What's the best AI model for Jewish textual research?
A friend asked me which AI model is best for Jewish textual research. The answer is that it's the wrong question — the model isn't where the knowledge lives. Here's what to do instead.
Blog
138 posts — the full archive.
A Claude Code plugin for filing better feedback to Anthropic
Latest addition to my Claude Code marketplace: a self-healing plugin that turns the agent itself into a feedback-filer. Interviews you against the live Anthropic issue templates, renders the body in the right format, and files via gh.
Three repos for running purchasing decisions through Claude Code
A pattern I've settled into for buying things thoughtfully: one repo per purchase, standing preferences in Mem0, an Israel-specific plugin that handles the local retail quirks, and two workspace templates that split product merit from sourcing.
AI Typer V2 — v0.5.5
Voice dictation with single-pass multimodal cleanup. Gemini 3 Flash is the new default; Debian package available.
How much bitrate does an audio-multimodal LLM actually need?
An eval across 12 audio-capable models on OpenRouter, 5 MP3 bitrates, 4 dictation samples. The default upload quality in most dictation apps is 2–4× overprovisioned — and the more interesting finding had nothing to do with bitrate.
API or MCP? When the CLI Just Works Better
The MCP protocol promises unified tool access for AI agents, but sometimes a plain API call or CLI command is more reliable. What does that tell us about MCP's maturity?
Why I Run Two MCP Aggregators (And You Might Want To)
A walkthrough of the two-tier MCP aggregation architecture I use to keep my agentic AI setup portable, remotely accessible, and free from tool bloat.
Why I Run Two MCP Aggregators (And You Might Want To)
A walkthrough of the two-tier MCP aggregation architecture I use to keep my agentic AI setup portable, remotely accessible, and free from tool bloat.
Open Claw Stack v3: A Multi-Layer MCP Aggregation Topology
The v3 iteration of my Open Claw Stack — bundling OpenClaw and MetaMCP into a multi-layered, multi-gateway topology that stress-tests MCP discovery across nested aggregators.
Nano Tech Diagrams: Whiteboard Photos to Polished Diagrams with 28 Style Presets
A multi-platform tool for creating and editing technical diagrams using Fal AI's Nano Banana 2 model — available as a desktop GUI, CLI, MCP server, and npm package with 28 style presets and 20 diagram types.
Gemini Transcription MCP: Voice Notes to Formatted Documents via Claude
An MCP server that turns audio files into transcripts, meeting notes, blog posts, emails, and dev specs using Google Gemini — with 200+ transformation presets, VAD preprocessing, and SSH file retrieval.
My MCP Projects: A Catalog of 100+ Model Context Protocol Repositories
A snapshot of my MCP project portfolio — 100+ repositories spanning functional servers, orchestration tools, management utilities, and research documentation across the Model Context Protocol ecosystem.