Introducing DeveloPassion's News Flash
I've just launched a new News page on my blog and a matching newsletter: DeveloPassion's News Flash.
Latest
LiteLLM Claude Code Proxy
Open-source LiteLLM configuration that lets Claude Code run against an Azure AI Foundry deployment instead of Anthropic's hosted API. Published by National Bank of Belgium. It's a thin wrapper: a `litellmconfig.yaml` with a wildcard model route, a `startproxy.sh` launcher, a Dockerfile, and a `.env`
Sidenotes plugin for Obsidian
Adds Tufte-style sidenotes and margin notes rendered in the margin of an Obsidian note. Inspired by Gwern.net and Edward Tufte's CSS conventions. Combines a CSS snippet with a plugin to handle behavior CSS can't (editing in margin, re-sequencing, etc.).
LiteLLM
LiteLLM is an open-source AI Gateway that exposes 100+ LLM providers through a single OpenAI-compatible interface. It ships in two forms: a Python SDK for embedding the gateway logic inside applications, and a self-hostable proxy server (the "LLM Gateway") that centralizes access, spend tracking, an
My communications plan
This is my (Sébastien Dubois) Communications plan. It describes where/how I share information and ideas. It's part of my business flywheel.
Claude Code Prompt Caching
Claude Code uses Anthropic's prompt cache to reuse large, stable chunks of context (system prompt, tool definitions, CLAUDE.md, prior turns) across requests instead of resending and re-billing them every turn. Cache reads are cheaper than uncached tokens; cache writes are more expensive than normal
2026-04-14 Interesting Links
Here are a few links I found interesting today.
DeveloPassion's Newsletter #210 - LLM Wikis
I built a full LLM Wiki system inside the Obsidian Starter Kit: 7 skills, a Wiki Curator agent, 70+ articles in one session. OSK v4 is coming with 360+ AI skills, agents with persistent memory, and LLM Wikis. Plus a new book, Claude Code updates, and 6,000+ subscribers.
I Built a Graph Explorer for Obsidian Bases. Here's Why LLM Wikis Need a Visual Layer
I built Graph Explorer Base View to solve a real problem: LLM Wikis generate tons of interconnected notes, but without a visual layer, you can't see clusters, gaps, or what still needs review.
#pillar-creator-systems
Slopsquatting, Typosquatting, and the New Software Supply Chain Attacks: How AI and Vibe Coding Are Making Package Registries Even More Dangerous
AI coding tools hallucinate fake package names. Attackers register them. You install malware. Here's how slopsquatting works and what you can do about it.
#pillar-creator-systems
I Built an Obsidian Plugin to Convert Handwritten Notes to Markdown
Point any image in your Obsidian vault at a local AI model and get structured Markdown back. Headings, lists, quotes, even Mermaid diagrams. No data leaves your machine.
#pillar-creator-systems
Analog Reading, Digital Knowledge: The Full Pipeline From Paper Notes to AI Skills
I read books on paper, take handwritten notes, and turn them into connected atomic notes and AI skills. Here's the full pipeline, and the thinking behind each step.