{"id":29,"date":"2026-05-11T15:02:15","date_gmt":"2026-05-11T15:02:15","guid":{"rendered":"https:\/\/oliverng.com\/ai\/?p=29"},"modified":"2026-05-11T15:04:05","modified_gmt":"2026-05-11T15:04:05","slug":"thrift-and-tokens","status":"publish","type":"post","link":"https:\/\/oliverng.com\/ai\/2026\/05\/11\/thrift-and-tokens\/","title":{"rendered":"thrift and tokens (printing press)"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">Everyone knows token economy is \ud83d\udcb0<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">I came across this new abstraction layer for integrating external tooling into LLMs, called <a href=\"https:\/\/printingpress.dev\/\" target=\"_blank\" rel=\"noreferrer noopener\">printingpress<\/a>.dev.<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p class=\"wp-block-paragraph\">From an API spec, from a website with no public API, from a beloved community fan project &#8211; one command prints a token-efficient Go CLI, a Claude Code skill, an OpenClaw skill, and an MCP server. Peter Steinberger showed the way with discrawl and gogcli: a local SQLite mirror beats a remote API call, compound commands beat ten round trips, and an agent-native CLI beats raw HTTP. The press bakes that playbook into every binary it prints. Muscle memory for agents.<\/p>\n<\/blockquote>\n\n\n\n<p class=\"wp-block-paragraph\">It uses custom compiled CLI saving valuable token exchange commonly seen with MCP, connectors etc. MCP traffic is heavy. Part of why my exploration into local LLMs stopped was that I realized how much context an MCP exchange takes.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Similar to how exa, tavily MCPs clean up garbage from the web to provide LLM clean search, printingpress goes a step further and forgoes the whole MCP exchange for a CLI interface that runs locally and does all the dirty work more efficiently, saving your tokens. <\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The beauty of it is there is also a prompt kit that helps generate brand new CLIs from any service. So point it at a service and watch it go. <\/p>\n","protected":false},"excerpt":{"rendered":"<p>Everyone knows token economy is \ud83d\udcb0 I came across this new abstraction layer for integrating external tooling into LLMs, called printingpress.dev. From an API spec, from a website with no public API, from a beloved community fan project &#8211; one command prints a token-efficient Go CLI, a Claude Code skill, an OpenClaw skill, and an [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4],"tags":[],"class_list":["post-29","post","type-post","status-publish","format-standard","hentry","category-experimenting"],"_links":{"self":[{"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/posts\/29","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/comments?post=29"}],"version-history":[{"count":2,"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/posts\/29\/revisions"}],"predecessor-version":[{"id":31,"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/posts\/29\/revisions\/31"}],"wp:attachment":[{"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/media?parent=29"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/categories?post=29"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/oliverng.com\/ai\/wp-json\/wp\/v2\/tags?post=29"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}