Blog — Intrane.fr (Page 11)

Product · July 2026

Your AI Assistant Can Run Your Website Chatbot Now

chatsnip is a website chatbot with no dashboard: your AI assistant installs it, configures it, and reports your leads weekly. One script tag, your own LLM key, $79 self-host or €19/mo hosted.

#chatsnip #ai-agents #chatbot #micro-saas #byok

Product · July 2026

grepapi — The Lead Engine That Found Its Own Customers

I built an affordable, agent-first alternative to SerpApi — a GTM warm-lead engine that returns real companies with phone numbers and warm LinkedIn leads, each with a brief your own LLM turns into outreach. Then I pointed it at its own market, and it found its first customers.

#grepapi #gtm #machin #agent-first #saas

Language · July 2026

Fearless Concurrency Without the Send/Sync Tax

Rust guarantees data-race freedom, but you pay for it in Send/Sync bounds and lifetimes — a tax on the human. I built the same class of guarantee into machin, inferred by the compiler with zero annotations. Here's why a machine-first language makes that tractable.

#machin #concurrency #compiler #ai-engineering

Language · July 2026

The Day My Language Started Compiling Itself

A year ago I built a programming language for AI agents. This year it crossed the line that separates a toy from a real compiler: it started compiling itself — byte-for-byte, faster than the original. Here's how, and why it's the clearest proof of how I build software with AI.

#machin #compiler #self-hosting #ai-engineering

Infrastructure · June 2026

The Self-Hosted Stack That Runs My Infrastructure

AutoMaintainer, mago, SuperCLI, SuperInsights, machin, a2a — each product works alone, but the real story is how they work together. This is the fully self-hosted stack that runs Intrane for ~€60/month. No lock-in, no vendor dependency, no surprise bills.

#self-hosted #infrastructure #automaintainer #machin #a2a

Framework · June 2026

a2a — When AI Agents Talk to Each Other

Most AI agent frameworks use a master-slave model — one orchestrator controls everything. a2a flips this: agents talk to each other as peers over a shared SQLite bus. No central command, no single point of failure, no dictatorial orchestrator.

#a2a #ai-agents #multi-agent #open-source

Language · June 2026

Machin in Production — Real Products Built with MFL

A language that optimizes for AI generation over human readability sounds good in theory, but theory does not ship products. Here is what we have actually built with machin — running in production today: auth broker, webhook relay, browser REPL, terminal emulator, and more.

#machin #mfl #production #self-hosted

Open Source · June 2026

Self-Hosted Analytics — Why I Built What GA Won't Give You

Google Analytics is a black box. Your data flows into someone else's servers and you get back whatever dashboards they decide to give you. SuperInsights is the opposite: self-hosted, raw event access, AI-powered analysis, zero third-party data sharing.

#superinsights #analytics #self-hosted #privacy

Open Source · June 2026

SuperCLI — 10,000 Tools, One Binary, Zero Configuration

Every developer has their own toolbox, their own scripts, their own way of doing things. SuperCLI is the last CLI you install — 10,000+ tools in a single binary, zero configuration, no package manager. Open source, self-hostable, team-ready.

#supercli #cli #devtools #open-source

Product · June 2026

mago — The €20 Autonomous Agent That Runs Your GitHub

AutoMaintainer is the flagship — verified gates, multi-agent fleets, human architect support. But not every team needs the flagship. mago is the €20/month flat, CLI-only, BYOK autonomous agent for solo devs and bootstrappers who just need code shipped.

#mago #ai-agents #cli #bootstrappers