Agency Orchestrator
A no-code orchestration platform that assembles a team of AI expert roles from a single sentence, runs them through YAML-defined workflows with acceptance checks, and delivers finished documents, images or video.
Agency Orchestrator turns a single natural-language request into a coordinated team of AI expert roles that produce a complete deliverable, such as a product plan, research report or short video, within minutes. Workflows are defined in zero-code YAML, and the assistant can automatically pick which of its many expert roles to staff on a task when the user does not specify one.
A web studio provides a drag-and-drop canvas for building and running workflows, a role library across several languages, an image and video prompt library, and pipelines that call text-to-image and text-to-video providers and assemble multi-shot results locally with ffmpeg. Finished runs can be shared as a single self-contained HTML report or pushed automatically to chat platforms after a scheduled run, and completed workflows can be submitted back to a community template library.
It supports around twenty LLM API providers, several of which need no API key, and ships as a web app, a desktop Electron client, or a Docker deployment. It is written in TypeScript and licensed under Apache-2.0.