--- title: GitHub - experientiallabs/world-model-optimizer: Build... description: World Model Optimizer (WMO) is an open-source tool that converts collected agent traces into smaller, fine-tuned models using the Tinker API. The `wmo... canonical: https://daily.dev/posts/github---experientiallabs-world-model-optimizer-build-continually-improving-models-on-your-agent-tr-izoxlkfkn twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: GitHub - experientiallabs/world-model-optimizer: Build continually improving models on your agent traces by distilling frontier open models | daily.dev og:description: World Model Optimizer (WMO) is an open-source tool that converts collected agent traces into smaller, fine-tuned models using the Tinker API. The `wmo... og:url: https://daily.dev/posts/github---experientiallabs-world-model-optimizer-build-continually-improving-models-on-your-agent-tr-izoxlkfkn og:image: https://api.daily.dev/og/posts/IzoxlKFKn.png og:image:alt: GitHub - experientiallabs/world-model-optimizer: Build continually improving models on your agent traces by distilling frontier open models 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. # GitHub - experientiallabs/world-model-optimizer: Build continually improving models on your agent traces by distilling frontier open models **[Hacker News](https://daily.dev/sources/hn)** · 5 min read · 1 upvotes · 0 comments ## Summary World Model Optimizer (WMO) is an open-source tool that converts collected agent traces into smaller, fine-tuned models using the Tinker API. The `wmo optimize` command handles distillation and routing policy fitting, while `wmo serve` exposes an endpoint that intelligently routes requests between frontier and smaller models — achieving frontier-level quality at 27% lower cost on RouterBench. The pipeline supports continuous improvement: as new traces arrive, models can be retrained. WMO also includes world models that simulate agent environments for closed-loop testing and optimization, with E2B sandbox support for isolated evaluation. The CLI covers the full workflow from provider registration and trace ingestion to model serving and reporting. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [MoE Routing for Faster, Cheaper AI Inference](https://daily.dev/posts/moe-routing-for-faster-cheaper-ai-inference-9qjnbnbah) · DigitalOcean Community · 0 upvotes · 0 comments - [Micro-Agent: Beat Frontier Models with Collaboration inside Model API](https://daily.dev/posts/micro-agent-beat-frontier-models-with-collaboration-inside-model-api-j31g6z1i8) · vLLM · 1 upvotes · 0 comments - [Medium](https://daily.dev/posts/medium-xaxoilist) · Medium · 0 upvotes · 0 comments --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#python](https://daily.dev/tags/python), [#llm](https://daily.dev/tags/llm), [#ai-agents](https://daily.dev/tags/ai-agents) [View this post on daily.dev](https://daily.dev/posts/github---experientiallabs-world-model-optimizer-build-continually-improving-models-on-your-agent-tr-izoxlkfkn) ```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":"GitHub - experientiallabs/world-model-optimizer: Build continually improving models on your agent traces by distilling frontier open models","url":"https://daily.dev/posts/github---experientiallabs-world-model-optimizer-build-continually-improving-models-on-your-agent-tr-izoxlkfkn","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/github---experientiallabs-world-model-optimizer-build-continually-improving-models-on-your-agent-tr-izoxlkfkn"},"datePublished":"2026-07-30T19:47:46.809Z","dateModified":"2026-07-30T20:36:49.210Z","description":"World Model Optimizer (WMO) is an open-source tool that converts collected agent traces into smaller, fine-tuned models using the Tinker API. The `wmo...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/d784d1258e55ce82b8f8bd8e0781cb98?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/d784d1258e55ce82b8f8bd8e0781cb98?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Hacker News","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":"Hacker News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/hn","url":"https://daily.dev/sources/hn"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/github---experientiallabs-world-model-optimizer-build-continually-improving-models-on-your-agent-tr-izoxlkfkn","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,python,llm,ai-agents","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hacker News","item":"https://daily.dev/sources/hn"},{"@type":"ListItem","position":3,"name":"GitHub - experientiallabs/world-model-optimizer: Build continually improving models on your agent traces by distilling frontier open models"}]} ```