1"use strict";(globalThis.webpackChunkdocusaurus_template_openapi_docs=globalThis.webpackChunkdocusaurus_template_openapi_docs||[]).push([[2543],{2929(e,o,t){t.r(o),t.d(o,{assets:()=>r,contentTitle:()=>i,default:()=>m,frontMatter:()=>l,metadata:()=>n,toc:()=>d});var n=t(52796),a=t(74848),s=t(28453);const l={slug:"ogx-codex-cli",title:"Connect Codex CLI to Local and Hosted Models with OGX",authors:["skamenan7"],tags:["ogx","codex","responses-api","vllm","ollama","agents"],date:new Date("2026-06-30T00:00:00.000Z")},i=void 0,r={authorsImageUrls:[void 0]},d=[];function c(e){const o={code:"code",p:"p",...(0,s.R)(),...e.components};return(0,a.jsxs)(a.Fragment,{children:[(0,a.jsx)(o.p,{children:"Codex CLI brings an agent into the terminal, but teams often want that agent to use more than one model source. OGX gives Codex one OpenAI-compatible connection to local models, hosted models, and secured deployments."}),"\n",(0,a.jsxs)(o.p,{children:["With ",(0,a.jsx)(o.code,{children:"ogx connect codex"}),", you can launch Codex against the models exposed by a running OGX server without hand-editing your normal Codex configuration. OGX discovers the available models, writes a temporary Codex session home, forwards auth and provider data when needed, and starts Codex with a session that points at OGX."]}),"\n",(0,a.jsx)(o.p,{children:"This post walks through the command, the generated Codex profile, and a local-first path with Ollama and vLLM. The result is a small but useful workflow: Codex gets a familiar Responses API endpoint, and teams keep model access, auth, and provider choice in OGX instead of hard-coding those details into every developer tool."})]})}function m(e={}){const{wrapper:o}={...(0,s.R)(),...e.components};return o?(0,a.jsx)(o,{...e,children:(0,a.jsx)(c,{...e})}):c(e)}},28453(e,o,t){t.d(o,{R:()=>l,x:()=>i});var n=t(96540);const a={},s=n.createContext(a);function l(e){const o=n.useContext(s);return n.useMemo(function(){return"function"==typeof e?e(o):{...o,...e}},[o,e])}function i(e){let o;return o=e.disableParentContext?"function"==typeof e.components?e.components(a):e.components||a:l(e.components),n.createElement(s.Provider,{value:o},e.children)}},52796(e){e.exports=JSON.parse('{"permalink":"/blog/ogx-codex-cli","source":"@site/blog/2026-06-30-codex-ogx-cli.md","title":"Connect Codex CLI to Local and Hosted Models with OGX","description":"Codex CLI brings an agent into the terminal, but teams often want that agent to use more than one model source. OGX gives Codex one OpenAI-compatible connection to local models, hosted models, and secured deployments.","date":"2026-06-30T00:00:00.000Z","tags":[{"inline":true,"label":"ogx","permalink":"/blog/tags/ogx"},{"inline":true,"label":"codex","permalink":"/blog/tags/codex"},{"inline":true,"label":"responses-api","permalink":"/blog/tags/responses-api"},{"inline":true,"label":"vllm","permalink":"/blog/tags/vllm"},{"inline":true,"label":"ollama","permalink":"/blog/tags/ollama"},{"inline":true,"label":"agents","permalink":"/blog/tags/agents"}],"readingTime":4.61,"hasTruncateMarker":true,"authors":[{"name":"Sumanth Kamenani","url":"https://github.com/skamenan7","imageURL":"https://github.com/skamenan7.png","key":"skamenan7","page":null}],"frontMatter":{"slug":"ogx-codex-cli","title":"Connect Codex CLI to Local and Hosted Models with OGX","authors":["skamenan7"],"tags":["ogx","codex","responses-api","vllm","ollama","agents"],"date":"2026-06-30T00:00:00.000Z"},"unlisted":false,"prevItem":{"title":"The OGX Python SDK Has a New Foundation","permalink":"/blog/python-sdk-new-foundation"},"nextItem":{"title":"Under the Hood: How OGX Enforces Guardrails Inside the Agentic Loop","permalink":"/blog/guardrails-responses-api"}}')}}]);
Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.