Open-source multimodal MCP plugin for text-only AI agents: recognize and generate images, video, and audio through Qwen/DashScope. Supports Codex, Claude Code, and DeepSeek Harness ecosystem.
Latest release v3.1.0 — Omnimodal v3.1.0 · 5 Aug 2026
1 file for Claude Code: Deepseek-omnimodal CLAUDE.md — 495 tokens loaded in every session.
CLAUDE.md A 495 tok These files are good-boy4069/Deepseek-omnimodal's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.