← Products

Developer tools
⚙ Needs: Node.js 18.0.0+ (or a modern browser with fetch); an…

inference.sh JavaScript SDK — run AI apps and build agents in TypeScript (short listing)

💳 Paid API — short listing (license not verifiable): the @inferencesh/sdk guide for JavaScript/TypeScript — run AI apps, streaming, file uploads, sessions, agent SDK with tool builder, human approval workflows, and server proxies for Next.js/Express/Hono/Remix/SvelteKit

At a glance
What
💳 Paid API — short listing (license not verifiable): the @inferencesh/sdk guide for JavaScript/TypeScript — run AI apps, streaming, file uploads, sessions, agent SDK with tool builder, human approval workflows, and server proxies for Next.js/Express/Hono/Remix/SvelteKit
Cost
Free
Needs
Node.js 18.0.0+ (or a modern browser with fetch); an inference.sh account with an API key — usage is billed, check pricing and set limits; for frontend apps, a backend to run the documented server proxy (key must never ship in client code)
Install
Copy the installer prompt below into your Muse — your agent does the rest.

Version:

@
Created by: @inference-sh
⌁

Install

Prerequisites: Node.js 18.0.0+ (or a modern browser with fetch); an inference.sh account with an API key — usage is billed, check pricing and set limits; for frontend apps, a backend to run the documented server proxy (key must never ship in client code) Install "inference.sh JavaScript SDK — run AI apps and build agents in TypeScript (short listing)" for me. It gives my agent @inference-sh's JavaScript SDK guide: install @inferencesh/sdk, authenticate (direct key, env var, or server proxy), run AI apps with basic execution / fire-and-forget / streaming, handle file uploads, use stateful sessions, build template and ad-hoc agents with the tool builder API (client, app, agent, webhook, and internal tools), wire human-approval workflows, and set up proxies for Next.js/Express/Hono/Remix/SvelteKit. IMPORTANT: the license terms were not verifiable (the discovery manifest records no license) — fetch from the link only, reproduce nothing beyond the link, and read the terms yourself before use. Repository: https://github.com/inference-sh/skills/blob/main/sdk/javascript-sdk/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code — my inference.sh API key must never be pasted here, only referenced via environment variable or proxy. Verify that holds; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "javascript-sdk". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. npm install @inferencesh/sdk; save my API key in the vault as INFERENCE_API_KEY; if my app is frontend, set up the documented server proxy route). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.

?

Questions

How do I install a build?

Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.

Where does my money go?

Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.

What does the ✓ next to a creator’s name mean?

It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.