wizenheimer/tinylm

Browser based ML Inference | OpenAI compliant | Run models like DeepSeek, Llama 3.2, NomicEmbed, KokoroTTS, and more

31
/ 100
Emerging

This helps web developers integrate advanced AI capabilities directly into web browsers and Node.js applications. It allows them to take user input text and generate responses, create text embeddings for search or analysis, and even produce spoken audio, all running on the client-side. The target users are web and JavaScript developers building interactive applications that leverage AI without needing a backend server.

No commits in the last 6 months.

Use this if you are a web developer looking to embed AI features like text generation, semantic search, or text-to-speech directly into your client-side applications for real-time, cost-effective inference.

Not ideal if you need to train large AI models or require server-side processing for complex, high-throughput AI workloads.

web-development client-side-AI real-time-inference AI-powered-applications developer-tooling
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

52

Forks

8

Language

TypeScript

License

Last pushed

Mar 04, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/wizenheimer/tinylm"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.