LLM notes
My journey with LLMs, agents, tools and more.
Agents
- Matt Pocock skills - grill-me, grill-with-docs, tdd, diagnose, etc.
- Opencode Memory - Long-term context retention across sessions using local vector database
- Code doctrine - The Reusable Version of Kamil Chmielewski AI Coding Constitution
- Plannotator - Interactive plan annotation and colaborative sharing.
- Obra Superpowers - A complete software development workflow for your coding agents, built on top of a set of composable “skills” and some initial instructions that make sure your agent uses them.
- Pi Dev - Minimal terminal coding harness, that adapts to a developer’s specific workflow. Unlike more rigid agents, it provides a powerful foundation (with read, write, edit, and bash tools) and expects users to extend it through custom “Skills,” “Extensions,” and “Packages.”
- Oh My OpenCode - Multi-agent orchestration layer for the OpenCode platform that uniquely transforms single-stream AI coding into a parallelized team workflow by automatically delegating specialized subtasks—like planning, research, and execution.
- Open Agents Control - AI agent framework built specifically for the OpenCode ecosystem that prioritizes human-in-the-loop control and production-grade reliability over pure autonomy.
Tools
- The Open Agent Skills Ecosystem
- Coding (Agent) CLI Usage Analysis - Analyze coding (agent) CLI token usage and costs from local data
- RTK - CLI proxy that reduces LLM token consumption
- Caveman - Talk like a caveman and save the tokens