--- title: This open-source extension lets you rewrite your X... description: Bouncer is a free, open-source browser extension that filters your X (Twitter) timeline using plain-language rules and a local LLM instead of simple keyword... canonical: https://daily.dev/posts/this-open-source-extension-lets-you-rewrite-your-x-algorithm-using-a-local-llm-and-it-healed-my-tim-gmg3o5zah twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: This open-source extension lets you rewrite your X algorithm using a local LLM, and it healed my timeline | daily.dev og:description: Bouncer is a free, open-source browser extension that filters your X (Twitter) timeline using plain-language rules and a local LLM instead of simple keyword... og:url: https://daily.dev/posts/this-open-source-extension-lets-you-rewrite-your-x-algorithm-using-a-local-llm-and-it-healed-my-tim-gmg3o5zah og:image: https://api.daily.dev/og/posts/gmG3o5zAh.png og:image:alt: This open-source extension lets you rewrite your X algorithm using a local LLM, and it healed my timeline og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # This open-source extension lets you rewrite your X algorithm using a local LLM, and it healed my timeline **[XDA Developers](https://daily.dev/sources/xda-developers)** · 4 min read · 1 upvotes · 0 comments ## Summary Bouncer is a free, open-source browser extension that filters your X (Twitter) timeline using plain-language rules and a local LLM instead of simple keyword muting. You describe what you don't want to see — AI slop, crypto, rage politics — and Bouncer reads each post's meaning as it loads, hiding matches in real time. It also includes a dedicated AI-content detection mode with adjustable confidence sliders for posts, comments, and images. While AI-text detection isn't perfect and produces occasional false positives, the 'view filtered' panel lets you quickly review and restore hidden posts. The extension integrates directly into X's interface with no separate app to launch. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is the Bouncer browser extension and how does it filter my X (Twitter) feed? Bouncer is a free, open-source browser extension that filters your X feed by reading each post's meaning with a local LLM rather than matching keywords. You describe unwanted content in plain English, such as AI, crypto, rage politics, or engagement bait, and Bouncer hides matching posts automatically, with a panel to review and undo filtered items. _Track hands-on write-ups of AI-powered browser tools like this one on daily.dev as they evolve._ ### How does Bouncer detect AI-generated slop content on X differently from regular filtering? Bouncer has a dedicated AI-detection mode that activates automatically when a filter phrase mentions AI content, such as 'AI slop,' flagging AI-generated text and images without needing exact keywords. It includes three adjustable confidence sliders (defaulting to 60% for posts, 50% for comments, 90% for images) to control detection aggressiveness, though false positives still occur on borderline posts. _Developers weighing AI-detection accuracy tradeoffs can follow real-world testing accounts of tools like this on daily.dev._ --- Tags: [#open-source](https://daily.dev/tags/open-source), [#devtools](https://daily.dev/tags/devtools), [#local-ai](https://daily.dev/tags/local-ai) [View this post on daily.dev](https://daily.dev/posts/this-open-source-extension-lets-you-rewrite-your-x-algorithm-using-a-local-llm-and-it-healed-my-tim-gmg3o5zah) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"This open-source extension lets you rewrite your X algorithm using a local LLM, and it healed my timeline","url":"https://daily.dev/posts/this-open-source-extension-lets-you-rewrite-your-x-algorithm-using-a-local-llm-and-it-healed-my-tim-gmg3o5zah","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/this-open-source-extension-lets-you-rewrite-your-x-algorithm-using-a-local-llm-and-it-healed-my-tim-gmg3o5zah"},"datePublished":"2026-07-19T19:34:57.720Z","dateModified":"2026-09-14T08:57:27.509Z","description":"Bouncer is a free, open-source browser extension that filters your X (Twitter) timeline using plain-language rules and a local LLM instead of simple keyword...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/64d9d4c7698f95106626042085337fcc?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/64d9d4c7698f95106626042085337fcc?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"XDA Developers","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"XDA Developers","logo":"https://media.daily.dev/image/upload/s--kCg6yyAP--/f_auto,q_auto/v1774964407/logos/xda-developers?_a=BAMAMiWQ0","url":"https://daily.dev/sources/xda-developers"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/this-open-source-extension-lets-you-rewrite-your-x-algorithm-using-a-local-llm-and-it-healed-my-tim-gmg3o5zah","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"open-source,devtools,local-ai","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"XDA Developers","item":"https://daily.dev/sources/xda-developers"},{"@type":"ListItem","position":3,"name":"This open-source extension lets you rewrite your X algorithm using a local LLM, and it healed my timeline"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/this-open-source-extension-lets-you-rewrite-your-x-algorithm-using-a-local-llm-and-it-healed-my-tim-gmg3o5zah#faq","mainEntity":[{"@type":"Question","name":"What is the Bouncer browser extension and how does it filter my X (Twitter) feed?","acceptedAnswer":{"@type":"Answer","text":"Bouncer is a free, open-source browser extension that filters your X feed by reading each post's meaning with a local LLM rather than matching keywords. You describe unwanted content in plain English, such as AI, crypto, rage politics, or engagement bait, and Bouncer hides matching posts automatically, with a panel to review and undo filtered items. Track hands-on write-ups of AI-powered browser tools like this one on daily.dev as they evolve."}},{"@type":"Question","name":"How does Bouncer detect AI-generated slop content on X differently from regular filtering?","acceptedAnswer":{"@type":"Answer","text":"Bouncer has a dedicated AI-detection mode that activates automatically when a filter phrase mentions AI content, such as 'AI slop,' flagging AI-generated text and images without needing exact keywords. It includes three adjustable confidence sliders (defaulting to 60% for posts, 50% for comments, 90% for images) to control detection aggressiveness, though false positives still occur on borderline posts. Developers weighing AI-detection accuracy tradeoffs can follow real-world testing accounts of tools like this on daily.dev."}}]} ```