Who it is for
Teams running coding agents that need shared context across sessions and machines.
Long-term team memory and live work context for coding agents
Overview
Vibsync gives coding agents two things that normally vanish between sessions: what the team knows, and what the team is doing.
The first covers discoveries, fixes, failed approaches, product rules and decisions, the failed approaches being the part almost never written down and the most expensive to rediscover. The second covers open questions, tasks, ownership and active work areas. The boundaries are stated plainly: Git remains the source of truth for code, Vibsync holds the context around it; it works alongside existing agents without launching or controlling them; and it runs no inference of its own. Community tier.
Teams running coding agents that need shared context across sessions and machines.
The endpoint requires credentials, so twenty is the listing's own count. Knowledge capture, live work context, task and ownership tracking are the groupings described.
Availability
Vibsync is listed in the Claude connectors directory only. LOOSEDAYS Co., Ltd. has no app under the same domain in the ChatGPT directory; 392 of the 3,150 products here are on both marketplaces, and this is not one of them.
The MCP server behind a Claude connector is usually the same server a ChatGPT app would need, so the absence is a distribution decision rather than a technical one.
Claude listing
Vibsync publishes 20 tools to Claude, deeper than 68.5% of the 1,253 Claude-listed connectors.
The median Claude-listed connector filed under Productivity publishes 12, so this one runs 8 tools above its bucket's median and ranks 156th of 462 by tool count.
It falls in the 11-20 tools band, which holds 22.5% of the Claude directory.
Vibsync publishes a remote MCP endpoint. Claude connects to it over HTTP; there is nothing to install locally.
Every connector in the Claude directory is remote, all 1,253 of them, so transport is not a differentiator there.
https://mcp.vibsync.com/mcp Vibsync is community-listed in the Claude directory, the tier 770 of 1,253 connectors sit in (61.5%). It is the default for a self-published server, and says nothing either way about quality.
In the publisher's words
Vibsync gives Claude Code, Cursor, Codex, and other AI coding agents long-term team memory and live work context. It carries both what the team knows — discoveries, fixes, failed approaches, product rules, and decisions — and what the team is doing now — questions, tasks, ownership, and active work areas — across sessions and machines. Git remains the source of truth for code; Vibsync keeps the context around the work. It works alongside existing agents rather than launching, routing, or controlling them. Bring your own model; Vibsync does not run inference. [ja] Vibsync は Claude Code・Cursor・Codex などのAIコーディングエージェントに、長期的なチームメモリと現在の作業状況を与えます。発見、修正方法、失敗したアプローチ、プロダクトルール、意思決定といった「チームが知っていること」に加え、質問、タスク、担当、作業中の領域といった「チームが今していること」を、セッションやマシンを越えて引き継ぎます。コードの正本はGitのまま、Vibsyncが作業の 周辺にあるコンテキストを保持します。既存のエージェントを起動・振り分け・制御するオーケストレーターではありません。利用者自身のモデルを使い、Vibsyncは推論を実行しません。
Quoted from the connector's own Claude directory listing as captured in August 2026. Node8 did not write it and does not vouch for it.
Nearby
Shared team workspace with brokered connector tools
ChatGPT
Backup administration and audit logs from a Druva Cloud account
Claude
Run Tallyfy processes, tasks, and approvals from chat
ChatGPT
Turn documents into schema validated JSON
ChatGPT
Tasks, lists, and calendar blocks from chat
ChatGPT
Spin up a database, REST API and admin inside the conversation
Claude
This is an independent catalogue entry compiled by Node8 from Vibsync's public marketplace listing as it stood in August 2026. Listing facts come from the marketplaces; the comparisons against the rest of the directory and any live-endpoint measurements are Node8's. Node8 is not affiliated with LOOSEDAYS Co., Ltd., and inclusion here is not an endorsement.
Node8 builds MCP servers end to end: deciding which tools are worth exposing, the authentication and permission model, the review submissions, and the onboarding that gets them used. One server serves ChatGPT, Claude, and Microsoft Copilot.