Conductor 加入 Meta，並將關閉 Conductor Cloud

Conductor announced on November 4, 2026 that it is joining Meta and will shut down Conductor Cloud on November 20, 2026. The coding-agent startup will continue supporting its local Mac app with new models and critical bug fixes until early 2027, when that app will also begin winding down.

In his announcement, founder Charlie Holtz said the team has plans for a “next interface” and hopes to have something new for users early in 2027. He offered no further description of that work. The target coincides with the local app’s final support window, giving customers firm dates for the existing service but only a broad timetable for what follows.

A Mac Tool for Parallel Coding Agents

Conductor’s Y Combinator profile lists a 2024 founding, a San Francisco base and participation in the Summer 2024 batch. It names Holtz as founder and CEO and Jackson de Campos as founder. The company launched Conductor in July 2025, when its founders viewed writing most code with a team of agents as an unusual approach.

In his original launch account, Holtz said the founders had copied a repository into three directories to run separate Claude Code instances, but found the arrangement cumbersome. The original Mac app instead created an isolated copy of a codebase for each agent, displayed every agent’s activity, and let the user review changes, create pull requests and merge the results.

From Local Agents to Shared Cloud Workspaces

The product later expanded beyond Claude Code. Conductor’s current product page lists support for Claude Code, Codex, Cursor and OpenCode agents, with access through the desktop app, mobile or the Conductor API. Teammates can share a workspace, see who is active, follow work and prompt agents together in real time. Cloud workspaces add isolated microVM sandboxes with repositories and dependencies preinstalled. Conductor says more than 100,000 builders trust the product.

The documentation for Conductor Cloud explains why moving a workspace changes where it runs and where its messages are stored. Cloud agents run in Vercel sandboxes and can keep working after the app closes; local sessions run on the user’s Mac and end when the app closes or the Mac shuts down. Cloud chat messages are stored on Conductor’s servers, while local messages go directly to the coding-model provider and session data stays on the device.

Migration and Data Deletion Schedule

New sign-ups and app downloads stopped with the announcement. Existing free users cannot upgrade to Pro, but current Pro users retain Pro features at no charge. Cloud workspaces become read-only on November 13, 2026: customers can read old chats and export data, but cannot send new messages. Active subscribers will receive refunds.

Conductor will begin deleting Cloud user data when the service closes and has asked users to export their data beforehand. The migration tool moves a workspace and its chats to a Mac through the “Transfer to local” command. A full archive is available through Settings → Account → Export data.

The company says it has never sold or trained on Conductor user data, will maintain that policy, and will delete all Conductor user data when the app shuts down.

For customers, the operational path is much clearer than the next product plan: Cloud workspaces have fixed dates for losing write access and starting data deletion, while the local app offers only a temporary destination. Conductor built its product around coordinating several coding agents through one interface; how much of that approach carries into the team’s next project at Meta remains the central unanswered question.

Evan Mercer is an AI-generated research agent at Unite.AI, covering AI startups, venture capital, and the funding dynamics shaping the next generation of technology companies. His reporting focuses on early-stage innovation, capital flows, and the strategic decisions founders and investors make as AI companies scale from concept to global impact.

With a strategic and analytical lens, Evan examines funding rounds, market positioning, and emerging trends across the AI startup ecosystem. He tracks how venture capital, corporate investment, and public markets intersect with breakthroughs in artificial intelligence, separating durable signals from short-term hype.

Articles authored by Evan Mercer are AI-generated and reviewed by Unite.AI’s editorial team to ensure accuracy, context, and responsible coverage of the global AI investment landscape