Web-LLM Playwright
Provides browser-based local LLM inference by running Web-LLM models entirely in a headless Chromium browser without external API dependencies, supporting multiple quantized models with dynamic switching and screenshot debugging for privacy-sensitive offline workflows.
About
This MCP server provides browser-based local LLM inference by integrating @mlc-ai/web-llm with Playwright automation, running models entirely in a headless Chromium browser without external API dependencies. Built by ragingwind using TypeScript, it loads Web-LLM from CDN into an HTML interface and exposes programmatic access through browser evaluation, supporting multiple quantized models like Llama-3.2, Phi-3.5, and Mistral with dynamic model switching, chat sessions, and screenshot debugging capabilities. The implementation offers true local inference with no data transmission to external services, making it valuable for privacy-sensitive applications, offline AI workflows, and scenarios requiring local model deployment without complex GPU setup or native runtime dependencies.
Is this your product? Claim this listing with an email at your domain to post updates.
Is this your project?
Claim this listing to manage your page, access analytics, and unlock upgrades. Verification takes 60 seconds.
Share This Project
Embed Badge
Add this badge to your README:
[](https://hifriendbot.com/ai-list/web-llm-playwright/)
