Policy Enforcement
Enforcing rules and guardrails on agent behavior. As of 2026-11-21, 262 indexed products offer it (96 with full profiles), in 10 forms: 207 MCP servers, 14 Infrastructure, 14 Plugins, 6 Agent skills. 117 were published in the last 90 days, against 63 in the 90 days before. OpenAI Agents SDK has the most GitHub stars, 25% of the total across 227 products with their own repository.
CapabilitySegment label: Crowded, slowing DER
Available as
All in the directoryProfiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.
MCP servers 207 indexed · 51 profiled
Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | archestraEnterprise AI Platform with guardrails, MCP registry, gateway & orchestrator | archestra-ai | 4.5k | today | ||
| 2 | Tracekit MCP gatewayMCP gateway you deploy: a Tracekit signer decides and signs each call; agents send each run's token. | Cygnux-Labs | 760 | today | ||
| 3 | omniclawThe first agentic payment network: policy-controlled, gasless, and real money-ready. OmniClaw CLI + Financial Policy Engine let autonomous agents pay and earn safely at machine speed. | omnuron | 571 | 5mo ago | ||
| 4 | CoWork-OSRent the model. Own everything else. Free, open-source AI app for real work. | CoWork-OS | 554 | 1d ago | ||
| 5 | Emilia ProtocolExact-action approval for consequential agent actions: request, track, and verify signed receipts. | emiliaprotocol | 525 | 5d ago | ||
| 6 | cordumThe action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence. | cordum-io | 507 | 2d ago | ||
| 7 | HyphaHarness-oriented agent system framework for production-grade LLM agent applications | CodeSoul-co | 452 | 6d ago | ||
| 8 | auraAURA is a production-tested SRE agent platform you can deploy in minutes. AURA handles the guardrails, APIs, state management, streaming, and failure handling required to put AI to work safely on production infrastructure. | mezmo | 415 | 1d ago | ||
| 9 | AISIX AI GatewaySelf-hosted AI gateway that governs MCP servers, LLM traffic, and A2A agents behind one endpoint | api7 | 230 | 1d ago | ||
| 10 | jevmemShared project rules and memory for AI coding agents: a JEVMEM.md in git, with a command guard. | Avinash-jetwani | 155 | 1d ago |
Infrastructure 14 indexed · 14 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | Portkey AI GatewayGateway that routes requests to many LLM providers with retries, fallbacks, load balancing, caching and guardrails; open-source core plus hosted control plane. | Palo Alto Networks (Portkey) | 13k | 1d ago | ||
| 2 | failproofaiObservability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement. | FailproofAI | 9.9k | today | ||
| 3 | BifrostGo-based LLM gateway exposing many providers through one OpenAI-compatible API with failover, load balancing, governance and an MCP gateway. | Maxim AI | 9.9k | today | ||
| 4 | planoPlano is an AI-native proxy server and data plane for agentic apps. Smart LLM routing, observability, agent orchestration, and guardrails so you stay focused on your agents core logic. | katanemo | 7.1k | 28d ago | ||
| 5 | future-agiOpen-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0. | future-agi | 2.3k | today | ||
| 6 | Multi-Agent-Medical-Assistant⚕️GenAI powered multi-agentic medical diagnostics and healthcare research assistance chatbot. 🏥 Designed for healthcare professionals, researchers and patients. | souvikmajumder26 | 1.0k | 1y ago | ||
| 7 | ai-engineer-notebooksHands-on, framework-free Colab notebooks for the AI Engineer / Forward Deployed Engineer (FDE) skill set — model APIs, structured output, tool calling, RAG, evals-as-the-spine, agents (loop from scratch, tool design, guardrails, MCP, Skills), fine-tuning vs LoRA, prompt-injection/security, LLMOps, and customer craft. Runs on the free Groq API. | calmrocks | 756 | 14d ago | ||
| 8 | AegisRuntime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes. | Justin0504 | 524 | 21d ago | ||
| 9 | dodoguardDodoGuard: Take AI Agents to Production. Test, validate, and operate AI Agents before and after deployment.for Dify, Coze, FastGPT, n8n, Tencent ADP, ByteDance HiAgent, and more. | dodoguardai | 275 | 1mo ago | ||
| 10 | awesome-agent-observabilityCurated list of LLM and AI agent observability and evaluation tools: tracing, evals, LLM-as-judge, guardrails, OpenTelemetry GenAI, MCP. | anhermon | 65 | 2d ago |
Plugins 14 indexed · 8 profiled
8 of these are Claude plugins, which Claude Code documents (protocol-level). DER
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | cc-safety-netA pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Devin CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi. | kenryu42 | 2.1k | 1d ago | ||
| 2 | netsuite-ai-companionGuides AI assistants that use the NetSuite AI Connector: tool-selection order, output formatting, NetSuite domain knowledge, multi-subsidiary and currency handling, and SuiteQL safety guardrails. Requires the NetSuite AI Connector Service. | oracle | 386 | 3d ago | ||
| 3 | governorClaude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails. | 0xhimanshu | 133 | 2mo ago | ||
| 4 | ultraship"ULTRASHIP" Claude Code plugin — 39 skills, 33 tools, 11 agents for ship-ready workflows: planning, review, pentesting, safety guardrails, canary monitoring, SEO/AI-readiness check, penetration testing, code review, competitive analysis, incident response. 1 dependency. 180 tests. MIT. | Houseofmvps | 124 | 4mo ago | ||
| 5 | project-sentinelMission control for long Claude Code runs: context and run progress at a glance, Autopilot handoffs, guardrails and a calm activity view, in the terminal and Claude Desktop. | Arjun0014 | 59 | 5d ago | ||
| 6 | swing-skillsOpen-source Claude Code skills — 6 cognitive firewalls block AI hallucination, bias & sloppy reasoning. npx skills add | TheStack-ai | 41 | 6mo ago | ||
| 7 | claude-bulkheadStop Claude Code and other coding agents from running rm -rf on an empty $VAR, pkill-ing your other dev servers, taking their ports, and git add -A-ing another session's edits. Hooks that know which session owns which process, port and git tree. Zero dependencies. | dooly6276 | 35 | today | ||
| 8 | 42crunch-api-security-testingAutomate API security directly in Claude Code with 42Crunch - automatically audit OpenAPI specs, detect vulnerabilities aligned with OWASP API Security risks (including BOLA/BFLA), and apply AI-powered fixes. Designed for AI-assisted development workflows, it provides continuous guardrails through an audit->scan->remediate->validate loop, ensuring APIs meet enterprise security standards before deployment. | 42crunch-ai | 1 | 4d ago |
Agent skills 6 indexed · 6 profiled
Protocol-level reach: 26 of the 45 active platforms AgentSidekick tracks document support for the Agent Skills format. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | stop-that-shitStop That Shit(别再造史了)|面向 Codex/GPT 场景的多平台 Hook + Skill Guard:拦截 AI coding agent 无需求的哈希、校验和与任务范围膨胀。 A multi-platform Hook + Skill Guard for AI coding agents in Codex/GPT workflows: stop unrequested hashes, checksums, and task-scope creep. | lennney | 4.0k | 2d ago | ||
| 2 | building-with-typesafe-jevUnofficial skill that teaches coding agents to build with TypeSafe AI's Jev: typed decisions, calibrated confidence, and prior art from 150+ community projects. | aaddrick | 158 | 1mo ago | ||
| 3 | arduino-azure-iot-edge-integrationDesign and implement Arduino integration with Azure IoT Hub and IoT Edge, including secure provisioning, resilient telemetry, command handling, and production guardrails. | github | — | 1d ago | ||
| 4 | llamaguardMeta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails. | Orchestra-Research | — | 1mo ago | ||
| 5 | nemo-guardrailsNVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU. | Orchestra-Research | — | 1mo ago | ||
| 6 | baoyu-wechat-summarySummarizes WeChat group chat highlights into a structured digest using the local wx-cli binary (https://github.com/jackwener/wx-cli). Generates a normal digest by default; a roast (毒舌) version is opt-in. Maintains per-group history (history.json + history-digests.jsonl), per-user profiles, and per-group fact memory (memory.md) across runs, with privacy guardrails baked in. Use when the user asks to "总结群聊", "群聊精华", "群聊摘要", "summarize group chat", "group chat digest", mentions a WeChat group name with a time range, says "帮我看看 XX 群最近聊了什么", "XX 群有什么值得看的", or asks to "回溯画像" / "初始化画像" / "backfill profiles". Adds the roast version when the user says "毒舌版", "roast 版", "再来个毒舌的", or similar. | JimLiu | — | 1d ago |
Libraries 6 indexed · 6 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | Guardrails AIPython framework that wraps LLM calls with input/output validators from a hub to detect PII, toxicity, jailbreaks and schema violations. | Guardrails AI | 7.6k | 3d ago | ||
| 2 | NeMo GuardrailsToolkit for adding programmable rails (topic control, jailbreak and content safety checks) to LLM apps using the Colang language. | NVIDIA | 7.5k | 2d ago | ||
| 3 | OpenAI GuardrailsLibrary that wraps OpenAI clients with configurable checks such as jailbreak, PII, moderation and hallucination detection. | openai | 268 | 3d ago | ||
| 4 | idun-agent-platform🟪 Open-source runtime that ships any LangGraph or Google ADK agent as a production-ready FastAPI service. Bundled , AG-UI copilotkit API, chat UI, 15+ guardrails, MCP, OpenTelemetry, OIDC. One pip install. Self-hosted, no vendor lock-in. | Idun-Group | 208 | 22d ago | ||
| 5 | sample-agentcore-enterprise-platformAmazon Bedrock AgentCore enterprise platform accelerator with AWS CDK, Terraform organization guardrails, MCP/A2A agents, security, memory, and observability. | aws-samples | 28 | 1d ago | ||
| 6 | Agentic_AI_EngineerMy complete journey to becoming an Agentic AI Engineer through structured learning, projects, experiments, and production-ready implementations of modern AI systems. | NIKHIL-KASHMEERABEN-RUPALA | 19 | 1mo ago |
Rules packs 6 indexed · 2 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | agentic-osGovernance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evidence. Drop-in rules and guardrails for Claude Code, Codex, Cursor, Copilot, and Antigravity, via AGENTS.md. | KbWen | 239 | 8d ago | ||
| 2 | araiYour AI assistant reads CLAUDE.md and ignores it anyway. Ārai makes instruction files enforced — hooks that block, a tamper-evident audit trail, per-rule compliance stats. | taniwhaai | 7 | today |
Frameworks 5 indexed · 5 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | agent-governance-toolkitAI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10. | microsoft | 6.6k | today | ||
| 2 | agentic_securityAgentic LLM Vulnerability Scanner / AI red teaming kit 🧪 | msoedov | 2.0k | 2d ago | ||
| 3 | LightAgentLightAgent: Lightweight Python framework for OpenAI-compatible agents with tools, memory, guardrails, tracing, lifecycle hooks, multi-agent collaboration, and workflows. | wanxingai | 1.2k | 6d ago | ||
| 4 | agentosTypeScript AI agent framework: cognitive memory, dynamic personalities, emergent behaviors and self-building designs | framerslab | 691 | today | ||
| 5 | orlojAn orchestration runtime for multi-agent AI systems. Declare agents, tools, and policies as YAML; Orloj schedules, executes, routes, and governs them for production-grade operation. | OrlojHQ | 127 | 1d ago |
Agent projects 2 indexed · 2 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | teaql-agent-kitA model-driven harness for AI coding agents: semantic modeling, app generation, progressive API Assist and evidence-based verification. | teaql | 2.8k | 11d ago | ||
| 2 | cuga-agentCUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web and APIs, OpenAPI/MCP integrations, composable architecture, reasoning modes, and policy-aware features. | cuga-project | 1.2k | 1d ago |
AI APIs 1 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | Amazon BedrockManaged AWS service offering models from Anthropic, Meta, Mistral, Amazon and others through one API, with knowledge bases and guardrails. | Amazon Web Services | — | — |
Agent SDKs 1 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | OpenAI Agents SDKLightweight SDK for multi-agent workflows with agents, handoffs, guardrails, sessions and built-in tracing; works with OpenAI and other model providers. | openai | 31k | today |
Which platforms these forms can reach
All platformsProtocol-level: the platform documents support for the standard. No specific pairing has been tested.
MCP servers 207 indexed here
36 platforms document MCP support CUR.
ContinueOpenCodeClaude CodeCodexGemini CLIZedOpenHandsClineWarpgooseQwen CodeBolt (bolt.new)KiroAmazon Bedrock AgentCoreAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)Augment CodeChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)Gemini Enterprise Agent Platform (formerly Vertex AI / Vertex AI Agent Builder)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJetBrains AI AssistantJunieLovableMicrosoft Copilot StudioReplit AgentTabninev0
Agent skills 6 indexed here
26 platforms document Agent Skills support CUR.
OpenClawOpenCodeClaude CodeCodexGemini CLIOpenHandsWarpgooseBolt (bolt.new)KiroAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)ChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJunieReplit AgentTabnine
Platforms publishers name
| Platform | Profiled products naming it |
|---|---|
| Claude Code | 8 |
| Codex | 3 |
| Cursor | 2 |
| Google Antigravity | 2 |
| Devin | 1 |
| GitHub Copilot | 1 |
| OpenClaw | 1 |
| OpenCode | 1 |
| Amazon Bedrock AgentCore | 1 |
| Claude Desktop | 1 |
Integrations most often paired
Third-party services named by products with this capability, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| GitHub | 3 | 1.1% |
| Kubernetes | 3 | 1.1% |
| AWS | 2 | 0.8% |
| Stripe | 2 | 0.8% |
| Azure | 1 | 0.4% |
| BigQuery | 1 | 0.4% |
| Databricks | 1 | 0.4% |
| Gmail | 1 | 0.4% |
| Google Ads | 1 | 0.4% |
| MySQL | 1 | 0.4% |
| OpenAPI | 1 | 0.4% |
| PayPal | 1 | 0.4% |
Keywords that trigger this capability
Matched as whole words, ignoring case, in a product's name, description and repository topics.
| Keyword | Products matched |
|---|---|
| policy enforcement | 25 |
| policy engine | 19 |
| guardrails | 213 |
| open policy agent | 1 |
| rego | 3 |
| content filtering | 1 |
| usage policy | 0 |
Segment statistics
Whole catalogue (262 indexed products). Calculated 2026-11-21.
Crowded, slowing. Among the largest fifth of capabilities, but its launches grew more slowly than the catalogue’s. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 0.104 means stars are spread as if across about 10 equally popular projects — unconcentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.
Limits
- Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
- Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
- Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
- Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.
Page data last updated .