{"id":1084,"date":"2026-06-11T10:12:14","date_gmt":"2026-06-11T10:12:14","guid":{"rendered":"https:\/\/convly.ai\/opencode-explained-2026\/"},"modified":"2026-06-11T10:15:27","modified_gmt":"2026-06-11T10:15:27","slug":"opencode-explained-2026","status":"publish","type":"post","link":"https:\/\/convly.ai\/ar\/opencode-explained-2026\/","title":{"rendered":"What Is OpenCode? The Open-Source AI Coding Agent That Dethroned Cursor (2026)"},"content":{"rendered":"<p>In 2026, the most-talked-about AI coding tool isn&#8217;t from Anthropic, OpenAI, or a billion-dollar startup \u2014 it&#8217;s <strong>OpenCode<\/strong>, an open-source agent that lives in your terminal and works with <em>any<\/em> model you choose. It topped the year&#8217;s AI dev-tool rankings, displacing Cursor, and crossed <strong>160,000 GitHub stars<\/strong> with millions of developers using it monthly. Here&#8217;s what OpenCode is, why it caught fire, and how it stacks up against Claude Code.<\/p>\n<div class=\"convly-tldr\">\n<h3>\u0627\u0644\u0648\u062c\u0628\u0627\u062a \u0627\u0644\u0631\u0626\u064a\u0633\u064a\u0629<\/h3>\n<ul>\n<li><strong>OpenCode<\/strong> is an open-source, terminal-native AI coding agent from the team behind SST (Anomaly Innovations).<\/li>\n<li><strong>Model-agnostic:<\/strong> works with <strong>75+ providers<\/strong> \u2014 Claude, GPT-5.5, Gemini, DeepSeek, Grok, or local models via <strong>\u0623\u0648\u0644\u0627\u0645\u0627<\/strong> \u2014 from one interface.<\/li>\n<li><strong>LSP-powered:<\/strong> it reads your code through Language Server Protocol, so the model gets real type info and live compiler diagnostics, not just text.<\/li>\n<li><strong>Momentum:<\/strong> ~160K GitHub stars, ~7.5M monthly developers, and #1 on the June 2026 dev-tool power rankings (ahead of Cursor).<\/li>\n<li><strong>Trade-off vs Claude Code:<\/strong> more thorough but reportedly ~78% slower on the same model \u2014 it favors depth over speed.<\/li>\n<\/ul>\n<\/div>\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_84 counter-flat ez-toc-counter ez-toc-container-direction\">\n<label for=\"ez-toc-cssicon-toggle-item-6a2db366695c5\" class=\"ez-toc-cssicon-toggle-label\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">\u062a\u0628\u062f\u064a\u0644<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #000000;color:#000000\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewbox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #000000;color:#000000\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewbox=\"0 0 24 24\" version=\"1.2\" baseprofile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/label><input type=\"checkbox\"  id=\"ez-toc-cssicon-toggle-item-6a2db366695c5\"  aria-label=\"\u062a\u0628\u062f\u064a\u0644\" \/><nav><ul class='ez-toc-list ez-toc-list-level-1' ><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/convly.ai\/ar\/opencode-explained-2026\/#What_is_OpenCode\" >What is OpenCode?<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/convly.ai\/ar\/opencode-explained-2026\/#The_killer_feature_it_works_with_any_model\" >The killer feature: it works with any model<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/convly.ai\/ar\/opencode-explained-2026\/#How_LSP_makes_it_write_better_code\" >How LSP makes it write better code<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/convly.ai\/ar\/opencode-explained-2026\/#Multi-session_and_other_features\" >Multi-session and other features<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/convly.ai\/ar\/opencode-explained-2026\/#OpenCode_vs_Claude_Code_%E2%80%94_the_honest_comparison\" >OpenCode vs Claude Code \u2014 the honest comparison<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/convly.ai\/ar\/opencode-explained-2026\/#OpenCode_vs_Cursor_Codex_and_Aider\" >OpenCode vs Cursor, Codex, and Aider<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/convly.ai\/ar\/opencode-explained-2026\/#When_to_use_which\" >When to use which<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/convly.ai\/ar\/opencode-explained-2026\/#How_to_get_started\" >How to get started<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-9\" href=\"https:\/\/convly.ai\/ar\/opencode-explained-2026\/#FAQ\" >\u0627\u0644\u0623\u0633\u0626\u0644\u0629 \u0627\u0644\u0634\u0627\u0626\u0639\u0629<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-10\" href=\"https:\/\/convly.ai\/ar\/opencode-explained-2026\/#Bottom_line\" >\u062e\u0644\u0627\u0635\u0629 \u0627\u0644\u0642\u0648\u0644<\/a><\/li><li class='ez-toc-page-1'><a class=\"ez-toc-link ez-toc-heading-11\" href=\"https:\/\/convly.ai\/ar\/opencode-explained-2026\/#Related_articles\" >\u0645\u0642\u0627\u0644\u0627\u062a \u0630\u0627\u062a \u0635\u0644\u0629<\/a><\/li><\/ul><\/nav><\/div>\n<h2><span class=\"ez-toc-section\" id=\"What_is_OpenCode\"><\/span>What is OpenCode?<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>OpenCode is an <strong>open-source AI coding agent built for the terminal<\/strong>. Instead of a separate IDE or a web app, it gives you a terminal user interface (TUI) where an AI agent can read, write, and edit code, run shell commands, and navigate a whole codebase \u2014 all from the command line. It&#8217;s developed by <strong>Anomaly Innovations<\/strong>, the team formerly known as <strong>SST<\/strong> (Serverless Stack).<\/p>\n<p>Its rise has been remarkable: it hit #1 on Hacker News in March 2026 and, by June, topped LogRocket&#8217;s AI dev-tool power rankings \u2014 knocking Cursor off the top spot it had held for much of the AI-coding era.<\/p>\n<div class=\"convly-specs\">\n<div><strong>\u0627\u0644\u0623\u062f\u0627\u0629<\/strong><span>OpenCode \u2014 open-source AI coding agent<\/span><\/div>\n<div><strong>\u0635\u0627\u0646\u0639<\/strong><span>Anomaly Innovations (the SST team)<\/span><\/div>\n<div><strong>Interface<\/strong><span>Terminal (native TUI)<\/span><\/div>\n<div><strong>\u0627\u0644\u0646\u0645\u0627\u0630\u062c<\/strong><span>75+ providers, incl. local Ollama\/vLLM<\/span><\/div>\n<div><strong>Code awareness<\/strong><span>Language Server Protocol (LSP) \u2014 18+ languages<\/span><\/div>\n<div><strong>Popularity<\/strong><span>~160K GitHub stars \u00b7 ~7.5M monthly developers<\/span><\/div>\n<div><strong>\u0627\u0644\u062a\u0631\u062e\u064a\u0635<\/strong><span>Open source<\/span><\/div>\n<div><strong>\u0627\u0644\u0623\u0641\u0636\u0644 \u0644\u0640<\/strong><span>Developers who want model choice, privacy, and thoroughness<\/span><\/div>\n<\/div>\n<h2><span class=\"ez-toc-section\" id=\"The_killer_feature_it_works_with_any_model\"><\/span>The killer feature: it works with any model<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>The single biggest reason for OpenCode&#8217;s success is <strong>freedom of model choice<\/strong>. Most AI coding tools are tied to one lab: Claude Code requires Anthropic, OpenAI&#8217;s Codex requires OpenAI, and Cursor defaults to Claude or GPT. OpenCode is <strong>provider-agnostic by design<\/strong> \u2014 it connects to <strong>75+ model providers<\/strong> from the same interface, on the same project.<\/p>\n<p>That means you can run:<\/p>\n<ul>\n<li><strong>Claude, GPT-5.5, Gemini, DeepSeek, or Grok<\/strong> via their APIs,<\/li>\n<li><strong>Local models through <a href=\"\/ar\/what-is-ollama-complete-guide-2026\/\">\u0623\u0648\u0644\u0627\u0645\u0627<\/a> or vLLM<\/strong> \u2014 keeping your code entirely on your own machine,<\/li>\n<li>or mix and match per task, even switching mid-project.<\/li>\n<\/ul>\n<p>For privacy-conscious teams and anyone who doesn&#8217;t want to be locked to a single vendor&#8217;s pricing or rate limits, that flexibility is the whole pitch. Pair it with one of the <a href=\"\/ar\/best-local-llm-for-coding-2026\/\">best local LLMs for coding<\/a> and you get a capable, fully private coding agent that costs nothing per token.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"How_LSP_makes_it_write_better_code\"><\/span>How LSP makes it write better code<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>OpenCode&#8217;s other standout is technical: it <strong>sees your code through the Language Server Protocol (LSP)<\/strong> \u2014 the same engine that powers autocomplete and error-checking in editors like VS Code. For TypeScript, Python (Pyright), Rust (rust-analyzer), Go (gopls), C\/C++ (clangd), Java, and 18+ other languages, the agent receives <strong>actual type information, function signatures, import paths, and live compiler diagnostics<\/strong> \u2014 not just the raw text of your files.<\/p>\n<p>This creates a feedback loop: the agent writes code, sees the compiler&#8217;s real errors and type mismatches, and corrects itself. The payoff is measurable. In one head-to-head test (DataCamp), OpenCode generated <strong>21 more tests on average<\/strong> than Claude Code running the <em>same underlying model<\/em> \u2014 thoroughness that traces directly to that LSP feedback loop.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Multi-session_and_other_features\"><\/span>Multi-session and other features<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>Beyond models and LSP, OpenCode ships the conveniences power users expect:<\/p>\n<ul>\n<li><strong>Multi-session<\/strong> \u2014 run several agents in parallel on one project (e.g., one researching while another implements).<\/li>\n<li><strong>opencode zen<\/strong> \u2014 a curated list of recommended models so you&#8217;re not guessing which to use.<\/li>\n<li><strong>Shareable links<\/strong> \u2014 share a session for review or collaboration.<\/li>\n<li><strong>Claude Pro integration<\/strong> \u2014 use an existing Claude subscription as a backend.<\/li>\n<\/ul>\n<h2><span class=\"ez-toc-section\" id=\"OpenCode_vs_Claude_Code_%E2%80%94_the_honest_comparison\"><\/span>OpenCode vs Claude Code \u2014 the honest comparison<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>These two are the headline rivalry of 2026 AI coding, and they optimize for <strong>different things<\/strong>:<\/p>\n<table class=\"convly-vs\">\n<thead>\n<tr>\n<th>\u0627\u0644\u0628\u064f\u0639\u062f<\/th>\n<th>OpenCode<\/th>\n<th>\u0643\u0648\u062f \u0643\u0644\u0648\u062f<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>\u0627\u062e\u062a\u064a\u0627\u0631 \u0627\u0644\u0637\u0631\u0627\u0632<\/td>\n<td class=\"convly-vs-winner\">75+ providers (incl. local)<\/td>\n<td>\u0623\u0646\u062b\u0631\u0648\u0628\u0643 \u0641\u0642\u0637<\/td>\n<\/tr>\n<tr>\n<td>Privacy \/ local models<\/td>\n<td class=\"convly-vs-winner\">Yes (Ollama\/vLLM)<\/td>\n<td>Cloud (Anthropic)<\/td>\n<\/tr>\n<tr>\n<td>Speed (same model)<\/td>\n<td>~78% slower<\/td>\n<td class=\"convly-vs-winner\">Faster, highly tuned<\/td>\n<\/tr>\n<tr>\n<td>Thoroughness<\/td>\n<td class=\"convly-vs-winner\">More tests, LSP-driven<\/td>\n<td>Polished, efficient<\/td>\n<\/tr>\n<tr>\n<td>\u0627\u0644\u062a\u0643\u0644\u0641\u0629<\/td>\n<td class=\"convly-vs-winner\">Open source + your model<\/td>\n<td>Anthropic pricing<\/td>\n<\/tr>\n<tr>\n<td>Polish on complex autonomy<\/td>\n<td>\u062c\u064a\u062f<\/td>\n<td class=\"convly-vs-winner\">\u0645\u0645\u062a\u0627\u0632<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>The most important honest caveat: OpenCode is reportedly <strong>~78% slower than Claude Code<\/strong> on the same underlying model. That&#8217;s a real benchmark figure, and it reflects a genuine design choice \u2014 OpenCode&#8217;s defaults prioritize thoroughness (and that LSP loop) over raw latency, while Anthropic has poured engineering into making Claude Code fast and polished.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"OpenCode_vs_Cursor_Codex_and_Aider\"><\/span>OpenCode vs Cursor, Codex, and Aider<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>OpenCode&#8217;s rise is best understood against the wider field of 2026 coding tools:<\/p>\n<ul>\n<li><strong>vs Cursor<\/strong> \u2014 Cursor is a polished, paid AI-first <em>IDE<\/em>; OpenCode is a free, open-source <em>terminal<\/em> agent. Cursor is friendlier for newcomers and GUI lovers, while OpenCode wins on model freedom, privacy, and cost. OpenCode overtaking Cursor in the rankings is the headline upset of the year.<\/li>\n<li><strong>vs OpenAI Codex<\/strong> \u2014 Codex is tied to OpenAI&#8217;s models; OpenCode runs any of 75+ providers. If you want GPT <em>\u0648<\/em> the option to switch to Claude or a local model later, OpenCode keeps that door open.<\/li>\n<li><strong>vs Aider<\/strong> \u2014 Aider is the other beloved open-source terminal coder. OpenCode&#8217;s edge is its richer TUI, multi-session support, and deep LSP integration; Aider stays a lean, git-centric favorite. Many developers moved from Aider to OpenCode for the polish.<\/li>\n<\/ul>\n<p>The throughline: OpenCode is the option that refuses to lock you in \u2014 to a vendor, a model, or a GUI.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"When_to_use_which\"><\/span>When to use which<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<ul>\n<li><strong>Use OpenCode<\/strong> when <strong>model choice or privacy matters<\/strong> \u2014 you want to run local models, avoid vendor lock-in, or pick the cheapest capable model per task. It&#8217;s also a natural fit if you value test coverage and thoroughness.<\/li>\n<li><strong>Use <a href=\"\/ar\/claude-code-review-2026\/\">\u0643\u0648\u062f \u0643\u0644\u0648\u062f<\/a><\/strong> when <strong>speed and polish on complex autonomous tasks<\/strong> are the priority and you&#8217;re happy on Anthropic&#8217;s models.<\/li>\n<\/ul>\n<p>They&#8217;re not really competing for the same user in every scenario \u2014 they&#8217;re tuned for different constraints. Many developers keep both. For the broader field, see our roundup of the <a href=\"\/ar\/best-ai-coding-assistants\/\">best AI coding assistants<\/a>, and if open-source agents are your thing, OpenCode pairs naturally with tools like <a href=\"\/ar\/hermes-agent-explained-2026\/\">Hermes Agent<\/a>.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"How_to_get_started\"><\/span>How to get started<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<ol>\n<li><strong>\u0627\u0644\u062a\u062b\u0628\u064a\u062a<\/strong> OpenCode from its site (<code>opencode.ai<\/code>) or GitHub \u2014 it runs in your terminal.<\/li>\n<li><strong>Connect a model<\/strong> \u2014 add an API key for Claude\/GPT\/Gemini, or point it at a local model via Ollama for a private, zero-cost setup.<\/li>\n<li><strong>Open a project<\/strong> and start prompting \u2014 the agent reads your codebase through LSP, so it understands types and errors from the first message.<\/li>\n<li><strong>Scale up<\/strong> with multi-session when you want parallel agents on the same repo.<\/li>\n<\/ol>\n<h2><span class=\"ez-toc-section\" id=\"FAQ\"><\/span>\u0627\u0644\u0623\u0633\u0626\u0644\u0629 \u0627\u0644\u0634\u0627\u0626\u0639\u0629<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<h3>What is OpenCode?<\/h3>\n<p>OpenCode is an open-source, terminal-native AI coding agent from the SST team (Anomaly Innovations). It lets an AI read, write, and run code in your terminal, works with 75+ model providers, and uses the Language Server Protocol to understand your code&#8217;s types and errors. It topped the 2026 AI dev-tool rankings with ~160K GitHub stars.<\/p>\n<h3>Is OpenCode free?<\/h3>\n<p>The tool itself is open source and free. You only pay for whatever model you connect it to \u2014 and if you run a local model through Ollama or vLLM, even that is free beyond your own hardware. That open, bring-your-own-model design is a big part of its appeal.<\/p>\n<h3>OpenCode vs Claude Code \u2014 which is better?<\/h3>\n<p>It depends on your priorities. OpenCode wins on model choice (75+ providers, including local\/private models) and thoroughness, while Claude Code wins on speed and polish \u2014 OpenCode is reportedly about 78% slower on the same model. Use OpenCode for flexibility and privacy; use Claude Code for fast, polished autonomous work on Anthropic models.<\/p>\n<h3>Can OpenCode use local models?<\/h3>\n<p>Yes. OpenCode is provider-agnostic and connects to local models via Ollama and vLLM, so you can run a fully private coding agent with no code ever leaving your machine \u2014 one of the main reasons developers choose it over cloud-locked tools.<\/p>\n<h3>Why did OpenCode get so popular?<\/h3>\n<p>Three reasons: it&#8217;s open source and free, it&#8217;s not locked to one AI vendor (75+ providers), and its LSP integration makes it genuinely good at writing correct, well-tested code. That combination pushed it to ~160K GitHub stars and the #1 spot in the June 2026 dev-tool rankings, ahead of Cursor.<\/p>\n<h3>What languages does OpenCode support?<\/h3>\n<p>Through LSP, OpenCode has deep, type-aware support for TypeScript, Python (Pyright), Rust (rust-analyzer), Go (gopls), C\/C++ (clangd), Java, and 18+ additional languages \u2014 giving the AI real compiler feedback rather than just file text.<\/p>\n<h2><span class=\"ez-toc-section\" id=\"Bottom_line\"><\/span>\u062e\u0644\u0627\u0635\u0629 \u0627\u0644\u0642\u0648\u0644<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p>OpenCode is the clearest sign of where AI coding is heading in 2026: <strong>open, model-agnostic, and terminal-native<\/strong>. By refusing to lock you to a single AI vendor \u2014 and by feeding the model real compiler diagnostics through LSP \u2014 it earned ~160K GitHub stars and the top spot in the dev-tool rankings, ahead of well-funded rivals.<\/p>\n<p>It isn&#8217;t the fastest option (Claude Code keeps that crown), and the ~78% speed gap is a real trade-off. But if you care about <strong>model choice, privacy, cost, or thoroughness<\/strong> \u2014 and especially if you want to run a coding agent on local models \u2014 OpenCode is the most important tool in the category right now, and it&#8217;s free to try.<\/p>\n<p><!--related-block--><\/p>\n<div class=\"convly-related\">\n<h2><span class=\"ez-toc-section\" id=\"Related_articles\"><\/span>\u0645\u0642\u0627\u0644\u0627\u062a \u0630\u0627\u062a \u0635\u0644\u0629<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<ul>\n<li><a href=\"https:\/\/convly.ai\/ar\/hermes-desktop-explained-2026\/\">Hermes Desktop: Run Nous Research&#039;s Self-Improving AI Agent Without the Terminal (2026)<\/a><\/li>\n<li><a href=\"https:\/\/convly.ai\/ar\/hermes-agent-explained-2026\/\">What Is Hermes Agent? Nous Research&#039;s Self-Improving Open-Source AI Agent (2026)<\/a><\/li>\n<li><a href=\"https:\/\/convly.ai\/ar\/veo-3-vs-kling-3-for-ai-video-2026\/\">Veo 3.1 vs Kling 3.0 for AI Video in 2026: Which Wins for Realism?<\/a><\/li>\n<li><a href=\"https:\/\/convly.ai\/ar\/flux-vs-midjourney-2026\/\">Flux 2 vs Midjourney V7 in 2026: Photorealism vs Artistry (and Price)<\/a><\/li>\n<\/ul>\n<\/div>","protected":false},"excerpt":{"rendered":"<p>OpenCode is the model-agnostic, open-source coding agent that displaced Cursor at the top of the 2026 rankings. Run Claude, GPT, Gemini or a local model from your terminal \u2014 here&#8217;s what makes it different.<\/p>","protected":false},"author":1,"featured_media":1086,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","ast-disable-related-posts":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"categories":[5],"tags":[581,720,423,719,583],"class_list":["post-1084","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-tools","tag-ai-coding-agent","tag-claude-code-alternative","tag-open-source-ai","tag-opencode","tag-terminal-ai"],"_links":{"self":[{"href":"https:\/\/convly.ai\/ar\/wp-json\/wp\/v2\/posts\/1084","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/convly.ai\/ar\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/convly.ai\/ar\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/convly.ai\/ar\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/convly.ai\/ar\/wp-json\/wp\/v2\/comments?post=1084"}],"version-history":[{"count":3,"href":"https:\/\/convly.ai\/ar\/wp-json\/wp\/v2\/posts\/1084\/revisions"}],"predecessor-version":[{"id":1093,"href":"https:\/\/convly.ai\/ar\/wp-json\/wp\/v2\/posts\/1084\/revisions\/1093"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/convly.ai\/ar\/wp-json\/wp\/v2\/media\/1086"}],"wp:attachment":[{"href":"https:\/\/convly.ai\/ar\/wp-json\/wp\/v2\/media?parent=1084"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/convly.ai\/ar\/wp-json\/wp\/v2\/categories?post=1084"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/convly.ai\/ar\/wp-json\/wp\/v2\/tags?post=1084"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}