Top 100 Guardrails Repositories
Ranking
| Ranking | Project Name | Stars | Forks | Language | Open Issues | Description | Last Commit |
|---|---|---|---|---|---|---|---|
| 1 | litellm | 47,917 | 8,253 | Python | 1375 | Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropi... | 2026-05-22 |
| 2 | gateway | 11,819 | 1,078 | TypeScript | 83 | A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API. | 2026-05-19 |
| 3 | free-code | 8,374 | 1,993 | TypeScript | 8 | The free build of Claude Code. All telemetry removed, security-prompt guardrails stripped, all experimental features enabled. | 2026-04-01 |
| 4 | baml | 8,281 | 422 | Rust | 187 | The AI framework that adds the engineering to prompt engineering (Python/TS/Ruby/Java/C#/Rust/Go compatible) | 2026-05-22 |
| 5 | presidio | 8,229 | 1,060 | Python | 53 | An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines. | 2026-05-20 |
| 6 | guardrails | 6,902 | 612 | Python | 21 | Adding guardrails to large language models. | 2026-05-19 |
| 7 | superagent | 6,612 | 960 | TypeScript | 5 | Superagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers. | 2026-04-11 |
| 8 | Guardrails | 6,208 | 684 | Python | 82 | NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems. | 2026-05-21 |
| 9 | bifrost | 5,141 | 623 | Go | 214 | Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS. | 2026-05-22 |
| 10 | mcp-context-forge | 3,757 | 670 | Python | 856 | An AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails and management. Optimizes Agent & Tool call... | 2026-05-22 |
| 11 | archestra | 3,726 | 848 | TypeScript | 83 | Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator | 2026-05-22 |
| 12 | openlit | 2,461 | 280 | TypeScript | 15 | Open source platform for AI Engineering: OpenTelemetry-native LLM Observability, GPU Monitoring, Guardrails, Evaluations, Prompt Management, Vault, Playground. 🚀💻 Integrates with 50+ LLM Providers, ... | 2026-05-22 |
| 13 | ragbits | 1,646 | 137 | Python | 40 | Building blocks for rapid development of GenAI applications | 2026-05-18 |
| 14 | llmgateway | 1,232 | 139 | TypeScript | 24 | Route, manage, and analyze your LLM requests across multiple providers with a unified API interface. | 2026-05-22 |
| 15 | future-agi | 1,015 | 203 | Python | 53 | Open-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. | 2026-05-22 |
| 16 | shellfirm | 912 | 33 | Rust | 1 | Safety guardrails for ai coding agents and human terminal commands | 2026-05-15 |
| 17 | GoModel | 889 | 60 | Go | 7 | AI gateway written in Go. Lightweight unified OpenAI-compatible API for OpenAI, Anthropic, Gemini, Groq, xAI & Ollama. LiteLLM alternative with observability, guardrails, streaming, costs and usage tr... | 2026-05-22 |
| 18 | Multi-Agent-Medical-Assistant | 888 | 197 | Python | 2 | ⚕️GenAI powered multi-agentic medical diagnostics and healthcare research assistance chatbot. 🏥 Designed for healthcare professionals, researchers and patients. | 2025-05-03 |
| 19 | cuga-agent | 738 | 131 | Python | 63 | CUGA 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-aw... | 2026-05-21 |
| 20 | awesome-azure-policy | 538 | 112 | - | 0 | A curated list of blogs, videos, tutorials, code, tools, scripts, and anything useful to help you learn Azure Policy - by @JesseLoudon | 2026-04-08 |
| 21 | agentos | 472 | 68 | TypeScript | 0 | Build autonomous AI agents with adaptive intelligence and emergent behaviors, included with multimodal RAG and optional HEXACO personalities. | 2026-05-22 |
| 22 | AgentDoG | 470 | 19 | Python | 1 | A Diagnostic Guardrail Framework for AI Agent Safety and Security | 2026-05-14 |
| 23 | Qwen3Guard | 462 | 31 | Python | 11 | Qwen3Guard is a multilingual guardrail model series developed by the Qwen team at Alibaba Cloud. | 2025-10-21 |
| 24 | baseline-environment-on-aws | 459 | 72 | TypeScript | 5 | Baseline Environment on AWS(BLEA) is a set of reference CDK template to establish secure baseline on standalone-account or ControlTower based multi-account AWS environment. This solution provides basi... | 2026-02-01 |
| 25 | evolving-agents | 451 | 35 | Python | 16 | Your toolkit for autonomous, evolving agent ecosystems. Create, execute, govern, and evolve agents that learn from experience, collaborate, build new capabilities, and operate safely within defined gu... | 2025-11-24 |
| 26 | research-units-pipeline-skills | 438 | 32 | Python | 0 | Research pipelines as semantic execution units: each skill declares inputs/outputs, acceptance criteria, and guardrails. Evidence-first methodology prevents hollow writing through structured intermedi... | 2026-04-17 |
| 27 | invariant | 421 | 46 | Python | 9 | Guardrails for secure and robust agent development | 2026-01-12 |
| 28 | modelence | 404 | 38 | TypeScript | 1 | Modelence is a full-stack framework for building production web apps with a built-in database, authentication and monitoring. Modelence is opinionated and AI agent-first, which means it's optimized fo... | 2026-05-21 |
| 29 | lc-studylab | 351 | 70 | Python | 1 | LC-StudyLab 是一个完整演示 LangChain v1.0 全家桶能力的开源项目，整合了 LangGraph、DeepAgents、RAG 检索增强生成、Guardrails 安全校验与流式输出智能体等核心特性，帮助开发者系统掌握 LangChain v1 的所有关键组件 | 2025-12-09 |
| 30 | LLMs-Finetuning-Safety | 350 | 37 | Python | 3 | We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20 via OpenAI’s APIs. | 2024-02-23 |
| 31 | statewright | 345 | 9 | Rust | 1 | State machine guardrails for AI agents | 2026-05-21 |
| 32 | opencode-swarm | 333 | 33 | TypeScript | 64 | Architect-centric agentic swarm plugin for OpenCode. Hub-and-spoke orchestration with SME consultation, code generation, and QA review. | 2026-05-22 |
| 33 | harness | 327 | 45 | Python | 0 | Harness is an AI Agent development guardrail Meta-Skill that establishes four layers of defense for any project in one command: knowledge management, architecture constraints, feedback loops, and entr... | 2026-05-04 |
| 34 | CoWork-OS | 318 | 52 | TypeScript | 1 | Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and artifacts. | 2026-05-22 |
| 35 | Harmonize | 315 | 14 | Swift | 0 | Harmonize is a modern linter for Swift that allows you to write architectural lint rules as unit tests. In the era of AI-generated code, it provides your team with deterministic guardrails to keep you... | 2026-05-12 |
| 36 | Sponsio | 313 | 22 | Python | 0 | Deterministic safety solutions for probabilistic AI agents | 2026-05-22 |
| 37 | packmind | 283 | 14 | TypeScript | 21 | Packmind seamlessly captures your engineering playbook and turns it into AI context, guardrails, and governance. | 2026-05-22 |
| 38 | guardrails | 257 | 26 | Clojure | 0 | Efficient, hassle-free function call validation with a concise inline syntax for clojure.spec and Malli | 2026-05-16 |
| 39 | agent-control | 249 | 34 | Python | 17 | Centralized agent control plane for governing runtime agent behavior at scale. Configurable, extensible, and production-ready. | 2026-05-21 |
| 40 | ultimate_bug_scanner | 241 | 34 | Shell | 0 | Static analysis tool that catches 1000+ bug patterns across all popular programming languages, with auto-wiring into AI coding agent quality guardrails | 2026-05-13 |
| 41 | paig | 213 | 220 | CSS | 53 | PAIG (Pronounced similar to paige or payj) is an open-source project designed to protect Generative AI (GenAI) applications by ensuring security, safety, and observability. | 2025-08-05 |
| 42 | openai-guardrails-python | 209 | 34 | Python | 4 | OpenAI Guardrails - Python | 2026-03-28 |
| 43 | CKA-Agent | 203 | 45 | Python | 1 | [ICML 2026 & ICLR 2026 AIWILD] Official Implementation of the CKA-Agent, "The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search". | 2026-05-20 |
| 44 | changeway_guardrails | 190 | 18 | - | 0 | 2025-07-26 | |
| 45 | azure-policy-as-code | 185 | 77 | HCL | 4 | Bicep and Terraform code examples for policy-as-code workflows. Azure governance guardrails and automation - by @JesseLoudon | 2024-04-20 |
| 46 | idun-agent-platform | 184 | 9 | Python | 72 | 🟪 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 in... | 2026-05-22 |
| 47 | cloud-guardrails | 183 | 17 | HCL | 1 | Rapidly apply hundreds of security controls in Azure | 2025-05-01 |
| 48 | gate22 | 176 | 22 | TypeScript | 17 | Open-source MCP gateway and control plane for teams to govern which tools agents can use, what they can do, and how it’s audited—across agentic IDEs like Cursor, or other agents and AI tools. | 2025-12-12 |
| 49 | AgentGuard | 160 | 8 | JavaScript | 1 | Real-time guardrail that shows token spend & kills runaway LLM/agent loops. | 2025-07-31 |
| 50 | fast-llm-security-guardrails | 151 | 21 | Python | 1 | The fastest Trust Layer for AI Agents | 2026-02-03 |
| 51 | guardrail | 151 | 27 | Python | 0 | GuardRail: Advanced tool for data analysis and AI content generation using OpenAI GPT models. Features sentiment analysis, content classification, trend analysis, and tailored GPT model usage. Ideal f... | 2023-12-12 |
| 52 | pi-guardrails | 146 | 23 | TypeScript | 2 | Security hooks for Pi. Prevents dangerous operations, protects env files, gates destructive commands. | 2026-05-22 |
| 53 | immunity-agent | 140 | 10 | Python | 6 | The security layer for AI coding agents : Skill governance, safe package recommendations, MCP/tools guardrails, secret protection, runtime policy enforcement and full audit visibility with a self-serv... | 2026-05-22 |
| 54 | LowLevelVulnerabilities | 135 | 14 | Solidity | 0 | Examples and POCs of Vulnerabilities that are unique to EVM contracts written without the guardrails of higher level languages like solidity or vyper | 2023-12-23 |
| 55 | Awesome-LLMSecOps | 133 | 37 | HTML | 0 | LLM | Security | Operations in one github repo with good links and pictures. | 2026-05-19 |
| 56 | Object-detection-in-Point-Cloud-road-boundary | 132 | 39 | C++ | 1 | Object detection in Point Cloud is popular in HD Map and sensor-based autonomous driving. There basically four types of object you can obtain in daily scenario: road surface - contains painted lane ... | 2018-05-08 |
| 57 | aws-iam-permissions-guardrails | 128 | 42 | Python | 29 | AWS IAM Permissions Guardrails https://aws-samples.github.io/aws-iam-permissions-guardrails/ | 2023-04-17 |
| 58 | novice-ChatGPT | 127 | 17 | Jupyter Notebook | 0 | ChatGPT API Usage using LangChain, LlamaIndex, Guardrails, AutoGPT and more | 2024-08-16 |
| 59 | open-bias | 124 | 4 | Python | 0 | Open Source Reliability Harness: Make your agents follow rules. One line of code to enforce, trace, and improve. | 2026-05-14 |
| 60 | foundry-citadel-platform | 123 | 35 | - | 0 | Deploy production-ready AI agents in one click! Citadel delivers unified governance, end-to-end observability & rapid development for secure, compliant AI at scale. Built on Azure best practices—turn ... | 2026-05-11 |
| 61 | gateway | 122 | 13 | Python | 0 | The Open Source Firewall for LLMs. A self-hosted gateway to secure and control AI applications with powerful guardrails. | 2025-06-25 |
| 62 | raga-llm-hub | 115 | 14 | Python | 2 | Framework for LLM evaluation, guardrails and security | 2024-09-09 |
| 63 | oh-my-githubcopilot | 112 | 8 | TypeScript | 0 | Ultimate Harness Automation for Github Copilot on VS Code. It provides 28+ specialized agents, 30+ reusable skills, hooks, guardrails, and etc. | 2026-05-20 |
| 64 | aws-control-tower-controls-terraform | 108 | 35 | HCL | 0 | This repository describes how to use AWS Control Tower controls, HashiCorp Terraform, and infrastructure as code (IaC) to implement and administer preventive, detective, and proactive security control... | 2025-04-17 |
| 65 | claude-interactive-documentation-workflow | 105 | 11 | - | 0 | I used to whiteboard, then code. Now I markdown, then code. This is how I vibe-code: I can direct, guardrail, and understand the LLM-built code, come back to it 6 months later and actually understand ... | 2026-04-21 |
| 66 | cloud-guardrails | 102 | 32 | JavaScript | 11 | Minimum guardrails for GC's cloud operationalization framework. | 2024-12-12 |
| 67 | ultraship | 102 | 13 | JavaScript | 0 | "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 testin... | 2026-05-18 |
| 68 | awesome-cloud-guardrails | 102 | 1 | JavaScript | 0 | Schema-driven awesome list of cloud security guardrails powering cloudguardrail.com/tools | 2026-05-21 |
| 69 | ClawGuard | 101 | 1 | TypeScript | 5 | The antivirus for OpenClaw — approve dangerous actions, scan skills, block secret leaks, and keep humans in control, for safety. | 2026-03-20 |
| 70 | thebrain | 100 | 11 | JavaScript | 0 | A Claude Code plugin that gives your AI persistent memory, code awareness, safety guardrails, and a behavioral system that learns how you work | 2026-04-17 |
| 71 | humanities-thesis-skill | 100 | 9 | Python | 0 | AI skill for humanities thesis writing — from topic selection to publication. 8 academic databases, 21 review rules, anti-hallucination guardrails. 人文社科论文写作 AI Skill | 2026-04-29 |
| 72 | zexus | 100 | 6 | C# | 0 | In-process Revit AI agent with dynamic C# code execution, multi-provider LLM support, and a guardrail system for safe BIM automation. | 2026-05-05 |
| 73 | shellward | 98 | 14 | TypeScript | 0 | AI Agent Security Middleware — 8-layer defense, DLP data flow, prompt injection detection, zero dependencies. SDK + MCP server for Claude Code, Cursor, LangChain, Hermes Agent & more. | 2026-05-18 |
| 74 | entrix | 97 | 10 | Python | 0 | A Harness Engineering tool for turning quality rules, architecture constraints, and validation steps into executable guardrails. | 2026-04-13 |
| 75 | rm-safely | 97 | 2 | Shell | 0 | 'rm' safely – a safety net for rm | 2026-05-12 |
| 76 | orloj | 96 | 9 | Go | 9 | An 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. | 2026-05-21 |
| 77 | ai-gateway | 93 | 15 | Go | 7 | Unified AI Gateway for 30+ LLMs (OpenAI, Anthropic, Bedrock, Azure etc) with Caching, Guardrails, A/B test & cost controls. Go-native Fastest & Scalable AI Gateway LiteLLM & Kong AI Gateway alternativ... | 2026-05-22 |
| 78 | guardrail3 | 92 | 0 | Rust | 3 | Composable code guardrails for Rust and TypeScript projects | 2026-05-20 |
| 79 | LLMSecurityGuide | 92 | 9 | - | 1 | A comprehensive reference for securing Large Language Models (LLMs). Covers OWASP GenAI Top-10 risks, prompt injection, adversarial attacks, real-world incidents, and practical defenses. Includes cata... | 2026-04-03 |
| 80 | any-guardrail | 88 | 11 | Python | 16 | Guardrails to support any-agent | 2026-05-22 |
| 81 | anti-lie | 88 | 7 | Python | 0 | Don't make LLMs honest. Make every factual claim auditable. — An LLM Claim Auditing Layer with T1-T7 truth gradients. 98.1% business effectiveness on LiarBench v0.2. | 2026-05-10 |
| 82 | openclaw-shield | 86 | 11 | TypeScript | 4 | Security plugin for OpenClaw agents - prevents secret leaks, PII exposure, and destructive command execution | 2026-05-12 |
| 83 | governor | 83 | 1 | Python | 0 | Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails. | 2026-05-19 |
| 84 | watchflow | 81 | 25 | Python | 4 | Agentic GitHub Guardrails - Replace static protection rules with context-aware enforcement. | 2026-04-16 |
| 85 | openai-guardrails-js | 80 | 14 | TypeScript | 5 | OpenAI Guardrails - TypeScript / JavaScript | 2026-03-26 |
| 86 | arthur-engine | 80 | 10 | Python | 2 | Make AI work for Everyone - Monitoring and governing for your AI/ML | 2026-05-22 |
| 87 | codexmaster | 78 | 8 | HTML | 0 | Master Codex with this Framework file system + Prompt Generator consisting of 32 markdown files that will set such strict constraints and rules for Codex that its output is nearly flawless. Files for:... | 2026-04-02 |
| 88 | PIGuard | 76 | 9 | Python | 0 | [ACL 2025] The official implementation of the paper "PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free". | 2025-12-04 |
| 89 | rag-ops | 75 | 19 | Python | 0 | This project applies the core knowledge from the LLMOps module, including the design and implementation of the API Layer, Inference Layer, Observability Layer, Cache Layer, Guardrails Layer, Routing L... | 2025-12-27 |
| 90 | valqore | 74 | 33 | Python | 0 | Safety-first guardrails for AI-driven cloud and Kubernetes operations | 2026-05-17 |
| 91 | langevals | 72 | 9 | - | 3 | LangEvals aggregates various language model evaluators into a single platform, providing a standard interface for a multitude of scores and LLM guardrails, for you to protect and benchmark your LLM mo... | 2026-02-15 |
| 92 | heinzel | 72 | 11 | Shell | 0 | A ruleset that turns AI coding assistants into disciplined Linux, FreeBSD & macOS sysadmins. Manages servers via SSH and localhost with safety guardrails, checklists, and team support. Named after the... | 2026-05-19 |
| 93 | invariant-gateway | 72 | 9 | Python | 1 | LLM proxy to observe and debug what your AI agents are doing. | 2025-11-06 |
| 94 | End-to-End-Agentic-Ai-Automation-Lab | 72 | 34 | Jupyter Notebook | 0 | This repository contains hands-on projects, code examples, and deployment workflows. Explore multi-agent systems, LangChain, LangGraph, AutoGen, CrewAI, RAG, MCP, automation with n8n, and scalable age... | 2026-05-21 |
| 95 | pfsense-mcp-server | 71 | 11 | Python | 2 | pfSense MCP Server enables security administrators to manage their pfSense firewalls using natural language through AI assistants like Claude Desktop. Simply ask "Show me blocked IPs" or "Run a PCI co... | 2026-03-27 |
| 96 | agent-os | 70 | 21 | Python | 0 | [DEPRECATED] Moved to microsoft/agent-governance-toolkit | 2026-03-03 |
| 97 | circle-guard-bench | 69 | 4 | Python | 0 | First-of-its-kind AI benchmark for evaluating the protection capabilities of large language model (LLM) guard systems (guardrails and safeguards) | 2026-03-07 |
| 98 | claude-code-guardrails | 67 | 8 | Python | 1 | Real-time guardrails for Claude Code tool calls. | 2026-02-04 |
| 99 | pydantic-ai-shields | 67 | 10 | Python | 0 | Guardrail capabilities for Pydantic AI — cost tracking, prompt injection detection, PII filtering, secret redaction, tool permissions, and async guardrails. Built on pydantic-ai's native capabilities ... | 2026-05-05 |
| 100 | hermes-agent-helm-chart | 66 | 21 | Shell | 0 | The community-driven unofficial chart packages Hermes Agent for Kubernetes with cloud-native defaults, explicit state-safety guardrails, and flexible composition points for platform teams. | 2026-04-12 |