A Knowledge-Assetization OS for AI agents — an industry-specialized LLM wiki + business-logic core agents. Where manufacturing quality engineering meets agent harness engineering. Self-building, dogfooded, cross-platform.
This repository also configures its own agents. See what agent-wiki tells them →
Agent Claude Code
A specification for writing core-agent cards: files that define an agent’s role, project rules, allowed knowledge sources, recovery steps, and links to reusable skills.
Agent Claude Code
An example core for mobile and web apps that keeps records, statistics, and assistant answers based on one trusted data source.
Agent Claude Code
An example core for automated trading and other time-sensitive bots, with rules for checking whether a strategy can make money and for handling risky actions.
Agent Claude Code
An example core for serverless and edge applications—small services that run near users—with rules for deployment, database checks, production changes, and large uploads.
Agent Claude Code
An example core for factory production lines, covering processes, product and quality rules, production timing, defect categories, and escalation.
Agent Claude Code
An example agent for running data-collection pipelines, where separate collectors gather data from different channels. It tracks each collector's owner, service targets, failures, and recovery work using an external source of truth.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: