inference-sh/skills

inference.sh Agent skills for using our API to give your agents access to hundreds of apps and other agents

What it solves

It provides a set of modular "skills" (tools and SDKs) that allow AI agents to perform complex tasks such as generating images and videos, searching the web, and automating social media, rather than just generating text.

How it works

These skills are integrated via the inference.sh CLI (called belt) and can be installed as plugins for tools like Claude Code. Users can add specific skills (e.g., flux-image or web-search) to their environment, enabling the agent to call these external capabilities through a standardized interface.

Who it’s for

Developers building AI agents who want to quickly add multimodal capabilities (image, video, search) and UI components to their applications without building each integration from scratch.

Highlights

  • Multimodal Tools: Access to 50+ image models (FLUX, Gemini) and 40+ video models (Veo, Seedance).
  • Agent Integration: Direct installation as a Claude Code plugin.
  • Developer SDKs: Available in both JavaScript/TypeScript and Python with support for streaming and async operations.
  • UI Components: Includes pre-built interfaces for chat, tool calls, and full agent interactions.

Related

  • Project
  • Project
  • Project
  • Project
  • Project