Run AI models anywhere.
Caution
Never embed access keys client-side (i.e. in the browser). Instead, create a proxy URL in your backend.
Muna is distributed on NPM. Open a terminal and run the following command:
# Run this in Terminal
$ npm install munaFirst, create a Muna client, specifying your access key (create one here):
import { Muna } from "muna"
// 💥 Create an OpenAI client
const openai = new Muna({ accessKey: "<ACCESS KEY>" }).beta.openai;Next, run a model:
// 🔥 Create a chat completion
const completion = openai.chat.completions.create({
model: "@openai/gpt-oss-20b",
messages: [
{ role: "user", content: "What is the capital of France?" }
],
acceleration: "local_gpu"
});Finally, use the results:
// 🚀 Use the results
console.log(completion.choices[0].message);- Check out several AI models we've compiled.
- Join our Slack community.
- Check out our docs.
- Read our blog.
- Reach out to us at hi@muna.ai.
Muna is a product of NatML Inc.
