Your coding agents remember what you decided — and what you changed. Plain-Markdown memory in Obsidian, shared by Claude Code, Codex and Cursor over MCP. Every answer cites its page; when the vault does not know, it says so. Imports your past sessions on install.

Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM

Multi-workspace profile router, MCP server isolation auditor, and CLAUDE.md <-> AGENTS.md instruction bridge for Claude Code and OpenAI Codex.

The Loop Engine for Claude Code — engineer the loop, not the prompt. 1 router · 14 agents · 21 skills · 8 workflows. Fail-closed gates, test honesty, anti-anchored review.

Semantic skill router for Claude Code — load only the skills you need, save 20k+ tokens per session