Remix StudioBatch AI generation & campaign workspace

A self-hosted AI assistant workspace for orchestration, batch content generation, and social campaign planning — powered by a built-in assistant and reusable workflow libraries.

What Is Remix Studio

Get Started

View on GitHub

🧩

Combination Engine

Build workflows from reusable libraries and direct inputs, then expand them into full combination sweeps or randomized shuffle samples — 3 subjects × 4 styles × 2 references becomes 24 drafts before you send anything.

How workflows work

🤖

Assistant-First Orchestration

A built-in assistant (powered by Gemini models) can inspect libraries, albums, model availability, and storage, then prepare project mutations behind explicit confirmation.

Learn more

📚

Reusable Libraries

Store prompt fragments, tags, and media inputs in text, image, video, and audio libraries — then reuse them across every project and workflow.

Libraries & prompts

📅

Campaign Workspace

Turn generated copy and media into campaign posts, schedule them on a timeline, and publish across connected social channels like X and Threads.

Plan campaigns

🔌

MCP Support

The same shared tool layer powers an MCP server at /mcp, so clients like Claude and Codex can create libraries, inspect albums and models, and assemble projects.

MCP integration

🏠

Self-Hosted Control

Providers, storage, exports, auth, and automation all stay in your own deployment — backed by PostgreSQL, S3-compatible storage, and Docker.

Deploy it

Multimodal by design

Remix Studio runs text, image, video, and audio generation projects from one workspace. It combines four layers in one product:

An in-app assistant for planning and operating workflows
A project system for composing workflows from library-backed and direct inputs
A campaign workspace for scheduling and publishing social posts
A background execution stack for queueing, storing, exporting, and delivering results

Available in English, Simplified Chinese, Traditional Chinese, Japanese, Korean, and French.

Built with Google AI Studio and Antigravity.

Found a bug or have a request?

Please report it on GitHub Issues. Bug reports, feature requests, and questions are all welcome — clear reports with steps to reproduce help the most.