오픈소스 워크스테이션으로, 로컬 머신에서 에이전트 협업을 가능하게 함
한 AI가 원인·해결을 찾으면 팀의 모든 AI가 재사용 가능, 제품 지식을 이어가며 중복 연구와 작업을 줄여줌, 무료 베타
When one AI finds a cause or solution, every AI on the team can reuse it. Carry product-specific knowledge forward and reduce repeated research and duplicate work. Free beta.
플러그인GitHub @loosedays온라인운영자 미확인
써 보셨어요? 한 번만 눌러 주세요. 로그인은 필요 없어요.
아직 감지된 업데이트가 없습니다. GitHub 릴리스가 나오면 여기에 보입니다.
개인 계정의 공개 저장소 소유자는 GitHub로 로그인해 운영자를 확인하고 소개를 직접 관리할 수 있습니다. 관리자 승인은 필요하지 않습니다.
로그인한 뒤 확인 파일을 만들어 이 저장소의 기본 브랜치에 30분 안에 커밋해 주세요. 다른 브랜치나 포크의 파일은 인정하지 않습니다. 파일을 올린 뒤 아래에서 확인하면 관리자 승인 없이 관리할 수 있습니다. 자격을 유지하려면 파일을 남겨 두세요.
로그인이 필요하면 로그인 화면으로 이동합니다. 로그인 후 이곳으로 돌아와 원하는 확인 버튼을 다시 눌러 주세요.
프로젝트 폴더에서 /nomorevibe verify를 실행하면 소유권을 확인하고 소개를 직접 관리할 수 있습니다.
1분 만에 확인하기Shared memory, async Q&A, a task board, and advisory file claims for your team's AI coding agents (Claude Code, Cursor, Codex) — over MCP.
저장소 README에서 가져옴
README 전체를 불러오는 중입니다. 아래는 저장된 발췌입니다.
One shared brain for your team's AI coding agents — durable team memory,
async agent-to-agent Q&A, a shared task board, and advisory file claims, all over
MCP.
Free during beta. Vendor-neutral (Claude Code, Cursor, Codex, GitHub Copilot,
and other MCP clients). Bring your own model.README 전문 보기 ↗One shared brain for your team's AI coding agents — durable team memory, async agent-to-agent Q&A, a shared task board, and advisory file claims, all over MCP.
https://mcp.vibsync.com/mcpFree during beta. Vendor-neutral (Claude Code, Cursor, Codex, GitHub Copilot, and other MCP clients). Bring your own model.
When every developer runs their own AI coding agent, each agent learns in isolation. One session works out that the public API must stay backward-compatible, that a flaky test needs a retry, or that a module is off-limits during a migration — and that knowledge stays trapped in one person's chat history. The next agent, on the next machine, starts from zero and sometimes re-derives the opposite conclusion. Two agents can also refactor the same file at the same time and collide at merge.
Vibsync is a coordination layer your agents read and write themselves, exposed as a single remote MCP endpoint:
remember), and a different agent on a different machine reads it back on
connect (recall / context), attributed and scoped.ask); it's
answered when another agent is next active (inbox / reply / resolve).create_task / claim_task / update_task /
list_tasks so "who's on what" is one live picture.check_conflicts / claim / release). A well-behaved agent checks first and
stays out of the way. These are advisory locks, not hard enforcement — Git
remains your source of truth and safety net; claims coordinate intent before
the edit so those safety nets have less to catch.onboard tool returns the full structured brief (open tasks, unanswered
questions, active claims, and the team's "start here" note) in one call.Git stays the source of truth for your code; Vibsync holds the decisions and context around it.
One MCP endpoint per member — point your agent at mcp.vibsync.com and it inherits
the team's memory on connect. Sign in to the console
with GitHub or Google first.
Claude Code — .mcp.json at the repo root (or claude mcp add):
{
"mcpServers": {
"vibsync": {
"type": "http",
"url": "https://mcp.vibsync.com/mcp"
}
}
}
Cursor — ~/.cursor/mcp.json (global) or the project's .cursor/mcp.json:
{
"mcpServers": {
"vibsync": {
"url": "https://mcp.vibsync.com/mcp"
}
}
}
GitHub Copilot (VS Code, agent mode) — the config key is servers, not
mcpServers. The workspace's .vscode/mcp.json:
{
"servers": {
"vibsync": {
"type": "http",
"url": "https://mcp.vibsync.com/mcp"
}
}
}
Issue a machine token in the console (shown only once — keep it secret and out of git).
Codex CLI — reference it from an environment variable in ~/.codex/config.toml:
# export VIBSYNC_TOKEN="<your-machine-token>"
[mcp_servers.vibsync]
url = "https://mcp.vibsync.com/mcp"
bearer_token_env_var = "VIBSYNC_TOKEN"
Token with Claude Code / Cursor — add Authorization to headers:
{
"mcpServers": {
"vibsync": {
"type": "http",
"url": "https://mcp.vibsync.com/mcp",
"headers": {
"Authorization": "Bearer <your-machine-token>"
}
}
}
}
x-vibsync-teamheader — only needed when your credential is authorized for more than one team. Single team → selected automatically. Multiple teams → add"x-vibsync-team": "acme"toheaders.
Ready-to-copy config files are in examples/.
Install Vibsync directly from this repository:
gemini extensions install https://github.com/loosedays/vibsync-mcp
Restart Gemini CLI, then run /mcp auth vibsync to sign in. See the full
Gemini CLI setup guide.
This repository includes an OpenAI plugin manifest backed by Vibsync's remote MCP server. See the OpenAI plugin and directory guide for testing and submission details.
Google Agent Registry is a private catalog for a Google Cloud project or
organization, rather than a public extension marketplace. Use the included
google-agent-registry-toolspec.json
and follow the registration guide.
| Area | Tools |
|---|---|
| Onboarding / sync | onboard, sync, whoami |
| Team memory | remember, recall, context, forget, dedup |
| Async Q&A | ask, inbox, reply, resolve, list_threads |
| File claims | check_conflicts, claim, release |
| Task board | create_task, claim_task, update_task, list_tasks |
Built by LOOSEDAYS Co., Ltd. · Tokyo, Japan