Havuz

The open standard for runtime agent control — declarative hooks, policy enforcement, and observability across AI agent frameworks.

Companion repository to "Governed Agentic AI in IT Service Management" (IEEE Software, 2026). Tool contracts, OPA policies, evidence schemas

AutoHarness: Automated Harness Engineering for AI Agents

Yao Meta Skill, tekrar kullanılabilir agent skills oluşturma, değerlendirme, paketleme ve yönetişim süreçlerini tek bir araç zincirinde birleştiren Python projesidir.

Neden yükseliyor · Agent skills ve bunların platformlar arasında taşınabilirliği gündemde; proje, üretimin yanı sıra eval ve yönetişim süreçlerini de kapsayan geniş bir kapsam sunuyor. 180 günde 2675 yıldız ilgiye işaret etse de son 28 günde commit ve farklı yazar olmaması güncel geliştirme veya topluluk ivmesi için kanıt sağlamıyor.

AgentGuard: Zero-Trust Security Foundation for AI Agents

A Geiger counter for AI agents — one read-only command that inventories every agent, MCP server, plugin, and AI extension on a machine

An accelerator that reviews a Microsoft Fabric tenant end-to-end through metadata-only scans across governance, cost, capacity, performance,

Open-source security gateway & static scanner for AI agents. Enforce role-based access control (RBAC), human-in-the-loop approvals, segreg

Build AI agents you can trust in production. AgentFlow4J is a framework and runtime for governed, stateful multi-agent systems on the JVM.

CloakPipe is the verifiable control plane for production AI agents: evaluate a release, certify it, enforce it at runtime, and prove what ha

Longitudinal relational modeling for reflective agents: behavioral signals, evolving subject profiles, inspectable runtime governance.

AI agent firewall that intercepts tool calls (file, shell, network) and enforces deterministic policies at sub-microsecond latency using CEL

Git & file-based SOC 2

Open-source governance infrastructure for AI-assisted legal work

Machine-readable architecture decision records. Git-native decision memory and governance for human and agent-authored plans -- lint, CI, an

The definitive PMO operating manual & executable skill framework aligned with PMI PMBOK® 8th Edition. Standardizes lifecycle delivery (Predi

Control consequential AI-agent actions, from financial transactions and database migrations to dependency upgrades and production changes, b

Build, govern, and ship Streamlit-in-Snowflake apps with Claude Code and AI agents

See what AI coding agents do on a machine. The open-source observer behind Phigon.

Govern: one Decionis verdict before a workflow step runs — a deploy, a migration, an infrastructure change, an agent's action — with a signe

Agyn is an open-source Kubernetes-native runtime that moves AI agents like Claude Code and Codex from laptops to company infrastructure with

Open-source AI-era employment platform connecting skills, jobs, enterprises, governance, and AI agents.

Run-aware token governance for multi-agent systems.

Custom proactive skills for Azure SRE Agent — governance, cost intelligence, architecture quality, AI workload posture

A Sovereign Agent Governance Protocol for Deep-Water Workflows

Clyro is a governance platform for AI agents. While most tools let you watch agents fail, Clyro stops failures before they happen, catching

Synthetic datasets, experiment protocols, and evaluation code for "Governed Memory: A Production Architecture for Multi-Agent Workflows"

🎱 AI Agent Governance Framework — Constrain how AI Agents behave in your project. pip install pattern8

十三希诺 Agent 工作流 · 中文源库：把工程纪律做成可机检门禁的元工作流 Skill 家族——三级跑道／判级／GATE 12 字段可复跑证据／405 条细则库／五包交付（核心+流程+角色+产品工程+单文件蒸馏），五平台注入适配。docs/ 为开发工作区，实验数据已归档。En

Claude Code governance templates by tech stack : CLAUDE.md, scoped rules, architecture docs, cost control & dev-level adaptation

A structured template for AI coding agents. Three markdown layers: agent.md for session context, docs/ for project knowledge, and a governan

mori MCP server — a governed memory layer for AI coding agents.

Checks every AI agent action against your company's real rules before it runs. Git-native, PR-reviewed.

A decision protocol for AI agents — critical thinking, evidence verification, and structured review. Less confident advice, more testable de

DeepSeek Harness (DSH) plugin: a read-only ledger for the plugins you already have installed — a capability inventory with file:line evidenc

A verifiable semantic kernel for legacy business systems: build a governed domain ontology from your existing schema, and make every verdict

Local-first control plane for verifiable AI-assisted software engineering and Linux operations with structured knowledge substrate

Scan a codebase for AI SDKs, MCP servers and agent tools; map risks to NIST AI RMF, ISO 42001, EU AI Act and the OWASP LLM and Agentic Top 1

Umbrella for the LLM Dark Patterns Hooks suite — single-purpose Claude Code Stop hooks that suppress sycophancy, paternalism, false-success,

PotBot POTFolio: any basket of Solana assets as one liquid token. Non-custodial, Pyth-priced, redeemable any time. Anchor program + Next.js

A managed proxy gateway and compiler for AI agents. It takes noisy OpenAPI/MCP directories, compresses them in flat mode, saves tokens, and

Constitutional governance runtime for autonomous AI agents

Provena : Context governance for agentic AI — tamper-evident audit trails, provenance validation, EU AI Act compliance. 6 framework adapters

SHACKLE — a governance protocol and policy-decision daemon for autonomous AI agents. Enforces guardrails, budget/loop limits, and policy con

洁癖.skill：让 AI Agent 少留痕，留下的都有用。 Tidy Skill: make AI agent artifacts intentional, scoped, and disposable when needed.

多 AI 协作开发的项目治理引擎：Scene→Spec→Task 文件化追溯 + 结构门禁，只引导不强制。MCP 服务 + CLI 双形态，文件即真相，零模型依赖——让 AI 会话有记忆、有依据、不打架。

The Company Brain your agents install — use your coding agent to run projects and coordinate agents, not just code. Cross-project knowledge

Supervisor/Lead/Peer governance for multi-agent coding — one policy core enforced identically on Pi and Claude Code, brief-scoped authority,

Harmovela Protocol: open coordination protocol for autonomous systems — event, task, state, delegation, recovery, and governance.