A French video API for developers: upload, encode, host, stream live and play video inside your own app, with free encoding, per-minute pricing and AI transcription.

Tencent's open-source 1.5B speech model: text to speech, voice cloning, and editing of recorded speech (words, pitch, speed, emotion, noise) from plain-language instructions.

A European CDN and edge platform from Slovenia: content delivery from $0.01 per GB, video hosting with free encoding, storage, image optimisation, DNS and security, pay as you go from $1 a month.

Caps Lock to talk, a live transcript while I speak, clean text pasted where the cursor is. Everything runs on my Mac Studio. Built with Claude Code in 22 prompts.

A free, open-source Markdown editor for Mac, written in native Swift: it opens in 0.1 seconds, idles at 50 MB of memory, and keeps every note a plain .md file.

A local dashboard on port 9000 that starts, stops and opens every browser app under ~/ai. Fixed ports, start on click, 1 file of stdlib Python.

A Claude Code skill that turns the project you just built into a 20-second launch video, with music, motion and share copy, in 1 command.

React-first slide framework where AI agents write the deck as code. Version 2.0 adds visual editing, a presenter view and editable PowerPoint export.

One API key and one bill for 458 AI models from 63 labs, with automatic fallbacks when a provider fails. Model prices pass through, and OpenRouter takes 5.5% on credit purchases.

Microsoft's open-source method for training agent skills like a neural network, without touching the model: small edits to a skill file, kept only if they score better on held-out tasks.

An open-source framework that analyses a stock the way a trading firm would: analyst agents, a bull-versus-bear debate, a trader, a risk team and a portfolio manager.

An open-source Claude Code framework that runs a whole job search: profile, portal search, fit scoring, tailored CV and cover letter, reviewer agent, interview prep and tracking.

A cloud drive that shows up in Finder but takes no disk space: files stream on demand, every save is a version, and agents can work on instant copies of a whole drive.

NVIDIA's open-weight 100M-parameter model that tells who spoke when, for up to 8 speakers, live or recorded. Ranked first on VoiceArena's diarization benchmark at launch.

How I configure Claude Code for NicAI: layered CLAUDE.md files, hooks, auto-memory, permissions, skills, connectors and the output conventions.

What NicAI has cost me in time and services, what failed on the way, and the lessons I would give anyone building their own AI layer.

Why SQLite files, Markdown knowledge bases and JSON are the source of truth for NicAI, and the 4 nightly jobs that keep them current.

LlamaIndex's open-source local document parser, rewritten in Rust: PDFs and Office files to text, JSON or Markdown in milliseconds, with no model and no cloud.

My personal AI layer: what it is, why I am building it, how it started in 2022, and where it stands in September 2026.

NicAI Lab, the site where NicAI and I put the pages, demos and files we build, shared through unlisted links that only work if I give them out.

How NicAI turns "write a note about X" into a live, signed page on this site in about 15 seconds: the write-note skill, the publish hook and the 5 publish phases.

Anthropic's guidance for getting the most out of each Opus release in Claude and Claude Code, newest first: Opus 5.5 (September 2026) and Opus 4.7 (April 2026).

The 30 small Python wrappers my NicAI skills call for research, web data, media, publishing, email, DNS and home automation, and the pattern they share.

Every skill in my NicAI setup, grouped by purpose, 1 line each, plus what a skill is and the rules I build them by.