This is your unified interface to 250+ AI models through the inference.sh CLI. Instead of juggling different APIs for FLUX image generation, Veo video, Claude/Gemini LLMs, Tavily search, and Twitter automation, you get one command line tool that handles them all. The CLI automatically uploads local files when you pass paths instead of URLs, which is genuinely convenient for image upscaling or avatar generation workflows. It's serverless, so no GPU required. If you're building agents that need to bounce between generating images, searching the web, calling LLMs, and posting to Twitter, this consolidates what would otherwise be a mess of different SDKs and auth flows into a single belt command.
npx -y skills add inference-sh-skills/skills --skill infsh-cli --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
sentry/dev
degausai/wonda
github/awesome-copilot
insforge/agent-skills
github/awesome-copilot
breaking-brake/cc-wf-studio