{"id":958,"date":"2026-05-06T19:47:00","date_gmt":"2026-05-07T00:47:00","guid":{"rendered":"https:\/\/www.jkspeaks.com\/wordpress\/?p=958"},"modified":"2026-07-05T11:46:09","modified_gmt":"2026-07-05T16:46:09","slug":"codeburn-open-source-for-cost-visibility","status":"publish","type":"post","link":"https:\/\/www.jkspeaks.com\/wordpress\/ai-data\/codeburn-open-source-for-cost-visibility\/","title":{"rendered":"Codeburn: For cost visibility"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">\ud83d\udea8AI developers or engineering team leaders, you need to look at this.\ud83d\udea8<br \/><br \/>Over the last few months, my usage of <a href=\"https:\/\/www.linkedin.com\/search\/results\/all\/?keywords=%23claude&amp;origin=HASH_TAG_FROM_FEED\">#Claude<\/a> has skyrocketed. As someone who spent years in the BI space, I have a natural itch to analyze patterns. Yet, I found myself hitting a wall with a fundamental question: Where exactly are my tokens getting spent?<br \/><br \/>I recently tested an open-source tool called Codeburn \u2728, and the &#8220;magic&#8221; is in its simplicity. You can just run &#8220;npx codeburn&#8221; on your PowerShell, and you can see this in action (no persistence).<br \/><br \/>While many of us are heavy users of Claude, our professional workflows are increasingly hybrid, spanning tools like Cursor, Codex, etc. Codeburn provides a unified, local TUI dashboard that parses your session data directly. Because it operates locally, there are no API keys to manage and no SaaS privacy concerns. Just raw, actionable observability!<br \/><br \/>In under a minute, I had visibility into:<br \/>\u2022 Which models I&#8217;m actually using (vs. thinking I&#8217;m using)<br \/>\u2022 Where my token spend clusters are (by request type, by tool, by time)<br \/>\u2022 The silent killers, whose &#8220;quick&#8221; tasks were quietly driving up costs<br \/>\u2022 Concrete optimizations levers to test<br \/><br \/>For consultants and practitioners piloting AI agents, this level of visibility is table-stakes. We often say you can\u2019t analyze or improve what you can\u2019t measure; in the world of agentic workflows, this is critical.<br \/><br \/>\ud83d\ude80I strongly recommend that developers use this for their individual cost visibility during the experimentation\/development phase. The dashboard does the storytelling for you.<br \/><br \/>\ud83d\udc49<strong>Git Repo<\/strong>: <a href=\"https:\/\/github.com\/getagentseal\/codeburn\">https:\/\/github.com\/getagentseal\/codeburn<\/a><br \/><br \/>If you have used other tools like codeburn, please share in the comments.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">DataDriven #TokenEconomics #AIEngineering #LLMObservability #DeveloperTools #AgenticAI #SixSigma #DMAIC<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><a href=\"https:\/\/www.jkspeaks.com\/wordpress\/wp-content\/uploads\/2026\/06\/image.jpeg\"><img loading=\"lazy\" decoding=\"async\" width=\"800\" height=\"459\" src=\"https:\/\/www.jkspeaks.com\/wordpress\/wp-content\/uploads\/2026\/06\/image.jpeg\" alt=\"\" class=\"wp-image-959\" srcset=\"https:\/\/www.jkspeaks.com\/wordpress\/wp-content\/uploads\/2026\/06\/image.jpeg 800w, https:\/\/www.jkspeaks.com\/wordpress\/wp-content\/uploads\/2026\/06\/image-300x172.jpeg 300w, https:\/\/www.jkspeaks.com\/wordpress\/wp-content\/uploads\/2026\/06\/image-768x441.jpeg 768w\" sizes=\"auto, (max-width: 800px) 100vw, 800px\" \/><\/a><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Get visibility into where you are burning tokens. An open-source repo solves it for you. No API keys needed.<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"_kad_post_transparent":"","_kad_post_title":"","_kad_post_layout":"","_kad_post_sidebar_id":"","_kad_post_content_style":"","_kad_post_vertical_padding":"","_kad_post_feature":"","_kad_post_feature_position":"","_kad_post_header":false,"_kad_post_footer":false,"_kad_post_classname":"","footnotes":"","_links_to":"","_links_to_target":""},"categories":[21],"tags":[182,123,179,183,226],"class_list":["post-958","post","type-post","status-publish","format-standard","hentry","category-ai-data","tag-agentic","tag-ai","tag-claude","tag-cost","tag-economics"],"acf":{"phase":"3","cluster":"Technical","topics":["AI Engineering","Claude","Ops"]},"_links":{"self":[{"href":"https:\/\/www.jkspeaks.com\/wordpress\/wp-json\/wp\/v2\/posts\/958","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.jkspeaks.com\/wordpress\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.jkspeaks.com\/wordpress\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.jkspeaks.com\/wordpress\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.jkspeaks.com\/wordpress\/wp-json\/wp\/v2\/comments?post=958"}],"version-history":[{"count":2,"href":"https:\/\/www.jkspeaks.com\/wordpress\/wp-json\/wp\/v2\/posts\/958\/revisions"}],"predecessor-version":[{"id":1095,"href":"https:\/\/www.jkspeaks.com\/wordpress\/wp-json\/wp\/v2\/posts\/958\/revisions\/1095"}],"wp:attachment":[{"href":"https:\/\/www.jkspeaks.com\/wordpress\/wp-json\/wp\/v2\/media?parent=958"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.jkspeaks.com\/wordpress\/wp-json\/wp\/v2\/categories?post=958"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.jkspeaks.com\/wordpress\/wp-json\/wp\/v2\/tags?post=958"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}