Skip to content
/
§ a11

Governance / observability

Hooks, lint, audit ledger, policy engine. Where compliance enforcement lives.

31 primary frameworks · 15 lower-confidence entries

OpenHarness
openharness
★ 13k
Tier A

Open-source Python agent runtime providing complete harness infrastructure: tools, memory, governance, swarm coordination, and messaging gateway.

Trae Agent
trae-agent
★ 12k
Tier A

Research-friendly open-source CLI coding agent by ByteDance, designed for academic ablation studies and modular LLM provider swapping.

Sweep AI
sweep
★ 7.7k
Tier A

Autonomous GitHub bot that converts issues to pull requests using a sequential multi-agent pipeline.

Agent Governance Toolkit (microsoft)
agent-governance-toolkit
★ 2.3k
Tier A

Enterprise-grade AI agent governance: YAML policy enforcement, 12-vector prompt injection defense, zero-trust identity, tamper-evident audit logging, and OWASP…

TDD Guard
tdd-guard
★ 2.1k
Tier A

Mechanically enforces the Red-Green-Refactor TDD cycle by blocking file writes that violate TDD principles via a PreToolUse hook and LLM semantic validator.

Agentic Coding Flywheel Setup (ACFS)
flywheel-sdd
★ 1.5k
Tier A

Take a complete beginner from laptop to three AI coding agents running on a VPS in 30 minutes via an idempotent manifest-driven Bash installer.

leash (strongdm)
leash-strongdm
★ 565
Tier A

Wraps AI coding agents in containers with eBPF-enforced Cedar policies, making policy violations (unauthorized file access, network connections, MCP tool…

Sponsio
sponsio
★ 445
Tier A

Deterministic runtime enforcement library checking every AI agent tool call against pure-code contracts at p50 0.139ms with zero LLM cost.

mcp-server-spec-driven-development
mcp-server-spec-driven-development
★ 430
Tier A

Provides a minimal MCP server with three EARS-format prompts that enforce the requirements→design→code spec-driven development pipeline in any MCP-compatible…

OpenClaw.NET
openclaw-net
★ 347
Tier A

Self-hosted NativeAOT .NET agent gateway with inspectable Passive Harness Contracts, Evidence Bundles, and a Governance Ledger for observable, auditable agent…

DashClaw
dashclaw
★ 268
Tier A

Full-stack AI agent governance platform: pre-action policy enforcement, multi-channel human approval routing, durable finality, audit trails, and Code Sessions…

ralphy-openspec
ralphy-openspec
★ 186
Tier A

Combines OpenSpec spec governance with Ralph Loop iterative execution and a SQLite run ledger to provide crash-recoverable, budget-tracked AI coding sessions.

GAAI Framework
gaai-framework
★ 142
Tier A

Dual-track governed delivery system: Discovery defines scope, Delivery executes in isolated OS processes, backlog-as-contract prevents scope drift, persistent…

AI Governor Framework (Fr-e-d)
ai-governor-framework
★ 78
Tier A

Provides structured governance protocols and in-repo rules to transform AI assistants into disciplined engineering partners that respect project architecture…

Spartan AI Toolkit
spartan-ai-toolkit
★ 72
Tier A

Engineering discipline layer delivering 73 commands, 9 reviewer agents, 8 stack profiles, and mandatory git worktree + quality gate enforcement for every…

IBM IaC Spec Kit
iac-spec-kit
★ 64
Tier A

Adapts SDD methodology to IaC by separating generic infrastructure specifications from cloud-specific implementation plans, enabling multi-cloud comparison and…

CLAUDER
clauder
★ 58
Tier A

Safety-first Claude Code toolkit with 14 PreToolUse/PostToolUse hooks, SQLite audit trail, web tracer, and 67 domain expansion agents.

Claude Code Guardrails
claude-code-guardrails
★ 54
Tier A

Automates git safety in Claude Code sessions: blocks writes to protected branches, snapshots every change as a micro-commit, and squashes session checkpoints…

VNX Orchestration
vnx-orchestration
★ 34
Tier A

Governance-first multi-agent orchestration: every agent action produces a receipt, quality gates use deterministic file-based verdicts (not LLM judgment), and…

AgentLint
agentlint
★ 33
Tier A

Scores agent harness files (CLAUDE.md, AGENTS.md, hooks, CI) against 58 evidence-backed checks to quantify harness quality and provide guided fix plans.

GreatCTO
greatcto
★ 32
Tier A

Full SDLC pipeline (57 specialist agents, 2 human gates, 12 jurisdiction detectors, 33+ compliance frameworks) for solo founders —…

Forge (LucasDuys)
forge-lucasduys
★ 29
Tier A

Replace the developer as the state machine by running tasks in isolated git worktrees with TDD, automatic backpropagation of runtime failures into specs, and a…

WORCA
worca
★ 26
Tier A

9-stage autonomous development pipeline with OS-level governance enforcement, per-agent model routing, real-time WebSocket dashboard, and fleet/workspace…

HOTL Plugin
hotl-plugin
★ 22
Tier A

Human-on-the-loop structured workflows that enforce design-before-code, resumable execution with state persistence, and explicit branch disposition — across 5…

MartinLoop
martinloop
★ 22
Tier A

Governance control plane that wraps Claude Code/Codex loops with hard budget caps, 11-class failure taxonomy, Red-Blue adversarial probes, safety leash, and…

AgentTier
agenttier
★ 19
Tier A

Kubernetes-native control plane for isolated, persistent sandbox environments for AI agents.

pi-steering-hooks
pi-steering-hooks
★ 5
Tier A

Pre-tool regex guardrails for the pi coding agent — deterministic, zero-token enforcement of behavioral rules with a self-authorizing override escape hatch.

AI Flywheel (agent-flywheel-plugin)
ag-coding-flywheel
★ 2
Tier A

Prevent multi-agent chaos through a structured bead lifecycle with file reservations, typed completion attestations, adversarial duel review, and 36-code…

cc-audit
cc-audit
★ 0
Tier A

CI gate that lints CLAUDE.md/AGENTS.md against a 12-rule baseline, detecting missing rules and leaked secrets in pull requests.

openspec-reviewed-workflow
openspec-reviewed-workflow
★ 0
Tier A

Inserts a mandatory evidence-driven codebase investigation gate between proposal and specs in OpenSpec workflows, forcing the AI to investigate existing…

Zenable
zenable
★ 0
Tier A

Commercial AI governance/compliance product (zenable.io) — no public source available.

Show 15 lower-confidence entriestier-b · tier-c · unknown · delta reports

These entries map to § a11 by tag but carry weaker evidence — fewer documented primitives, delta reports of absent skills, or marketing-only sites without a public repo. They're listed for completeness; treat them with appropriate caution.

Claude Scientific Skills ★ 26k
claude-scientific-skills

Provides 138 curated skills for scientific Python workflows across biology, chemistry, medicine, physics, and engineering — making AI coding agents significantl…

Parlant ★ 18k
parlant

Runtime conversation governance for customer-facing AI agents: per-turn contextual matching assembles only relevant behavioral rules into each LLM prompt, preve…

HumanLayer / CodeLayer ★ 11k
humanlayer

Orchestrate parallel Claude Code sessions per Linear ticket via dedicated git worktrees (MULTICLAUDE pattern) with structured research→plan→implement→PR workflo…

GitHub Agentic Workflows ★ 4.5k
gh-aw-githubnext

Write agentic workflows in natural language markdown, compile to GitHub Actions, run with production-grade security guarantees — read-only permissions by defaul…

ContextForge ★ 3.8k
contextforge

Federates MCP servers, REST APIs, and A2A agents behind one authenticated endpoint with governance plugins and OpenTelemetry observability.

AgentGateway ★ 2.9k
agentgateway

Rust-based agentic proxy providing drop-in security, observability, and governance for MCP, A2A, and LLM traffic across any AI framework.

cmux (coder) / Mux ★ 1.8k
cmux-coder

Desktop app with custom agent loop for parallel, isolated, multi-model agentic development with Plan/Exec modes, worktree isolation, and sub-agent code review.

ClawManager ★ 1.4k
clawmanager

Kubernetes-native control plane for multi-tenant AI agent instance management with AI Gateway governance, desired-state orchestration, and skill/channel resourc…

notque/claude-code-toolkit ★ 388
notque-cc-toolkit

Enterprise-scale Claude Code toolkit with 44 domain agents, 77 Python hooks, a confidence-decaying SQLite learning database, AFK headless mode, and formal promp…

Agent FM ★ 40
agent-fm

Ambient audio radio station for AI coding agent sessions — narrates progress, blockers, and decisions without terminal attention.

claude-code-settings-for-unity ★ 37
nowsprinting-cc-unity

Enforces test-first Unity C# development via a two-agent (Plan + test-designer) pipeline with a TESTABILITY gate before any code is written.

awesome-gemini-cli-subagents ★ 33
ankitmundada-gemini-subagents

Provide 128 specialized persona-MD agents for Gemini CLI with per-agent model routing and temperature optimization.

bmad-architecture-agent ★ 15
bmad-architecture-agent

Provides 8 specialized architecture expert AI personas (cloud, data, integration, platform, governance) as a BMAD expansion pack for architecture-heavy projects…

CueAPI ★ 8
cueapi

Replaces cron for AI agent tasks with outcome-aware scheduling: success/failure tracking, automatic retries, and execution history.

AI Dev Workflow Kit ★ 4
ai-dev-workflow-kit-aahil

Portable .ai-kit/ folder enforcing EPCC workflow loop, Max-2 Resource Rule, and Decision Gates to prevent context overload and unplanned agent behavior.