Muhammed Nazeem writes about a browser extension that provides a sidebar and web interface to interact with local large language models while browsing. It supports various providers like Ollama or OpenAI-compatible APIs, allowing users to chat with files such as PDFs through the sidebar.
- Includes vision model support and internet search capabilities.
- Features beta versions of tab mention, MCP client support, and memory functionality.
- Compatible with Gemini Nano (beta) via Chrome.
Page Assist is an open-source browser extension that provides a sidebar and web interface for interacting with local large language models from any webpage. It allows users to chat about current website content by connecting the tool to providers like Ollama or OpenAI API compatible endpoints. The software supports several browsers, including Chromium-based options and Firefox.
- Data is stored locally within browser storage to maintain privacy
- Features keyboard shortcuts such as Ctrl+Shift+Y for rapid sidebar access
- Compatible with various local model providers, including Chrome AI (Gemini Nano)
Mozilla is expressing strong opposition to Google's implementation of a Prompt API in the Chrome and Edge browsers, which allows web pages to interact directly with local machine learning models like Gemini Nano. The organization warns that this integration could undermine web interoperability and neutrality by forcing developers to optimize for specific vendor models and adhere to proprietary content policies.
Main points:
- Risk of creating model-specific code paths that harm browser compatibility.
- Concerns regarding the imposition of vendor-specific usage rules on an open platform.
- Disagreement over whether there is a genuine groundswell of developer support for the API.
Google Chrome is testing **WebMCP**, a new system to help AI agents interact with websites more efficiently. Currently, AI struggles with websites, often relying on slow and unreliable methods. WebMCP lets websites offer AI tools directly through a browser API, potentially lowering costs and speeding up development. It works alongside existing AI protocols like Anthropic’s MCP and focuses on improving how AI assists *with* human web use, not replacing backend systems. Essentially, it's aiming to be a standard way for AI to "talk" to websites.
A review of Google's Auto Browse agent, testing its ability to perform various online tasks, from playing web games to managing playlists and scanning emails. The agent shows promise but requires significant supervision and struggles with certain tasks, particularly those involving prolonged monitoring or complex interfaces.
Thorium is a Chromium-based browser that prioritizes speed and efficiency by stripping back unnecessary Google services and optimizing performance. It offers faster page loads, smoother scrolling, and lower CPU usage compared to Chrome, but has less frequent updates and potential DRM limitations.
FailSafe is an open-source, modular framework designed to automate the verification of textual claims. It employs a multi-stage pipeline that integrates Large Language Models (LLMs) with retrieval-augmented generation (RAG) techniques.
A Chrome extension using AI (LLaVa) to generate descriptive filenames for images when downloading them.
chrome://settings/content/all?searchSubpage=example.com
Allow user to edit web-page textareas with Emacs (and other editors).