Start · By AnyCap Team · Last updated April 10, 2026
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, then tell it what you want in natural language. It can install one skill and one CLI for you, then add image generation, video generation, image understanding, and video analysis through the same command surface.
Paste this into Claude Code, Cursor, or Codex
The smoother path is to ask in plain language and let the agent carry the setup, login, and capability call from there.
help me install AnyCap and generate a launch imagePick your agent
Claude Code →
Adds image, video, and vision commands to Claude Code through one skill; the Claude Code page shows real outputs.
npx -y skills add anycap-ai/anycap -a claude-code -yCursor →
Same skill and CLI inside Cursor, so the agent can generate and read media without leaving the editor.
npx -y skills add anycap-ai/anycap -a cursor -yCodex →
Adds image, video, and vision commands to Codex without wiring provider SDKs.
npx -y skills add anycap-ai/anycap -a codex -y
Prefer to run the commands yourself
1. Install the CLI
curl -fsSL https://anycap.ai/install.sh | shPrefer a package manager? npm install -g @anycap/cli works on macOS, Linux, and Windows.
2. Log in once
anycap loginAuthentication happens once and carries across every capability, so you can keep asking in natural language after setup.
Start from the gap you need to close
Add image generation to Claude Code →
Best next page if the gap is visuals, mockups, or creative assets.
Add video generation to Claude Code →
Best next page if the gap is demos, walkthroughs, or social clips.
What agents still can't do →
The gaps a coding agent hits first, each with the page that closes it.
Browse any capability →
Every capability with its command and the models behind it.