Multi-agent AI organisation
A production multi-agent system running research, code review, content, bots, and monitoring on local infrastructure.
A systems index for the notebook. Local agents, automation workflows, memory, web operations, and a few practical builds around FPV and visual work.
A production multi-agent system running research, code review, content, bots, and monitoring on local infrastructure.
Local operator console for Discord, scheduled jobs, browser tooling, persistent memory, and bounded delegation to coding/design workers.
A small local review layer for Hermes and Mads. It checks agent runs against artifacts instead of trusting green prose.
Repo-grounded frontend generation with no-apply-by-default safety, static verification, scorecards, and manual winner bundles.
Persistent memory routed through a local OpenAI-compatible Ollama endpoint. Built around durable facts rather than dumping every session into prompts.
Small local-first checks for live sites: HTTP status, crawlability, deployment freshness, screenshots, and compact reports.
A Windows 11 VM-hosted early-access game server that went live the same hour a friend asked for it, then got stabilized with the AI operations stack around it.
Discord-native shopping list with quick-add, store-aware sorting, and daily price alerts. Flask plus Nextcloud. Used daily.
AI-assisted modelling and print iteration for FPV camera mounts. First product: FlexMount Pro.