Sim

Sim Studio is an open-source platform for building, testing, and optimizing agentic workflows. It provides a visual interface for constructing large language model (LLM) workflows that connect to external tools and services, with the stated goal of making it fast to move from design to deployment. The project is licensed under Apache 2.0 and is available both as a cloud-hosted service and as a self-hosted application.

The application is built on Next.js using the App Router, with PostgreSQL as the database accessed through Drizzle ORM and authentication handled by Better Auth. The user interface uses Shadcn and Tailwind CSS, state is managed with Zustand, and the workflow editor is implemented with ReactFlow. Documentation is produced with Fumadocs. The repository includes a Docker Compose configuration with optional profiles for running local models through Ollama on either GPU or CPU, as well as Dev Container and manual installation options.

The project may be of interest to developers who want to prototype or host LLM-driven automation without building a custom orchestration interface, and to teams that require a self-hosted deployment for data control. Its support for local models through Ollama also makes it relevant to users who wish to run workflows without relying on external model providers.