10 Tools · 5 Topics
AI Tools
My attempts to learn by building so I can offer sensible suggestions at work. I think of my stack in five layers: memory & knowledge, LLM agents, and business tooling.
Memory & Knowledge
My AI agents should know my work better than I do. When I start an Agent session, the conversation should load all historical and current context, preferences, conventions, and templates for the featured and related projects.
Memory
A shared memory service across the AI tools I use daily, built to test what it actually takes to extract, deduplicate, and retrieve user context over months without losing track of contradictions.
Library
A personal research library that helps AI agents find source passages, inspect their context, and qualify claims across more than 300 documents.
Document Search
The local-only counterpart to Library: a document search server running on SQLite and Ollama so private drafts and NDA materials never leave the laptop.
News
A daily AI and EdTech news filter that cuts fifty stories down to five, paired with a golden-set evaluation pipeline to measure whether the scorer still agrees with my own judgment.
Vendor-Agnostic Tooling
Seamlessly swap between all LLM vendors, models, and CLI clients without needing to configure tools, manage authentication, or security.
Tool Mart
A single catalog and sync tool that keeps skills, MCP servers, credentials, and read-only permission boundaries consistent across five AI coding CLIs, plus an inter-rater benchmark comparing the models.
Document Canvas
A CLI client-agnostic WYSIWYG editor and review engine for Markdown, HTML, and raster images, connecting browser edits and passage-anchored comments directly to Claude Code, Codex, or Antigravity.
Niu Prototyper
Visual interactive prototyping for live web UIs: wraps any static build or dev server in an inspectable canvas where I pin element-anchored comments and iterate in place with any CLI coding agent.
Grammar for Everything
One token system and visual grammar (Imagism) across R/ggplot2 charts, analytical briefs, slide decks, and web UI, paired with a 97-term part lexicon for surgical edits.
Operationalizing AI for Research & Analysis
Automating K-12 survey research, psychometric analysis, and publication-ready district impact reports through stage-gated multi-agent pipelines where every number in the prose is verified against source tables.
What are my CLI agents doing?
Ultimate goal: turn work into a video game where I instruct NPCs to do my job.