https://blog.mattiaperetti.it/blog Backend architecture, keeping software running in production, and building AI agents. en-us undefined (Mattia Peretti) undefined (Mattia Peretti) Wed, 23 Sep 2026 00:00:00 GMT https://blog.mattiaperetti.it/blog/local-llm-coding-agent-setup https://blog.mattiaperetti.it/blog/local-llm-coding-agent-setup I moved my coding agents off hosted APIs and onto two machines I own, a MacBook Pro M5 Pro as the client and a gaming PC with an RX 7800 XT as the model server. Model capability was rarely the blocker. The blockers were unified memory limits, inference engines that mangle tool call formats, a model stuck in a loop, and a laptop that kept freezing for reasons I still have not pinned down. Wed, 23 Sep 2026 00:00:00 GMT undefined (Mattia Peretti) aillmlocal-llmcoding-agentsself-hosted https://blog.mattiaperetti.it/blog/agentic-writer-journey https://blog.mattiaperetti.it/blog/agentic-writer-journey How I built an agentic writing pipeline on Mastra: researcher, writer, editor, human approval, and the token-limiter bug that made revisions invent details. Thu, 23 Jul 2026 00:00:00 GMT undefined (Mattia Peretti) aiagentsmastratypescript https://blog.mattiaperetti.it/blog/composer_2_5_vs_grok_4_5_for_frontend https://blog.mattiaperetti.it/blog/composer_2_5_vs_grok_4_5_for_frontend Composer 2.5 and Grok 4.5 built the same PancakeBot frontend from the same prompt and skills. Composer finished faster, while Grok delivered the more polished first pass. Fri, 17 Jul 2026 00:00:00 GMT undefined (Mattia Peretti) aifrontendcursorcomposergrok https://blog.mattiaperetti.it/blog/local-llm-tipping-point https://blog.mattiaperetti.it/blog/local-llm-tipping-point Colibrì, a ~1,300-line pure C inference engine with zero dependencies, runs the 744B-parameter GLM 5.2 MoE model on a laptop with 25 GB of RAM and no GPU by streaming int4-quantized experts from NVMe. Cold-cache throughput is 0.05 to 0.1 tokens per second, so speed is the honest limiter, but it is an existence proof that frontier-scale local inference works on commodity hardware. Fri, 17 Jul 2026 00:00:00 GMT undefined (Mattia Peretti) aillmlocal-llmopen-sourceinference https://blog.mattiaperetti.it/blog/the-superpowers-of-a-software-engineer https://blog.mattiaperetti.it/blog/the-superpowers-of-a-software-engineer Coding agents get better every month, and the way to stay in control is to give them clear instructions and context rather than fight the shift. This covers agent instruction file conventions worth adding to a repo (AGENTS.md, SKILL.md, CLAUDE.md, Cursor skills) and two open-source tools, Ponytail and Caveman, that cut token spend by trimming what agents write and compressing what you send. Mon, 13 Jul 2026 00:00:00 GMT undefined (Mattia Peretti) aiagentic-aiclaude-codellm https://blog.mattiaperetti.it/blog/choose-the-right-ai-model-for-the-job https://blog.mattiaperetti.it/blog/choose-the-right-ai-model-for-the-job Model choice is an engineering decision that shows up in both output quality and your bill. This walks through models.dev and artificialanalysis.ai as the two resources for shortlisting on specs/price and then checking capability, cost per task, and latency, with worked comparisons across GPT-5.6 Sol, Claude Fable 5, Gemini, LongCat-2.0, and Seedance 2.0. Sun, 12 Jul 2026 00:00:00 GMT undefined (Mattia Peretti) aillmagentic-aitokens https://blog.mattiaperetti.it/blog/gpt-5.6-announced https://blog.mattiaperetti.it/blog/gpt-5.6-announced OpenAI's GPT-5.6 announcement is dense with benchmark numbers and efficiency claims. The company positions Sol as the flagship model, with Terra and Luna filling in for balanced and cost-efficient tiers. The through line is not just higher raw scores. It is capability per token and time to result across agentic workflows, coding, browsing, science, and cyber tasks, with repeated emphasis on lower cost and latency for comparable outcomes. Fri, 10 Jul 2026 00:00:00 GMT undefined (Mattia Peretti) aiopenai https://blog.mattiaperetti.it/blog/okf-and-the-two-brains-of-an-llm-agent https://blog.mattiaperetti.it/blog/okf-and-the-two-brains-of-an-llm-agent Google quietly published OKF, a plain markdown-plus-frontmatter format for agent knowledge, built on a pattern Karpathy sketched in a gist months earlier. Working through both taught me to stop thinking of an LLM as one brain and start thinking of it as two. Tue, 07 Jul 2026 00:00:00 GMT undefined (Mattia Peretti) aiagentic-aillmmemoryokf https://blog.mattiaperetti.it/blog/fable-5-export-controls-and-model-freedom https://blog.mattiaperetti.it/blog/fable-5-export-controls-and-model-freedom Claude Fable 5 was pulled from every user globally for two and a half weeks after a government export control order, then came back with a new safety classifier. Here is what happened and what it tells me about how "free" a model actually is. Mon, 06 Jul 2026 00:00:00 GMT undefined (Mattia Peretti) aiai-securityanthropicexport-control https://blog.mattiaperetti.it/blog/building-an-mcp-server-with-mastra https://blog.mattiaperetti.it/blog/building-an-mcp-server-with-mastra I followed the Mastra tutorial to build and publish a simple MCP server, then connected it to a self-built agent and to Claude. Here is what the protocol actually does under the hood and what surprised me. Fri, 03 Jul 2026 00:00:00 GMT undefined (Mattia Peretti) mcpaiagentic-aimastra https://blog.mattiaperetti.it/blog/the_uptime_monitor https://blog.mattiaperetti.it/blog/the_uptime_monitor Uptime is crucial for online businesses, and with tools like UptimeSphere, SMBs can proactively monitor their websites to ensure reliability and prevent customer-facing downtime. Mon, 28 Oct 2024 00:00:00 GMT undefined (Mattia Peretti) saasuptime https://blog.mattiaperetti.it/blog/shadcn_overview https://blog.mattiaperetti.it/blog/shadcn_overview Introduction of Shadcn UI, a components collection of reusable React components that can be copied directly into projects and used across various frameworks with Tailwind CSS. Fri, 16 Aug 2024 00:00:00 GMT undefined (Mattia Peretti) nextjsui