webllm

Review a GitHub pull request in your browser — free, no install, no API key. A code model runs on your own GPU via WebGPU; your code never leaves the tab.

Updated Sep 10, 2026
Python

zyziyun / llm-routing

Star

LLM routing across the edge↔cloud spectrum: server-side gateway (Python/FastAPI/Redis/k8s) + on-device router (TS/WebLLM/WebGPU)

routing monorepo webgpu on-device fastapi edge-ai llm ai-gateway webllm

Updated Aug 9, 2026
Python

VivekVagale / mock-interviewer

Star

Campus-placement mock interviews graded against key-point rubrics by a local LLM (Ollama), with a validated grader

evaluation whisper interview-preparation llm ollama webllm llm-as-a-judge

Updated Oct 5, 2026
Python

cipher982 / spoc-shot

Star

ai llm generative-ai webllm

Updated Sep 18, 2026
Python

dpan538 / browser-local-hybrid-rag-lanes

Star

Reproducible research lab for hybrid answer lanes in browser-local small-model RAG: separating deterministic evidence-field delivery from generative research guidance.

provenance webgpu digital-archives rag human-ai-interaction qwen rag-evaluation small-language-models webllm hybrid-rag deterministic-ai local-first-ai browser-local

Updated Jun 12, 2026
Python

veto777 / truthai-mini

Star

An AI that runs entirely in your browser. No account, no server reading your words, no filter. Ed25519-signed releases verified on-device.

privacy offline ed25519 webgpu in-browser llm local-ai qwen webllm

Updated Sep 21, 2026
Python

Add this topic to your repo

To associate your repository with the webllm topic, visit your repo's landing page and select "manage topics."

Learn more