comfy-cozy is an open-source AI co-pilot package designed for VFX artists working with ComfyUI. It provides 133 MCP tools, supports six swappable LLM providers (including OpenAI-compatible endpoints), and features artist recipes, safety gates, reversible edits, EXR-aware vision, and workflow provenance. Ideal for automating and enhancing VFX workflows.
In the Other AI space, comfy-cozy takes a focused approach. It focuses on enabling VFX artists to automate and enhance workflows in ComfyUI with AI-powered tools and multi-provider LLM integration. comfy-cozy is an open-source project aimed at VFX artists and developers using ComfyUI. The project is open source (MIT). It runs on the command line and API, and it can be self-hosted.
Joseph O Ibrahim builds and maintains comfy-cozy, and the product first shipped in 2026. The project is developed in the open on GitHub with 22 stars and 268 commits in the last 90 days. Across PulseGate's embedding index, comfy-cozy has few near neighbours, marking it as relatively distinct. Among its 9 catalogued features are MCP tools, LLM provider switching, and artist recipes. It exposes integrations via an MCP server and a public API.
Latest indexed changes and source events
Other apps tracked under the same category.
