https://codema.ai/build.htmlPublished articles from Codema.en-CAhttps://codema.ai/articles/quantization-explained-fp8-gguf.htmlhttps://codema.ai/articles/quantization-explained-fp8-gguf.htmlFri, 23 Oct 2026 13:00:00 -0400BF16, FP8, MXFP8, NVFP4, INT4 and a dozen GGUF flavours, compared. What published benchmarks say about quality loss, and how to pick the file for your GPU or Mac.Build GuidesDerrick K.https://codema.ai/articles/open-model-licenses-explained.htmlhttps://codema.ai/articles/open-model-licenses-explained.htmlFri, 23 Oct 2026 10:00:00 -0400Beam, Ornith-1.5-122B and MiniMax M3.1 Flash shipped in one week under three different licenses. What each license type allows commercially, read from the license texts themselves.Build GuidesDerrick K.https://codema.ai/articles/t3-code-guide.htmlhttps://codema.ai/articles/t3-code-guide.htmlThu, 22 Oct 2026 00:00:00 +0000T3 Code is a free, open-source control surface for the coding agents you already pay for. Here's what it does, how to install it, and what to know before you rely on it.Build GuidesDerrick K.https://codema.ai/articles/prompt-caching-explained.htmlhttps://codema.ai/articles/prompt-caching-explained.htmlThu, 22 Oct 2026 00:00:00 +0000Prompt caching lets you pay a fraction of the price for input the model has seen before. Here's how it works, what it costs on Claude, Gemini, GPT-6 and MiniMax, and how to structure prompts so the cache actually hits.Build GuidesDerrick K.https://codema.ai/articles/opencode-local-llm-ollama-lm-studio-llama-cpp.htmlhttps://codema.ai/articles/opencode-local-llm-ollama-lm-studio-llama-cpp.htmlThu, 22 Oct 2026 00:00:00 +0000Point OpenCode at a model running on your own machine. Copy-paste opencode.json configs for Ollama, LM Studio and llama.cpp's llama-server, plus the port and context gotchas that trip people up.Build GuidesDerrick K.https://codema.ai/articles/ollama-for-beginners.htmlhttps://codema.ai/articles/ollama-for-beginners.htmlThu, 22 Oct 2026 00:00:00 +0000Ollama runs open AI models on your own Mac, Windows or Linux machine. Here's how to install it, run your first model, learn the commands you'll actually use, connect it to your app or coding agent, and what hardware you need.Build GuidesDerrick K.https://codema.ai/articles/llm-api-pricing-compared-claude-gemini-minimax.htmlhttps://codema.ai/articles/llm-api-pricing-compared-claude-gemini-minimax.htmlThu, 22 Oct 2026 00:00:00 +0000Input, output and cached-token prices for Claude Opus/Sonnet/Haiku 5.5, Gemini 4 Argon, GPT-6 Astra, MiniMax M3.1 Flash and Mercury 3, from each provider's own pages, plus a worked example of what one agent workload costs.Build GuidesDerrick K.https://codema.ai/articles/gemini-api-cli-guide.htmlhttps://codema.ai/articles/gemini-api-cli-guide.htmlThu, 22 Oct 2026 00:00:00 +0000Google's open-source gemini-api CLI lets any coding agent with a shell call Gemini models: generate images, voiceovers, music and video, analyze PDFs, or launch managed agents. Here's the setup, the AGENTS.md snippet, and the safety flags.Build GuidesDerrick K.https://codema.ai/articles/design-md-design-system-for-coding-agents.htmlhttps://codema.ai/articles/design-md-design-system-for-coding-agents.htmlThu, 22 Oct 2026 00:00:00 +0000DESIGN.md is an open format from Google Labs for describing your visual identity to coding agents: tokens for exact values, prose for the why. Here's how to write one, lint it, and export it to Tailwind.Build GuidesDerrick K.https://codema.ai/articles/context-windows-explained.htmlhttps://codema.ai/articles/context-windows-explained.htmlThu, 22 Oct 2026 00:00:00 +0000A context window is a model's working memory: your system prompt, chat history, files, tool definitions and the reply all share it. Here's how it fills up, why 1M tokens isn't a free pass, and how to count before you send.Build GuidesDerrick K.https://codema.ai/articles/codex-cli-getting-started.htmlhttps://codema.ai/articles/codex-cli-getting-started.htmlThu, 22 Oct 2026 00:00:00 +0000A beginner's walkthrough of OpenAI's Codex CLI: install on Mac, Linux or Windows, sign in with your ChatGPT plan, generate an AGENTS.md with /init, and run your first task safely.Build GuidesDerrick K.https://codema.ai/articles/claude-opus-5-5-for-builders.htmlhttps://codema.ai/articles/claude-opus-5-5-for-builders.htmlThu, 22 Oct 2026 00:00:00 +0000A practical guide to Claude Opus 5.5: what it costs per job, how to pick an effort level, and the four breaking changes to fix before you swap the model ID.Build GuidesJohn F.https://codema.ai/articles/claude-code-subagents-vs-skills-vs-hooks.htmlhttps://codema.ai/articles/claude-code-subagents-vs-skills-vs-hooks.htmlThu, 22 Oct 2026 00:00:00 +0000Subagents, skills and hooks all extend Claude Code, but they do different jobs. A plain-English guide with a working example of each, plus the new \"Record a skill\" feature in Cowork for Mac.Build GuidesDerrick K.https://codema.ai/articles/what-is-agents-md-how-to-write-one.htmlhttps://codema.ai/articles/what-is-agents-md-how-to-write-one.htmlWed, 21 Oct 2026 00:00:00 +0000AGENTS.md is a Markdown file that tells AI coding agents how to work on your repo. What it is, which tools read it, and how to write one that works.Build GuidesCodema Editorialhttps://codema.ai/articles/utm-tracking-setup-guide.htmlhttps://codema.ai/articles/utm-tracking-setup-guide.htmlWed, 21 Oct 2026 00:00:00 +0000A UTM tracking setup for GA4: what each UTM parameter does, a lowercase naming convention to copy, auto-tagging rules, and launch checks for AI-built sites.Build GuidesCodema Editorialhttps://codema.ai/articles/run-coding-agents-safely-permissions-sandboxes.htmlhttps://codema.ai/articles/run-coding-agents-safely-permissions-sandboxes.htmlWed, 21 Oct 2026 00:00:00 +0000How to run coding agents safely with Claude Code permission modes, Codex sandbox and approval settings, deny rules, and habits that keep secrets out of reach.Build GuidesCodema Editorialhttps://codema.ai/articles/mcp-security-best-practices.htmlhttps://codema.ai/articles/mcp-security-best-practices.htmlWed, 21 Oct 2026 00:00:00 +0000MCP security best practices for vibe coders: prompt injection risks, what the MCP spec requires, and a checklist to use MCP servers without leaking data.Build GuidesCodema Editorialhttps://codema.ai/articles/git-github-basics-for-vibe-coders.htmlhttps://codema.ai/articles/git-github-basics-for-vibe-coders.htmlWed, 21 Oct 2026 00:00:00 +0000Git and GitHub basics for vibe coders: the commands you need, a branch-per-task workflow for coding agents, .gitignore for secrets, and push protection.Build GuidesCodema Editorialhttps://codema.ai/articles/ga4-predictive-audiences-google-ads.htmlhttps://codema.ai/articles/ga4-predictive-audiences-google-ads.htmlWed, 21 Oct 2026 00:00:00 +0000GA4 predictive audiences target users likely to buy or churn. The requirements, how to create one, and how to use it in Google Ads, from Google docs.Build GuidesCodema Editorialhttps://codema.ai/articles/back-up-supabase-database.htmlhttps://codema.ai/articles/back-up-supabase-database.htmlWed, 21 Oct 2026 00:00:00 +0000How to back up a Supabase database: what each plan backs up, how to export with supabase db dump, how to restore, and what backups leave out.Build GuidesCodema Editorialhttps://codema.ai/articles/add-mcp-server-cursor-claude-code-codex.htmlhttps://codema.ai/articles/add-mcp-server-cursor-claude-code-codex.htmlWed, 21 Oct 2026 00:00:00 +0000Step-by-step: how to add an MCP server to Cursor, Claude Code and Codex, with copy-paste config for the Supabase and GitHub MCP servers.Build GuidesCodema Editorialhttps://codema.ai/articles/vibe-code-saas-supabase-vercel-weekend.htmlhttps://codema.ai/articles/vibe-code-saas-supabase-vercel-weekend.htmlTue, 20 Oct 2026 00:00:00 +0000A two-day plan to vibe code a SaaS with an AI agent, Next.js, Supabase and Vercel, including the Row Level Security steps most weekend builds skip.Build GuidesCodema Editorialhttps://codema.ai/articles/review-ai-written-code-before-production.htmlhttps://codema.ai/articles/review-ai-written-code-before-production.htmlTue, 20 Oct 2026 00:00:00 +0000A practical routine to review AI-generated code before production: access control first, then secrets, dependencies, errors, and agents reviewing agents.Build GuidesCodema Editorialhttps://codema.ai/articles/predictive-creative-testing-ai-ad-creatives.htmlhttps://codema.ai/articles/predictive-creative-testing-ai-ad-creatives.htmlTue, 20 Oct 2026 00:00:00 +0000Predictive creative testing uses AI to generate and pre-score ad creatives, then confirms the winners with real Google Ads or Meta experiments.Build GuidesCodema Editorialhttps://codema.ai/articles/mcp-explained-for-vibe-coders.htmlhttps://codema.ai/articles/mcp-explained-for-vibe-coders.htmlTue, 20 Oct 2026 00:00:00 +0000What is MCP? The Model Context Protocol lets your coding agent use real tools like your database. How it works, how to connect a server, and how to stay safe.Build GuidesCodema Editorialhttps://codema.ai/articles/building-with-ai-in-french-quebec.htmlhttps://codema.ai/articles/building-with-ai-in-french-quebec.htmlTue, 20 Oct 2026 00:00:00 +0000How to build a bilingual app for Quebec with AI: OQLF French-language rules, Law 25 privacy duties, Next.js i18n patterns and resources.Build GuidesCodema Editorial