Best tools for agent security and safety (2026)
Guardrails, policies and monitoring that keep agents from doing what they shouldn't. We list 53 tools for agent security and safety below, each with a link-checked page, pricing as the maker states it and alternatives.
Updated
53 tools: 32 open source, 3 source-available, 7 free or freemium, 7 paid, usage-based or enterprise, 4 pricing on the maker's site.
Guardrails and policies (16) See the full list →
OpenAPPA
OpenAPPA is a deterministic guardrail that sits between an AI agent and its tools and tracks how data flows across tool calls, instead of asking a second model to judge each call. Policies decide whether untrusted or sensitive data may reach a given action, which blocks data exfiltration caused by prompt injection or hallucination while letting agents finish their tasks. It plugs into Claude Code, Pi, OpenCode, kAgent and Archestra, comes with reusable policy "batteries", validation, observability and reporting, and is backed by a NeurIPS workshop paper with published benchmarks. It is in preview as an open RFC.
Added
HOL Guard
HOL Guard is a free, open-source (Apache-2.0), local-first security layer for AI coding agents such as Claude Code, Codex, Cursor and GitHub Copilot CLI. On supported integrations it checks risky shell commands, reads of secret-bearing files, package installs and new or changed MCP tools before they run, lets you allow, ask or block each action, and keeps a local record for review. It installs with pipx (hol-guard) and works offline; optional Guard Cloud adds synced approvals, team policy and dashboards.
Added
Halofy
Halofy is an access and governance layer for a team's AI agents, giving every agent organizational context through one identity and policy model with provenance and audit, alongside a desktop AI workstation that turns power users' agent practices into shared policies.
Added
LiteLLM
Open-source AI gateway and Python SDK that calls 100+ LLM providers in the OpenAI format, with cost tracking, guardrails, load balancing and logging.
Added
Portkey AI Gateway
Fast open-source AI gateway that routes requests to hundreds of LLMs through one API with fallbacks, load balancing and built-in guardrails.
Added
coucou
Mac notch and phone companion that monitors your Claude Code, Codex, Cursor and Gemini CLI sessions and lets you approve permissions on the go.
Added
Mercury Agent
Self-hosted personal AI agent with a written personality, local memory, permission-gated tools and token budgets, reachable via CLI or Telegram.
Added
Metorial
Open-source identity and access layer that connects AI agents to 1,200+ integrations via MCP, CLI or API with auth, permissions and observability.
Added
Credal
Spins up governed MCP servers from your company systems so Claude, ChatGPT, Cursor or your apps can query them with permissions.
Added
Guardrails AI
Open-source framework for validating LLM inputs and outputs with configurable guardrails.
Added
Failproof AI
Observability and policy enforcement for AI agent harnesses.
Added
Archestra
Enterprise AI platform with guardrails, an MCP registry, gateway and orchestrator.
Added
NVIDIA Open Agent Safety Platform
Reference stack pairing OpenShell with NVIDIA Sentry on BlueField-4 DPUs for hardware-level agent monitoring.
Added
Openfort
Open-source stablecoin wallet infrastructure with policy-gated agent wallets, gas sponsorship and x402 support.
Added
Privy
Embedded and server wallets developers can hand to agents with policy controls.
Added
Zenity
Security and governance for AI agents across enterprise platforms.
Added
Penetration and security testing (13)
open-kritt
A self-hosted AI security research tool that orchestrates agents to hunt for vulnerabilities in a codebase and then validate and rank what they find; managed scans are also offered.
Added
AI Beat
An open-source AI red-teaming suite: PromptBeat attacks models and prompts, and AgentBeat runs black-box security evaluations against HTTP-exposed agents.
Added
CyberStrike
Terminal agent for authorized penetration testing that runs recon, vulnerability discovery and reporting with specialized security agents on your own LLM.
Added
Rogue
Agent evaluator and red-team tool that probes your agent with test conversations and attacks and reports pass or fail against your policies.
Added
Superagent
SDK for AI agent safety that blocks prompt injections and unsafe tool calls, redacts PII and secrets, and runs red-team scenarios.
Added
Mantis
Google's toolkit for AI coding agents to autonomously find, reproduce and patch software vulnerabilities in isolated environments.
Added
Strix
Open-source AI agents that run penetration tests on your app to find and help fix security vulnerabilities.
Added
PentAGI
Autonomous multi-agent system for running penetration testing tasks.
Added
AI-Infra-Guard
Tencent's AI red-teaming platform that scans agents, skills and MCP servers for risks.
Added
PentestAgent
Agent framework for black-box security testing and bug bounty work.
Added
Almanax
AI security engineer that finds vulnerabilities in applications and smart contracts and reviews pull requests; acquired by depthfirst (June 2026).
Added
Octane
Agentic security analysis that finds exploitable vulnerabilities in mission-critical code, including DeFi smart contracts.
Added
Sherlock AI
Sherlock's AI auditor for smart-contract vulnerabilities.
Added
Sandboxes and secure execution (4)
ToolHive
Stacklok platform that runs MCP servers in isolated containers with per-request identity, access policy and observability.
Added
Agent Safehouse
macOS sandbox for local coding agents that limits file and integration access with deny-first policy profiles.
Added
Perplexity SPACE
Perplexity's open-source sandbox platform that runs each agent task in its own Firecracker microVM, with credentials and network access controlled from outside.
Added
Agent Governance Toolkit
Microsoft toolkit for policy enforcement, identity and sandboxing for AI agents.
Added
More tools (20)
Handsy
Lets an AI model use a real iPhone through a $7 ESP32 board that acts as a Bluetooth keyboard and mouse, tapping and typing through apps with no jailbreak and no computer attached.
Added
Phase
An open-source secrets manager that syncs API keys and environment variables to apps, CI and agents with end-to-end encryption and access control. Free tier, Pro from $10 per user a month, or self-host.
Added
Kong Gateway
Cloud-native API, LLM and MCP gateway that adds routing, auth, multi-LLM support, semantic security and MCP traffic analytics through plugins.
Added
GoClaw
OpenClaw rebuilt in Go as a multi-tenant agent gateway with 20+ LLM providers, multiple chat channels and layered security.
Added
Jarvis Registry
Open-source MCP and A2A agent gateway that connects copilots and agents to enterprise tools with identity, access control and observability.
Added
ADR
Uber's Agentic AI Detection and Response system that secures employee and customer-facing AI agents with observability and threat detection.
Added
CodeRabbit
AI code review for pull requests, with PR triage, change explanations and continuous security monitoring.
Added
Delve
Compliance automation that uses AI agents to handle SOC 2, HIPAA and GDPR busywork.
Added
Sonatype MCP
Sonatype's dependency-management MCP server that gives coding agents component versions, security analysis and Trust Score recommendations.
Added
UiPath
Enterprise automation platform that orchestrates AI agents, software robots and people across business processes with security and compliance controls.
Added
Casdoor
Agent-first identity and access management with an MCP and agent gateway.
Added
agentgateway
Proxy for AI agents and MCP servers with security and observability.
Added
Tracecat
Open-source security automation platform for teams and AI agents.
Added
Snyk Agent Scan
Snyk's scanner for security risks in MCP servers and agent skills.
Added
SonarQube MCP Server
SonarQube MCP server for code quality and security analysis from agents.
Added
Dropzone AI
AI SOC analyst agents that investigate security alerts autonomously.
Added
Mindflow
No-code automation and AI agents for security and IT operations.
Added
Prophet Security
Agentic AI SOC analyst that triages and investigates alerts.
Added
Simbian
AI agents for security operations, threat hunting and response.
Added
Token Security
Security for non-human and AI agent identities.
Added
GitHub repos (36)
| Repo | GitHub stars | Licence | Last push |
|---|---|---|---|
| Strix ↗ | 69,022 | Apache License 2.0 | 2026-10-21 |
| LiteLLM ↗ | 61,465 | MIT | 2026-10-21 |
| Kong Gateway ↗ | 44,278 | Apache License 2.0 | 2026-10-19 |
| PentAGI ↗ | 30,728 | MIT | 2026-10-09 |
| Casdoor ↗ | 14,592 | Apache License 2.0 | 2026-10-21 |
| Portkey AI Gateway ↗ | 13,214 | MIT | 2026-05-25 |
| Guardrails AI ↗ | 7,529 | Apache License 2.0 | 2026-08-26 |
| AI-Infra-Guard ↗ | 6,887 | Apache License 2.0 | 2026-10-21 |
| Superagent ↗ | 6,770 | MIT | 2026-08-25 |
| Agent Governance Toolkit ↗ | 6,435 | MIT | 2026-10-21 |
| Failproof AI ↗ | 5,560 | MIT | 2026-10-20 |
| coucou ↗ | 5,468 | — | 2026-10-20 |
| agentgateway ↗ | 5,373 | Apache License 2.0 | 2026-10-20 |
| Archestra ↗ | 4,373 | AGPL-3.0 by default, with enterprise-licensed files | 2026-10-21 |
| Tracecat ↗ | 3,835 | GNU AGPL v3.0 | 2026-10-21 |
Top 15 of 36 by stars. Stars and licence come from each repo, checked when the listing was last verified.
Related tasks
Popular with: DevOps and SRE engineers · Security engineers · Startup CTOs · Related searches: Free AI agent security tools
Tools are matched to tasks by category, use cases and what each tool says it does. Missing one? Submit it free.