SShortSingh.
TopTechnologyAI & MLStartupsProgrammingScienceBusinessFinanceCrypto & Web3World
Back to feed
Programming

NeoBrowser Lets AI Agents Control Chrome Using Your Existing Login Sessions

0
·1 views

NeoBrowser is an open-source Model Context Protocol (MCP) server that enables AI agents to control a real Chrome browser instance. Unlike headless browser tools, it operates using the user's already-authenticated browser sessions, removing the need to re-enter credentials. The project is hosted on GitHub under the handle pitiflautico and has gained early attention on Hacker News. This approach allows AI-driven automation to interact with websites exactly as a logged-in user would. The tool is positioned for developers looking to integrate browser automation into MCP-compatible AI workflows.

Read the full story at Hacker News

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Log in to join the discussion and vote.

Log in

Related stories

0
ProgrammingDEV Community ·

Moonshot AI's Kimi K2 API Offers Native Multimodal Support with 256K Context Window

Moonshot AI has released Kimi K2, a Mixture-of-Experts model accessible via a standard chat-completions API endpoint at api.moonshot.cn/v1. The model supports both text and image inputs natively, allowing developers to pass image URLs or base64 data directly within message content arrays. Kimi K2 offers a 256K token context window and supports additional features including function calling, streaming responses, and agent-swarm workflows. Integration follows the same request structure used by other OpenAI-compatible APIs, making it straightforward to adopt via cURL or Python. Developers are advised to manage image resolution carefully, as images consume tokens against the shared context window and affect billing.

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

How to Implement UPI AutoPay Recurring Payments in Flutter Apps

A technical guide published on DEV Community explains how developers can integrate UPI AutoPay — NPCI's recurring payment system — into Flutter applications. UPI AutoPay allows customers to approve a payment mandate once inside their UPI app, after which merchants can debit their accounts on a scheduled basis without repeated approvals. The implementation requires four Flutter dependencies: http, url_launcher, webview_flutter, and uni_links, each serving a distinct role in the payment flow. A key security recommendation in the guide warns developers never to embed payment gateway credentials inside the Flutter app, instead routing all gateway communication through a backend server. The approach is described as gateway-agnostic, meaning the same Flutter code works across major Indian payment processors such as Razorpay, Cashfree, and PayU.

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

One Apple Health MCP Server Can Now Connect to Eight AI Clients Simultaneously

A newly published setup guide demonstrates how a single Model Context Protocol (MCP) server can feed Apple Health data to eight different AI clients, including Claude Desktop, Cursor, ChatGPT, and Codex CLI. The server exposes eight read-only tools capable of querying 190 Apple Health metrics locally, with no network calls or external dependencies. While each client stores its configuration file in a different location, the core server command remains identical across all platforms. The 84 kB npm package pulls live data directly from an iPhone via iCloud, enabling natural-language queries about metrics like HRV, sleep, and resting heart rate. Full configuration instructions and troubleshooting guidance are available at healthexport.dev.

0 comments Read more at DEV Community