Best Security & Guardrails Top 20
Top 20 most popular open-source Security & Guardrails projects, ranked by GitHub Stars.
SWE-agent
19.2k StarsSWE-agent takes a GitHub issue and automatically generates fixes using your LLM of choice, also applicable to cybersecurity auditing and competitive coding. NeurIPS 2024 paper.
OpenAI Evals
18.4k StarsOpenAI's framework for evaluating LLMs and LLM systems, providing an open-source registry of benchmarks and tools for systematic model assessment.
PentAGI
16.8k StarsFully autonomous AI Agents system capable of performing complex penetration testing tasks using multi-agent architecture with support for multiple LLM providers.
PentestGPT
13.0k StarsAn automated penetration testing agentic framework powered by large language models for security testing and vulnerability discovery.
E2B
12.2k StarsE2B provides secure cloud sandboxes for AI agents, supporting code execution, file operations, and isolated compute as an execution layer for coding and automation workflows.
Portkey AI Gateway
11.7k StarsPortkey AI Gateway is a blazing fast AI gateway with integrated guardrails, routing to 200+ LLMs with 50+ AI guardrails through a single fast and friendly API.
OpenSandbox
10.6k StarsOpenSandbox is an open-source, secure, fast, and extensible sandbox runtime for AI agents, developed by Alibaba.
GhidraMCP
8.8k StarsMCP server for Ghidra reverse engineering platform, enabling AI agents to autonomously perform binary analysis and vulnerability discovery.
HexStrike AI
8.7k StarsHexStrike AI is an advanced MCP server that lets AI agents autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, and security research.
Garak
7.8k StarsNVIDIA's open-source LLM vulnerability scanner that automatically detects security issues in language models including safety vulnerabilities, hallucination tendencies, jailbreak risks, and prompt injection attacks.
Guardrails AI
6.8k StarsGuardrails AI adds programmable guardrails to large language models, ensuring reliability and safety through input/output validation, structured data extraction, and custom validators.
Superagent
6.6k StarsSuperagent protects AI applications against prompt injections, data leaks, and harmful outputs, embedding safety directly into your app.
Anthropic Cybersecurity Skills
6.2k Stars754 structured cybersecurity skills for AI agents mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND and NIST AI RMF. Works with Claude Code, Codex CLI, Cursor, Gemini CLI and 20+ platforms.
NeMo Guardrails
6.1k StarsNVIDIA NeMo Guardrails is an open-source toolkit for adding programmable guardrails to LLM-based conversational systems, supporting topic control, safety enforcement, and dialog guidance.
Microsandbox
6.0k StarsSecure, local, cross-platform and programmable sandboxes for AI agents. Provides strict resource isolation using microVM technology.
OpenShell
5.8k StarsOpenShell is the safe, private runtime for autonomous AI agents, developed by NVIDIA. Provides controlled execution environments and resource management.
Giskard
5.3k StarsAn open-source evaluation and testing library for LLM agents providing automated model scanning, bias detection, performance benchmarking, and compliance checks.
Purple Llama
4.2k StarsMeta's set of tools to assess and improve LLM security, including safety benchmarks, prompt injection detection, and output auditing to help evaluate and enhance the safety of large language models.
PyRIT
3.8k StarsThe Python Risk Identification Tool for generative AI — an open-source framework by Microsoft for proactively identifying risks in generative AI systems through red teaming and automated probing.
MCP Context Forge
3.7k StarsAn AI Gateway, registry, and proxy by IBM that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails, and management.
Related Articles
Agent Evaluation and Testing: From Vibe Checks to End-to-End Pipelines
Most teams evaluate agents by checking a few examples. Real evaluation needs layered metrics, non-rotting datasets, and judges that push back. This article provides runnable code patterns and a practical decision framework.
AI Agent Security in Practice: From Prompt Injection to Defense in Depth
A systematic walkthrough of three major attack surfaces in AI agents, with practical code examples for prompt injection defense, tool permission scoping, and output filtering.
AI Coding Agents Deep Dive: Architecture Trade-offs from CLI to IDE-Integrated
A deep architectural comparison of seven open-source coding agents across three paradigms — CLI-first, IDE-integrated, and fully autonomous — examining context management, tool access, and autonomy levels to help you pick the right tool for each development scenario.