AI Video Tools

April 26, 2026 · View on GitHub

A curated index of GitHub projects for AI-driven video production — ComfyUI workflows and skills, MCP servers, agent skill packs, and agentic video frameworks.

Last Updated: 2026-04-26 Entries: 37


Scope

OUT OF SCOPE: Models (LTX, Wan, HunyuanVideo, etc. as standalone weights/checkpoints).

FOCUS: Tooling (MCPs, Agent Skills, CLIs, agentic frameworks) intended to provide reliable ways for AI agents — framework-agnostic and framework-specific — to perform video production tasks: generation, editing, cutting, montage, transcoding, captioning, etc.

DEFINING FEATURE: Built for agents with human users — not for human UIs. Inclusion criterion is whether the project exposes a stable, agent-callable surface (skill, CLI, MCP, SDK) rather than a GUI workflow.

In scope: skills, CLIs, MCPs, agent SDKs, agentic frameworks, ComfyUI integrations exposed to agents.


Table of Contents


Agentic Video Frameworks

agent

The agentic video editing framework

Stars Last commit Language

⭐ 244 · Last updated: 2025-02-10 · diffusionstudio/agent

agentic-video-editor

AI-powered video editor that turns raw footage and a creative brief into a polished ad using an ensemble of AI agents (Google Gemini + FFmpeg)

Stars Last commit Language

⭐ 366 · Last updated: 2026-04-14 · poseljacob/agentic-video-editor

Creator-Catalyst

AI Content Repurpose Agent using long form Videos

Stars Last commit Language

⭐ 0 · Last updated: 2026-02-07 · garvit-010/Creator-Catalyst

CutClaw

Agentic Hours-Long Video Editing via Music Synchronization

Stars Last commit Language

⭐ 755 · Last updated: 2026-04-17 · GVCLab/CutClaw

Director

AI video agents framework for next-gen video interactions and workflows.

Stars Last commit Language

⭐ 1367 · Last updated: 2026-01-23 · video-db/Director

ffmpeg-python

Python bindings for FFmpeg - with complex filtering support

Stars Last commit Language

⭐ 10993 · Last updated: 2024-08-04 · kkroening/ffmpeg-python

hyperedit

AI-powered video editor with FFMPEG, Remotion, & Obsidian Agents Baked in

Stars Last commit Language

⭐ 125 · Last updated: 2026-04-15 · kevinbadi/hyperedit

hyperframes

Write HTML. Render video. Built for agents.

Stars Last commit Language

⭐ 11156 · Last updated: 2026-04-26 · heygen-com/hyperframes

OpenMontage

World's first open-source, agentic video production system. 12 pipelines, 52 tools, 500+ agent skills. Turn your AI coding assistant into a full video production studio.

Stars Last commit Language

⭐ 3171 · Last updated: 2026-04-24 · calesthio/OpenMontage

video-edit-tools

Deterministic video editing SDK for AI agents. Ships with MCP tools.

Stars Last commit Language

⭐ 5 · Last updated: 2026-03-15 · swimmingkiim/video-edit-tools

ViMax

"ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator All-in-One)"

Stars Last commit Language

⭐ 2713 · Last updated: 2026-03-29 · HKUDS/ViMax


ComfyUI

comfyui-custom-node-skills

A curated collection of Claude Code skills for developing ComfyUI custom nodes. These skills give Claude comprehensive knowledge of the ComfyUI node system, covering both the V3 (recommended) and V1 (legacy) APIs.

Stars Last commit Language

⭐ 177 · Last updated: 2026-04-24 · jtydhr88/comfyui-custom-node-skills

comfyui-custom-node-skills

Provide Claude Code skills for building and managing ComfyUI custom nodes using V3 and V1 APIs with detailed node system knowledge.

Stars Last commit Language

⭐ 0 · Last updated: 2026-04-26 · MusfiqurRahma/comfyui-custom-node-skills

ComfyUI-Expert

Session-scoped Claude Code agent for ComfyUI video production — 12 specialized skills for image gen, video, voice cloning, LoRA training, and publishing

Stars Last commit Language

⭐ 49 · Last updated: 2026-03-18 · MCKRUZ/ComfyUI-Expert

ComfyUI-FFMPEGA

Intelligent FFMPEG agent node for ComfyUI - transforms natural language video editing prompts into automated video transformations

Stars Last commit Language

⭐ 7 · Last updated: 2026-04-26 · AEmotionStudio/ComfyUI-FFMPEGA

comfyui-workflow-skill

Natural language → ComfyUI workflow JSON. 34 built-in templates, 360+ node definitions, auto model download. Supports txt2img, img2img, txt2vid, img2vid, audio, 3D generation across SD1.5/SDXL/SD3/FLUX/Wan2.2/HunyuanVideo/LTXV/Mochi/Cosmos + LLM integration. Works as a skill for Claude Code, Cursor, and other AI coding agents.

Stars Last commit Language

⭐ 186 · Last updated: 2026-04-09 · twwch/comfyui-workflow-skill

comfyui-workflow-skills

ComfyUI Workflow Master is an open-source skill module designed for AI agent platforms (such as [OpenClaw], [Claude Code], or any agent framework that supports skill-based architectures). It enables an AI agent to fully automate the ComfyUI workflow lifecycle:

Stars Last commit Language

⭐ 2 · Last updated: 2026-03-16 · 21Pdontno/comfyui-workflow-skills

comfyui_LLM_party

LLM Agent Framework in ComfyUI includes MCP sever, Omost,GPT-sovits, ChatTTS,GOT-OCR2.0, and FLUX prompt nodes,access to Feishu,discord,and adapts to all llms with similar openai / aisuite interfaces, such as o1,ollama, gemini, grok, qwen, GLM, deepseek, kimi,doubao. Adapted to local llms, vlm, gguf such as llama-3.3 Janus-Pro, Linkage graphRAG

Stars Last commit Language

⭐ 2204 · Last updated: 2026-03-08 · heshengtao/comfyui_LLM_party

ComfyUI_Skill_CLI

Agent-friendly CLI for managing and executing ComfyUI workflow skills

Stars Last commit Language

⭐ 9 · Last updated: 2026-04-22 · HuangYuChuh/ComfyUI_Skill_CLI

ComfyUI_Skills_OpenClaw

Agent-friendly ComfyUI workflow skills for OpenClaw, Hermes Agent, Codex, and Claude Code. Turn any ComfyUI workflow into a callable AI agent skill via CLI.

Stars Last commit Language

⭐ 241 · Last updated: 2026-04-21 · HuangYuChuh/ComfyUI_Skills_OpenClaw

infinite-image-browsing

A full-featured image/video management app with AI-powered organization and semantic search. Supports metadata from SD-webui, ComfyUI, Fooocus, NovelAI, StableSwarmUI, and more. Available as standalone app, SD-webui extension, or library.

Stars Last commit Language

⭐ 1292 · Last updated: 2026-04-08 · zanllp/infinite-image-browsing

kyarakuri

Character Creation Skills With ComfyUI

Stars Last commit Language

⭐ 0 · Last updated: 2026-04-12 · hachiware-labs/kyarakuri


MCPs

comfy-mcp-server

A server using FastMCP framework to generate images based on prompts via a remote Comfy server.

Stars Last commit Language

⭐ 41 · Last updated: 2025-03-02 · lalanikarim/comfy-mcp-server

comfyui-mcp

ComfyUI MCP server + Claude Code plugin — workflow execution, visualization, composition, model management, and skill generation

Stars Last commit Language

⭐ 52 · Last updated: 2026-04-21 · artokun/comfyui-mcp

Davinci-MCP

An OpenSource mcp for Da Vinci Resolve, to allow agents to automatically compile, edit, and direct clips

Stars Last commit Language

⭐ 0 · Last updated: 2026-04-02 · Iamkewl/Davinci-MCP

mcp-kdenlive

MCP server for Kdenlive — wraps kdenlive-api for Claude Code and other LLM agents

Stars Last commit Language

⭐ 5 · Last updated: 2026-02-04 · D-Ogi/mcp-kdenlive

mcp-video

Video editing MCP server for AI agents. 83 tools, 858 tests collected, 3 interfaces. Works with Claude Code, Cursor, and any MCP client. Local, fast, free.

Stars Last commit Language

⭐ 5 · Last updated: 2026-04-23 · Pastorsimon1798/mcp-video

MeiGen-AI-Design-MCP

MeiGen-AI-Design-MCP — Turn Claude Code / OpenClaw into your local Lovart. Local ComfyUI, 1,400+ prompt library, multi-direction parallel generation.

Stars Last commit Language

⭐ 689 · Last updated: 2026-04-23 · jau123/MeiGen-AI-Design-MCP


Skills

alicloud-skills

alibaba cloud skills,qwen ,wan and all skills

Stars Last commit Language

⭐ 382 · Last updated: 2026-04-08 · cinience/alicloud-skills

Claude-Video-Production-Plugin

Claude Code plugin: video production workflow — transcode, organise, dedupe, ComfyUI generation, cover art, with editing/generative/cover-art variants.

Stars Last commit Language

⭐ 0 · Last updated: 2026-04-19 · danielrosehill/Claude-Video-Production-Plugin

Generative-Media-Skills

Multi-modal Generative Media Skills for AI Agents (Claude Code, Cursor, Gemini CLI). High-quality image, video, and audio generation powered by muapi.ai.

Stars Last commit Language

⭐ 3107 · Last updated: 2026-04-26 · SamurAIGPT/Generative-Media-Skills

higgsfield-claude-skills

19 Claude Code skills for Higgsfield AI — automate image generation, Seedance 2.0 video creation, and full UGC ad pipelines with Playwright browser automation

Stars Last commit Language

⭐ 61 · Last updated: 2026-04-13 · AKCodez/higgsfield-claude-skills

ltx-video

LTX-2.3 video generation skill — setup, inference, prompting, ComfyUI integration for Lightricks 22B DiT audio-video model

Stars Last commit Language

⭐ 4 · Last updated: 2026-03-27 · broomva/ltx-video

pexo-skills

A collection of open-source Agent Skills for content creation — images, audio, and video.

Stars Last commit Language

⭐ 731 · Last updated: 2026-04-09 · pexoai/pexo-skills

skills

HeyGen AI agent skills — avatar creation and video production via the v3 Video Agent pipeline

Stars Last commit Language

⭐ 179 · Last updated: 2026-04-26 · heygen-com/skills

vulca

Agent-native image-editing SDK for Claude Code. 21 MCP tools + /decompose skill — semantic layer splits, L1–L5 cultural scoring, region inpaint. Powered by ComfyUI, Gemini, or mock.

Stars Last commit Language

⭐ 7 · Last updated: 2026-04-26 · vulca-org/vulca

Wan-skills

AI Agent Skills for Wan — Enable your AI Agent to easily leverage Wan's AIGC capabilities.

Stars Last commit Language

⭐ 39 · Last updated: 2026-04-17 · Wan-Video/Wan-skills


License

License: CC BY 4.0