Blog — Intrane.fr — #agent-first

Product · August 2026

Your AI Agent Is Leaking Your Secrets

I audited a secret manager that had AES-256-GCM, X25519 sealed responses, ACLs, and attestation. It leaked secrets in the simplest way possible: the exec command passed child stdout straight to the model. No interception, no scrubbing. Here's how I found it, why it matters, and how veil fixes it — mandatory output scrubbing, no raw output by default, sealed mode as the only mode.

#security #secrets #agent-first #machin #mfl #encryption #open-source

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 · 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

Your CLI Should Update Itself

I have 6 servers running remotecmd daemons. Last week I spent 20 minutes manually updating each one to the latest version. That's stupid. So I implemented the cli-update-spec: rcmd update downloads, verifies, smoke-tests, and atomically swaps the binary. No SSH, no installer, no downtime. Here's how it works and why every CLI should do this.

#cli #self-update #agent-first #remotecmd #open-source #devtools

Product · July 2026

The Agent That Signed Up and Paid for Its Own Analytics

A live, unedited transcript: an AI agent discovers vigie's API from llms.txt, creates an org, hits its free quota, reads the HTTP 402, links a prepaid péage wallet, and pays for more events — real cents on the live rail, zero humans on either side.

#vigie #peage #x402 #agent-first #agent-economy

Product · July 2026

Web Analytics With No Dashboard (But There Is a Globe)

vigie is cookieless web analytics built for agents: JSON verbs instead of dashboards, on-demand HTML reports, and a living 3D globe with city-level dots. Full metric parity with the dashboard-first tools — geo to city, journeys, vitals, errors, heatmaps — in one MIT binary, hosted tier metered per-use.

#vigie #analytics #agent-first #machin #peage

Product · July 2026

Four Specs That Make Any CLI Agent-First

I ship a lot of CLIs — grepapi, mago, remotecmd, chatsnip, automaintainer. Each one needed the same four things: a way for agents to read its output, learn its model, report bugs, and update itself. So I wrote four tiny specs that any CLI can adopt in 30 minutes each.

#cli #agent-first #open-source #specs #devtools

Product · July 2026

The CRM That Maintains Itself

Every CRM dies of stale data because humans won't do data entry. So I built the one you never open — an agent runs it, cold-mail and cold-calls send themselves, replies and call outcomes log themselves. One binary, open source, hosted from €19/mo.

#crm-cli #crmd #agent-first #open-source #machin

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