workflow-governance

Experimental OpenCode-first orchestration plugin inspired by the Tang Dynasty's Three Departments and Six Ministries: draft, review, dispatch, execute, and audit.

Lightweight workflow guardrails that keep AI-assisted engineering scoped, reviewable, recoverable, and safe to hand off.

Codex 用人機共同開發下的 Loop - CER 工作法：Controller 統籌，同一 Executor 寫檔，只有風險需要時才由 Reviewer 驗收。 Human-guided development loop for Codex:: Controller plans, one Executor writes, and Reviewers check only when risk warrants it.

Agent hooks governance layer for task scope, policy gates, and auditable enforcement.

Official Rust SDK for AxonFlow — runtime control, MCP policy enforcement, approvals, and audit trails for production AI

Official Java SDK for AxonFlow — runtime control, MCP policy enforcement, approvals, and audit trails for production AI

Official TypeScript SDK for AxonFlow — runtime control, MCP policy enforcement, approvals, and audit trails for production AI

AI-agent workflow governance kit with multi-agent routing, runtime safety gates, semantic skill evaluation, evidence ledger, and readiness checks.

Review-first Codex skill for designing safe, gated agent loops before they become scaffolds or automation.

Implement a governance workflow plugin for OpenCode that maps the Tang Dynasty’s system into AI task drafting, review, dispatch, execution, and audit.

Official Go SDK for AxonFlow — runtime control, MCP policy enforcement, approvals, and audit trails for production AI

Official Python SDK for AxonFlow — runtime control, MCP policy enforcement, approvals, and audit trails for production AI

Exception-to-change risk map for Camunda incidents and IBM change-window exposure.

Governed AI coding workflow toolkit built with tmux, shell, handoff artifacts, validators, and Human Owner gates.

Lumio is a B-end enterprise workspace platform for governed request, approval, operations, review, and audit workflows.

Evidence-led lifecycle governance for reusable Agent workflows.

A portable workflow-governance skill for making high-consequence agent operations authorized, bounded, reversible, and auditable.

Public demo of governance outside the model for bounded agent control

Local deterministic CLI that assembles inspectable receipts for AI coding-agent work sessions from declared artifacts.

State-space gate engine for AI agent workflows: static gates, taboo/case matching, drift/anomaly scoring, human attention routing, and audit-ready gate decisions. / AIエージェント工程向けの状態空間ゲートエンジン。静的ゲート、禁忌・採用/却下例マッチング、ドリフト/異常検知、人間確認キュー、監査可能な判定ログを扱う。