Free AI agent security tools (2026)
AI agent security tools that you can use without paying: open-source projects plus tools with a free plan. Here are the top 25 of 28 from the AgentScout directory.
How we picked and ranked: tools are matched by category, the pricing each maker states and what each tool says it does. They are ranked by GitHub stars as recorded on each listing (link checks 2026-10-18); tools without a tracked repo follow, by listing maturity. No paid placements.
1. Strix
Open-source AI agents that run penetration tests on your app to find and help fix security vulnerabilities.
Pricing (as stated): Open source + cloud · Mature
2. 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.
Pricing (as stated): Open source + cloud · Mature
3. Kong Gateway
Cloud-native API, LLM and MCP gateway that adds routing, auth, multi-LLM support, semantic security and MCP traffic analytics through plugins.
Pricing (as stated): Open source + cloud · Mature
4. OpenSandbox
Secure, fast sandbox runtime for AI agents to run code.
Pricing (as stated): Open source · Mature
5. Instructor
Library for getting validated structured outputs from any LLM, built on Pydantic with retries and type safety.
Pricing (as stated): Open source · Mature
6. 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.
Pricing (as stated): Open source + cloud · Mature
7. CubeSandbox
Lightweight, concurrent sandbox for running AI agent code securely.
Pricing (as stated): Open source · Mature
8. Guardrails AI
Open-source framework for validating LLM inputs and outputs with configurable guardrails.
Pricing (as stated): Open source + cloud · Mature
9. Superagent
SDK for AI agent safety that blocks prompt injections and unsafe tool calls, redacts PII and secrets, and runs red-team scenarios.
Pricing (as stated): Open source · Mature
10. Agent Governance Toolkit
Microsoft toolkit for policy enforcement, identity and sandboxing for AI agents.
Pricing (as stated): Open source · Mature
11. Fragments
E2B's open-source Next.js template for AI-generated apps, like Claude Artifacts or v0, with generated code run in secure E2B sandboxes.
Pricing (as stated): Open source · Mature
12. Failproof AI
Observability and policy enforcement for AI agent harnesses.
Pricing (as stated): Open source · Mature
13. 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.
Pricing (as stated): Open source · Mature
14. agentgateway
Proxy for AI agents and MCP servers with security and observability.
Pricing (as stated): Open source · Mature
15. Archestra
Enterprise AI platform with guardrails, an MCP registry, gateway and orchestrator.
Pricing (as stated): Open source + cloud · Active
16. Tracecat
Open-source security automation platform for teams and AI agents.
Pricing (as stated): Open source + cloud · Active
17. OneCLI
Sandboxed agent harness for teams with secure credential handling.
Pricing (as stated): Open source · Active
18. Mercury Agent
Self-hosted personal AI agent with a written personality, local memory, permission-gated tools and token budgets, reachable via CLI or Telegram.
Pricing (as stated): Open source · Active
19. PentestAgent
Agent framework for black-box security testing and bug bounty work.
Pricing (as stated): Open source · Active
20. Snyk Agent Scan
Snyk's scanner for security risks in MCP servers and agent skills.
Pricing (as stated): Open source · Active
21. Moltis
Secure personal agent server in Rust with sandboxed execution.
Pricing (as stated): Open source · Active
22. ToolHive
Stacklok platform that runs MCP servers in isolated containers with per-request identity, access policy and observability.
Pricing (as stated): Open source · Active
23. Agent Safehouse
macOS sandbox for local coding agents that limits file and integration access with deny-first policy profiles.
Pricing (as stated): Open source · Active
24. ADR
Uber's Agentic AI Detection and Response system that secures employee and customer-facing AI agents with observability and threat detection.
Pricing (as stated): Open source · Active
25. Lyzr
Enterprise agent studio and framework for building secure AI agents.
Pricing (as stated): Freemium · Active
FAQ
What are the best free AI agent security tools?
Ranked by tracked GitHub stars, the top free AI agent security tools in our directory are Strix, LiteLLM, Kong Gateway, OpenSandbox, Instructor. Stars measure popularity, not fit, so compare a few against your own task.
How many free AI agent security tools does AgentScout list?
28 tools match. This page shows the top 25. Pricing mix on this page: Open source (17), Open source + cloud (7), Freemium (1).
Are these tools really free?
Pricing is what each maker states on their site. Open-source tools are free to self-host but may need a paid model API key or offer paid cloud plans; freemium tools have a free plan with limits. Check each official site.
Where can I see every tool for agent security and safety?
Our task page lists all 53 tools we match to agent security and safety.
Related: All tools for agent security and safety · MCP & infra (12) · evals & observability (6) · coding (3) · frameworks (2)
By role: For DevOps and SRE engineers · For security engineers
All popular searches · AI agents by role · Free tools
Best-of lists: Best MCP servers for Cursor · All best lists
Facts come from our directory listings; pricing is as each maker states it and can change. Check official sites before you choose.