Back to List
TechnologyAIBrowser ExtensionPrivacy

Tweeks (YC W25) Chrome Extension Leverages LLMs for Automated Userscript Generation, Sparks Debate on Privacy, Legality, and Open Source

Tweeks, a YC W25 Chrome extension, aims to 'de-enshittify' the web by automatically generating userscripts using Large Language Models (LLMs), similar to Greasemonkey/Tampermonkey. The extension captures current page content for LLM generation, with the resulting static scripts running locally. Key discussions revolve around technical feasibility, particularly with complex web structures and Manifest V3, and significant privacy concerns due to sending page content to LLMs during generation and the broad permissions required. Legal and platform risks, including potential site bans or lawsuits, are also central, with historical precedents like FB Purity cited. The business model and the extent of open-sourcing are debated, with the founders expressing caution about full open-source due to potential replication by larger entities. While users praise its ease of use for customization, the team acknowledges reliance on manual testing for accuracy and is exploring local small models for future cost and privacy improvements. The founders have disclosed DPA agreements with LLM providers regarding data retention and SOC II compliance.

News Hacker

Tweeks, a Chrome extension from YC W25, is designed to empower users to customize web pages by automatically generating userscripts through Large Language Models (LLMs). This functionality, akin to tools like Greasemonkey or Tampermonkey, aims to 'de-enshittify' the web. The process involves capturing the current web page content and sending it to an LLM for script generation. Once generated, these scripts operate statically and locally, applying to specific domains or patterns via `@match` rules.

The product has ignited extensive discussion across several critical areas. Technical feasibility is a major point, with concerns raised about the robustness of LLMs in handling complex web structures, deep nesting, iframes, and deliberately obfuscated CSS/JS. The team currently relies on a combination of manual testing and basic automated detection for script accuracy and selector matching, with many correctness validations still requiring manual regression testing. Future maintenance strategies include allowing users to pull updates, manually request selector updates, and the long-term vision of 'self-healing' scripts that periodically detect and fix selectors. Cross-browser portability is also a challenge, influenced by Manifest V3 and differences in browser extension APIs, making porting to Firefox or Safari non-trivial.

Privacy and permissions are central to the debate. Critics are concerned about data flow, as the founders admit that current page content is sent to the LLM during the 'generation' step. However, they clarify that generated scripts are static and execute locally, without passive logging. The extension requires broad page access permissions to run powerful scripts (reading/writing pages, notifications, localStorage), raising fears of permission abuse and malicious takeovers. The founders have stated they have Data Processing Agreements (DPAs) with LLM vendors that include non-training/non-retention clauses and claim SOC II compliance. However, a clause in their privacy policy regarding retaining the right to use generated scripts has been flagged as problematic and may be removed, with suggestions for greater transparency or open-sourcing to build trust.

The business model, open-source strategy, and investor concerns are also under scrutiny. Many question how Tweeks will monetize, as the founders acknowledge that a revenue model is not yet determined. There's a concern that widespread adoption could impact website revenue, making it difficult for Tweeks to directly capture that value. The community has repeatedly called for open-sourcing to protect user rights and prevent potential misuse if the company is acquired. However, the founders are cautious about full open-sourcing, fearing replication by larger companies for other purposes, and are leaning towards partial or gradual component release. The involvement of YC/VC funding is seen as enabling experimentation but also raises concerns about future acquisitions or commercialization potentially deviating from the product's original intent.

Legal and platform confrontation risks are significant. Historical precedents, such as the case of FB Purity, demonstrate that scripts modifying website appearance or functionality have faced platform bans or legal disputes. If Tweeks gains widespread adoption and significantly impacts platform revenue, large platforms could resort to legal and banning tactics to suppress such third-party tools. Some commentators believe that the actual impact might be overestimated due to limited general user adoption, while others warn of potential long-term legal battles. The startup team is advised to assess compliance risks and consider strategies like gentle modifications or communication with platforms to reduce the likelihood of direct conflict.

Related News

Technology

Hugging Face Introduces 'Skills' for AI/ML Task Definition, Compatible with Major Coding Agent Tools

Hugging Face has launched 'Skills,' a new framework designed to define AI/ML tasks such as dataset creation, model training, and evaluation. These 'Skills' are built to be compatible with leading coding agent tools, including OpenAI Codex, Anthropic's Claude Code, and Google De. This initiative aims to standardize and streamline the definition of various AI and machine learning tasks, facilitating integration across different development platforms.

Technology

Moonshine Voice: Fast and Accurate Automatic Speech Recognition (ASR) for Edge Devices Trends on GitHub

Moonshine Voice, a project by moonshine-ai, is gaining traction on GitHub Trending for its focus on delivering fast and accurate Automatic Speech Recognition (ASR) specifically designed for edge devices. Published on February 28, 2026, this initiative aims to optimize ASR capabilities for resource-constrained environments, making advanced speech recognition more accessible and efficient for a wide range of edge computing applications. The project's presence on GitHub Trending highlights its potential impact in the field of AI and edge device technology.

Technology

cc-switch: A Cross-Platform Desktop Assistant for Claude Code, Codex, OpenCode, and Gemini CLI Trending on GitHub

cc-switch is an innovative cross-platform desktop integrated assistant tool designed to streamline workflows for developers utilizing Claude Code, Codex, OpenCode, and Gemini CLI. Recently trending on GitHub, this tool aims to provide an all-in-one solution for managing these diverse coding and AI command-line interfaces, enhancing productivity and user experience across different operating systems. The project is authored by farion1231 and was published on February 28, 2026.