WebLLM

Research summary

WebLLM brings language-model inference into browser applications using WebGPU and the MLC runtime ecosystem. Developers can integrate supported models through a TypeScript-facing library rather than sending every completion request to a hosted inference API. The project offers familiar API conventions and browser-oriented execution patterns, making it relevant to local-first assistants and interactive applications.

It is an inference component rather than an agent framework, so tool use, application state, permissions, and user interfaces remain the responsibility of the embedding application. Practical compatibility depends on the browser, device, model artifacts, and available memory; downloading a model is also distinct from running subsequent inference locally. The library is Apache 2.0 licensed.

Model weights and third-party runtime components retain their own applicable terms, and browser-local inference should not be treated as a blanket privacy guarantee for the entire application.

Repository summary

Stars

19,134

Open issues

Unavailable

Last push

2026-09-15

Commits, 90 days

Unavailable

Repository activity

Not scored

Version

Unavailable

Recorded catalogue figures. View repository data and provenance →

Classification

Pricing & services

Paid services unknown

Whether the provider offers paid products or services has not been established.

Licence scope

Communities

• DiscordMLC-AI (shared community)↗
  Official
  Link details for Discord — MLC-AI (shared community)

  Access

  Public

  Last checked

  2026-10-01