Shared workspace for AI agents and human developers. See, audit, and review every change AI makes to your codebase. Multi-language graph (Python/TypeScript), MCP-native, local-first.
A shared record for AI agents: decisions, completed work, and commitments, with sources. Git-native engineering memory and a self-hosted state server.
Project rules for AI coding agents. An MCP server gives Claude Code, Codex CLI and Antigravity the rules for the files they are about to edit; AST checks run in a git pre-commit hook and in CI (aegis check). Zero dependencies, Python 3.9+, Apache-2.0.
Local-first anti-corruption defense for AI coding teams: symbol-level change impact across 5 languages, P95-calibrated gates, fail-closed evidence, and a Skill playbook agents actually read.
Point your coding agent at your repo: a 5-question AI-code-governance self-audit. By Black Box Research Labs.
Catch AI code mistakes before they ship — 50+ checks for hallucinated APIs, stub functions, hardcoded secrets, and SQL injection. SARIF output for GitHub Code Scanning.
Project-level change routing and reuse governance for AI coding agents. Helps Codex and Claude Code find the right capability boundary, avoid duplicate implementations, respect write constraints, and calibrate routing decisions for large full-stack repositories.
Point your coding agent at your repo: an air-gapped sweep that finds your kill zone — files at high complexity × high churn × security. By Black Box Research Labs.
面向 AI 参与开发的代码治理框架：静态规则源(ADU) + 运行时过程协议(ADP) + 会话入口路由(CLAUDE.md)。A code governance framework for AI-assisted development — scope lock, @gov annotations, issue trace, and read-only audits that keep AI-generated code reviewable.
Make AI coding agents produce Rust that is verifiable, secure by default, and repeatable. 8 rules, 9 skills, 20 katas, 7 verification gates.
AI-native coding governance framework, architecture-agnostic: intent routing, red-line pre-commit gates, doc gardener, self-evolution loop. Ships with a replaceable COLA DDD example rule pack.
Deterministic pre-modification governance layer for Python code changes — semantic similarity, behavioral analysis, and multi-signal fusion producing SAFE, REVIEW, or BLOCK decisions before repository modification is attempted.
Case law for codebases: repo-specific verification rules, Claude Code enforcement hooks, and positive-control audits.
A standardized instruction set and workflow protocol for AI-assisted programming that enforces strict behavioral constraints and surgical editing standards. This framework ensures consistent, traceable, and precise code modifications through a governance-first approach.
AI-generated React + Supabase app (built with Lovable and Claude Code) scanned by Norma for AI code governance and production readiness. Fork it, connect it to Norma for free, fix the findings, re-scan.
Deterministic PR governance GitHub Action: blocks architecture-boundary violations, flags naming/forbidden patterns, and catches behavior changes with differential property tests. LangGraph + Tree-sitter + Hypothesis, no LLM.
Production-oriented architecture governance and topology-scoped scaffolding for AI-assisted development.
Moderne — independent third-party profile of a public API surface, by API Evangelist. Moderne is a deterministic, large-scale code transformation and mass-remediation platform built on the open-source OpenRewrite framework and its Lossless Semantic Trees (LST) — compiler-accurate, format-preserving models of source code.
给 AI 一个目标，它自己跑完，交你一份带证据的交付报告：运行时门禁拦截 + L2 隔离分支 + JSONL 审计。适用于 Claude Code 等支持 hook 的 CLI。
EPOCH: the control and intelligence plane for software that never stops changing. IBM Bob drives governed changes through MCP; EPOCH measures trajectory, drift, invariants, incidents and counterfactual futures.
To associate your repository with the code-governance topic, visit your repo's landing page and select "manage topics."