--- title: Lemonade 11.5 Local AI Server Released With Completed... description: Lemonade 11.5, an open-source AMD-backed local AI server, has been released just one week after version 11.0. The headline feature is the completed Lemonade... canonical: https://daily.dev/posts/lemonade-11-5-local-ai-server-released-with-completed-lemonade-router-t0l4dmhxd twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Lemonade 11.5 Local AI Server Released With Completed Lemonade Router | daily.dev og:description: Lemonade 11.5, an open-source AMD-backed local AI server, has been released just one week after version 11.0. The headline feature is the completed Lemonade... og:url: https://daily.dev/posts/lemonade-11-5-local-ai-server-released-with-completed-lemonade-router-t0l4dmhxd og:image: https://api.daily.dev/og/posts/t0L4Dmhxd.png og:image:alt: Lemonade 11.5 Local AI Server Released With Completed Lemonade Router 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. # Lemonade 11.5 Local AI Server Released With Completed Lemonade Router **[Phoronix](https://daily.dev/sources/phoronix)** · 2 min read · 2 upvotes · 0 comments ## Summary Lemonade 11.5, an open-source AMD-backed local AI server, has been released just one week after version 11.0. The headline feature is the completed Lemonade Router, which automatically routes LLM queries to appropriate models based on configurable policies — including rule-based, classifier, semantic similarity, and LLM-as-router approaches. Policies can be defined via JSON files or the Lemonade GUI. Additional changes include a server-side job engine for managing multi-step recipes via /jobs endpoints (with pause/resume/delete support), and the lemond daemon can now act as an MCP client host to connect external stdio MCP servers. The server supports deployment across AMD Ryzen AI NPUs, Radeon GPUs, and CPUs on both Windows and Linux. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What new features are in Lemonade 11.5 for local AI serving on AMD hardware? Lemonade 11.5 completes the Lemonade Router, which steers LLM queries to different models based on rule, classifier, semantic similarity, or LLM-as-router policies defined in JSON or via the Lemonade GUI. It also adds a server-side job engine for multi-step recipes manageable through /jobs endpoints, and lets the lemonade daemon act as an MCP client host connecting external stdio MCP servers. _Track fast-moving local AI server releases like Lemonade's on daily.dev to keep deployment choices current._ ### How does the Lemonade Router decide which LLM to send a request to? It supports four routing policy types: rule-based, classifier-based, semantic similarity, and LLM-as-router, where a small LLM itself determines which model should handle a given request. Policies can be authored as JSON files or through the Lemonade GUI, giving developers flexible control over how queries get distributed across models deployed on Ryzen AI NPUs, Radeon GPUs, or CPUs. _Developers choosing model-routing strategies for local LLM setups can follow updates like this via daily.dev._ ## Similar posts on daily.dev - [AMD Making It Easier To Embed Lemonade AI Capabilities Into Other Apps](https://daily.dev/posts/amd-making-it-easier-to-embed-lemonade-ai-capabilities-into-other-apps-ynhc59a0x) · Phoronix · 0 upvotes · 0 comments - [Lemonade: Local AI for Text, Images, and Speech](https://daily.dev/posts/lemonade-local-ai-for-text-images-and-speech-izyg9llmu) · Hacker News · 2 upvotes · 0 comments - [First look: Lemonade serves up local AI with limitations](https://daily.dev/posts/first-look-lemonade-serves-up-local-ai-with-limitations-xejrequq1) · InfoWorld · 0 upvotes · 0 comments - [I switched my local AI setup to AMD's Lemonade after Nvidia support landed, and solved my local AI portability problem](https://daily.dev/posts/i-switched-my-local-ai-setup-to-amd-s-lemonade-after-nvidia-support-landed-and-solved-my-local-ai-p-ede18yoda) · XDA Developers · 1 upvotes · 0 comments - [AMD Releases Lemonade 11.0 Local AI Server With Text-To-Speech, Other New Features](https://daily.dev/posts/amd-releases-lemonade-11-0-local-ai-server-with-text-to-speech-other-new-features-mkmvvd9dt) · Phoronix · 2 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#mcp](https://daily.dev/tags/mcp), [#amd](https://daily.dev/tags/amd), [#local-ai](https://daily.dev/tags/local-ai) [View this post on daily.dev](https://daily.dev/posts/lemonade-11-5-local-ai-server-released-with-completed-lemonade-router-t0l4dmhxd) ```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":"Lemonade 11.5 Local AI Server Released With Completed Lemonade Router","url":"https://daily.dev/posts/lemonade-11-5-local-ai-server-released-with-completed-lemonade-router-t0l4dmhxd","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/lemonade-11-5-local-ai-server-released-with-completed-lemonade-router-t0l4dmhxd"},"datePublished":"2026-07-22T22:38:23.703Z","dateModified":"2026-09-14T06:38:21.788Z","description":"Lemonade 11.5, an open-source AMD-backed local AI server, has been released just one week after version 11.0. The headline feature is the completed Lemonade...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/520b6e1a8df30bec5cb438c025a73dfa?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/520b6e1a8df30bec5cb438c025a73dfa?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Phoronix","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":"Phoronix","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/6a26ba379dd64932830aa0c9803dd7ee","url":"https://daily.dev/sources/phoronix"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/lemonade-11-5-local-ai-server-released-with-completed-lemonade-router-t0l4dmhxd","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,mcp,amd,local-ai","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Phoronix","item":"https://daily.dev/sources/phoronix"},{"@type":"ListItem","position":3,"name":"Lemonade 11.5 Local AI Server Released With Completed Lemonade Router"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/lemonade-11-5-local-ai-server-released-with-completed-lemonade-router-t0l4dmhxd#faq","mainEntity":[{"@type":"Question","name":"What new features are in Lemonade 11.5 for local AI serving on AMD hardware?","acceptedAnswer":{"@type":"Answer","text":"Lemonade 11.5 completes the Lemonade Router, which steers LLM queries to different models based on rule, classifier, semantic similarity, or LLM-as-router policies defined in JSON or via the Lemonade GUI. It also adds a server-side job engine for multi-step recipes manageable through /jobs endpoints, and lets the lemonade daemon act as an MCP client host connecting external stdio MCP servers. Track fast-moving local AI server releases like Lemonade's on daily.dev to keep deployment choices current."}},{"@type":"Question","name":"How does the Lemonade Router decide which LLM to send a request to?","acceptedAnswer":{"@type":"Answer","text":"It supports four routing policy types: rule-based, classifier-based, semantic similarity, and LLM-as-router, where a small LLM itself determines which model should handle a given request. Policies can be authored as JSON files or through the Lemonade GUI, giving developers flexible control over how queries get distributed across models deployed on Ryzen AI NPUs, Radeon GPUs, or CPUs. Developers choosing model-routing strategies for local LLM setups can follow updates like this via daily.dev."}}]} ```