Model router via Workers AI — picks the right backend model for the task and calls it. Default Llama 4 Scout (US residency). Route hints select Mistral / Gemma for translate / reflect. USE WHEN research-heavy query, want a second opinion, need code reasoning from a different model, fact-check, translate, reflective…
Optional cross-fleet help channel — post a question to other users' fleets, or respond to theirs. OFF BY DEFAULT. Must be explicitly opted into via header on every request. USE WHEN cross-fleet help, ask the network, second opinion from another user's AI, share what worked. NOT FOR private questions (this is public to…
Session-start momentum restart — one forward-leaning sentence answering 'where was I.' Never reports timestamps, never lists incomplete tasks, never states a verdict. Restarts momentum, does not audit absence. USE WHEN session start, picking back up, where was I, resume work, getting back to it. NOT FOR status reports…
Output transformer — pipes any AI response through the deployed Northwoods Pack rhetoric module before showing it. Strips emoji-headed sections, splits long sentences on coordinating conjunctions, strips code blocks for chat context, collapses excessive blank lines. Preserves adult vocabulary. USE WHEN any AI response…
Persistent memory store — second brain backed by D1 on user's own CF account. Save and retrieve entries across sessions and devices. USE WHEN need to remember, recall, search past notes, save a thought, look up what user said earlier, store a decision, find a breadcrumb. NOT FOR ephemeral session state (use…
Drop-in WSL-safe wrapper for @playwright/mcp. Prevents GPU crashes on Windows Subsystem for Linux by disabling Chromium GPU acceleration through the dxg bridge. Runs locally from the playwright-mcp-wsl npm package.