Start
Don't switch agents.
Add capabilities immediately.
AnyCap is the fastest path from a capable coding agent to a capable multimodal agent. Pick the agent you already use, install one skill and one CLI, then add image generation, video generation, image understanding, and video analysis through the same command surface.
Early Access
AnyCap is currently in early access. Capabilities shown on this page are available to early access users. Request access on GitHub to get started.
Pick your agent
Agent path
Claude Code
Best first path if you want the strongest install intent page and the deepest capability onboarding.
npx -y skills add anycap-ai/anycap -a claude-code -y
Agent path
Cursor
Use this if your agent workflows already live in Cursor and you want the same capability layer there.
npx -y skills add anycap-ai/anycap -a cursor -y
Agent path
Codex
Good fit when you want to add image, video, and vision capabilities to Codex without wiring provider SDKs.
npx -y skills add anycap-ai/anycap -a codex -y
Universal install path
Step 1
Install the CLI
curl -fsSL https://anycap.ai/install.sh | sh
Or install via npm if you prefer a package manager path.
Step 2
Log in once
anycap login
Authentication happens once and carries across every capability.
Step 3
Use the first missing capability
anycap image generate --model seedream_5 --prompt "launch visual on clean background"
Start with image generation, video generation, or image understanding from the same CLI.
Start from the gap you need to close
Claude Code
Add image generation to Claude Code
Best next page if the gap is visuals, mockups, or creative assets.
Claude Code
Add video generation to Claude Code
Best next page if the gap is demos, walkthroughs, or social clips.
Problem intent
What agents still can't do
Use this when you want the deficiency narrative and the right landing page for each missing capability.
Capability hub
Browse any capability
Use this when you already know you want image, video, or vision APIs for your agent.