CLI
One CLI for the capabilities
your agent still needs.
The agent can plan the workflow. The missing layer is usually execution: one command surface for image generation, video generation, image understanding, and video analysis. AnyCap CLI gives that layer one install path, one auth flow, and one interface across Claude Code, Cursor, Codex, and similar agent products.
Don't switch agents. Add capabilities immediately.
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.
Install once
CLI installation will be available when AnyCap launches publicly. The install path below is the stable entry to the runtime.
# macOS / Linux / Windows (Git Bash)
curl -fsSL https://anycap.ai/install.sh | sh
# npm (all platforms)
npm install -g @anycap/cli
# Verify
anycap status
The first commands most agents need
Image Generation
Early AccessGenerate and edit visuals with Seedream 5, Nano Banana Pro, and more.
anycap image generateVideo Generation
Early AccessGenerate walkthroughs, clips, and motion output with Veo 3.1.
anycap video generateImage Understanding
Early AccessAnalyze screenshots, diagrams, and visual references through one runtime.
anycap image readVideo Analysis
Early AccessInspect recordings and extract structured detail from video content.
anycap video readWhy one CLI matters
Keep the command surface stable
Without a unified CLI, every new capability becomes a new SDK, dashboard, or shell script. AnyCap keeps the execution layer consistent.
Log in once
Authentication happens once and carries across image, video, and vision workflows instead of fragmenting across providers.
Move across agents without re-learning the runtime
The same commands can sit under Claude Code, Cursor, Codex, and similar agent environments without forcing a new mental model each time.
Available across agent products
Understand the rest of the stack
Learn
What agents can't do
Start here if you want the deficiency-first narrative and the shortest page for each missing capability.
Learn
How skills fit
Use this when you want to understand how the instruction layer connects the agent to the CLI and runtime.
Guide
Context Engineering
Use this when you want to understand when the agent should call a capability instead of staying inside the prompt.