Blog — Intrane.fr (Page 2)

Product · August 2026

I Told My Agent What It Couldn't Do. It Found a Way Anyway.

I built a permission system for AI agents. A live model found the hole in it, on its own, twice — and the destructive-approval gate I thought was the real backstop turned out to need proving too.

#commis #ai-agents #security #dogfooding #open-source #agent-first

Product · August 2026

Stop Giving AI Agents Your SSH Keys

Your AI agent needs to run commands on your servers. The only credential most people have to give it is an SSH key: everything, forever, with no record. rcmd's answer is a token scoped to named machines, expiring by default, revocable in one command, with every action audited — now one command to mint, and an MCP server to plug into. Includes the two security bugs I found in my own audit trail while building it.

#agent-tokens #ai-agents #devops #infrastructure #mcp #open-source #remotecmd #security #ssh

Product · August 2026

How I Made remotecmd 1.7× Faster Than scp Over a 77ms Relay

remotecmd routes file transfers through a WebSocket relay — which means a single TCP stream can't fill the pipe on high-RTT links. I spent two days reading kernel source, CERN GridFTP papers, and gorilla/websocket internals. The result: parallel TCP streams that auto-tune by file size, atomic header+binary framing in the relay, and gzip writer pooling. 50MB over 77ms RTT: 1.74× faster than single stream, 1.21× faster than scp. Here's what worked, what didn't, and why.

#remotecmd #performance #tcp #websocket #parallel-streams #open-source #devtools

Product · August 2026

Free SAST for private repos — no per-developer seat tax

GitHub CodeQL is free for public repos. For private repos it's $49/committer/month. Snyk is $25/dev. Semgrep is $40/dev plus AI credits per finding. machin-secure is free — for private repos too, no enterprise plan required, no per-developer seat tax, your code never leaves your CI. Here's what it is, what it isn't, and why I built it.

#machin-secure #security #ci #open-source #sast

Product · August 2026

I Built a Security Auditor for AI Agents. It Has No AI Inside.

machin-secure scans a codebase for secrets, injection, and weak crypto and streams JSONL findings. The interesting part isn't the scanner — it's that it has no LLM client, no report generator, and no sandbox. The calling agent already is the model.

#machin-secure #machin #ai-agents #open-source #self-hosted #security #hart

Product · July 2026

My Windows PC Died at 1% SSD Life — Here's How Linux + AI Saved Everything

My Windows laptop refused to boot with 'no boot device'. SMART showed 1% remaining write endurance on the SSD. With an AI assistant (GLM-5.2) guiding every step, I diagnosed, backed up, shrunk, cloned, and fixed three separate boot errors — entirely from Linux, no Windows recovery media.

#linux #ssd #data-recovery #windows #dd #ntfsresize #proxmox #ai-assistant

Product · July 2026

peage Shapes the x402 Fiat Binding — A Production Rail Joins the Spec

peage is a live fiat pay-per-call rail for agents — prepaid wallets, Stripe funding, signed receipts, no crypto. When the x402 foundation drafted a credit-backed binding for fiat API monetisation, peage was already running the shape they were specifying. Here's what happened when a production implementation met a spec in progress, and what the conversation produced.

#x402 #peage #payments #agents #fiat #open-source #specs

Product · July 2026

My Agents Needed a Room, Not a Slack

Two of my agents claimed the same issue last week. Neither was wrong — neither could have known. So I built cuzz: a fleet communication relay in one static binary, with an embedded database, exactly-once reads by watermark, and server-sent events on a server that has no concurrency in it at all.

#cuzz #ai-agents #machin #grange #devtools #sse

Product · July 2026

The Skill Graph — Why My Agent Was Using the Wrong Skill

I have 197 skills across 67 namespaces. My agents were finding the wrong one half the time — or missing it entirely. memgraph is a skill discovery engine that builds a knowledge graph from SKILL.md files and ranks them by relevance to the task at hand. TF-IDF + graph boost, a galaxy visualization, and a feedback command that dual-writes to a central relay. One Go binary, MIT, agent-first.

#memgraph #agent-first #skill-discovery #cli #devtools

Product · July 2026

I Put a Graph Engineering Layer on AutoMaintainer — With GLM-5.2 as the Architect

AutoMaintainer ships PRs autonomously. But when a PR needs a human decision, the fleet used to stall for hours. So I built a graph engineering layer on top — mago for HITL, a deterministic merger, live dashboards — and the whole thing was crafted with GLM-5.2 as the architect. It works. Honestly.

#automaintainer #glm-5.2 #ai-agents #graph-engineering #devtools #human-in-the-loop