AI tools for agent security and safety: guardrails and policies
Guardrails, policy engines and permission layers that limit what agents are allowed to do. Of the 55 tools on our agent security and safety page, 20 fit this narrower job. By pricing: 13 open source, 1 source-available, 1 paid, usage-based or enterprise, 5 pricing on the maker's site. The most-starred open repos here are LiteLLM (61,465 stars), Instructor (14,029 stars), Portkey AI Gateway (13,214 stars). Most come from the MCP & infra (8), security & governance (6), crypto (3) categories.
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
Instructor
Library for getting validated structured outputs from any LLM, built on Pydantic with retries and type safety.
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
Guardrails AI
Open-source framework for validating LLM inputs and outputs with configurable guardrails.
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
Agent Governance Toolkit
Microsoft toolkit for policy enforcement, identity and sandboxing for AI agents.
Added
Failproof AI
Observability and policy enforcement for AI agent harnesses.
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
Archestra
Enterprise AI platform with guardrails, an MCP registry, gateway and orchestrator.
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
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
Aave MCP
Official Aave MCP server for V3 and V4 markets, positions, governance and transaction preparation by AI agents.
Added
Altmetric MCP
Altmetric's MCP server for tracking research attention across news, policy documents and social media.
Added
Credal
Spins up governed MCP servers from your company systems so Claude, ChatGPT, Cursor or your apps can query them with permissions.
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
GitHub repos (13)
| Repo | GitHub stars | Licence | Last push |
|---|---|---|---|
| LiteLLM ↗ | 61,465 | MIT | 2026-10-18 |
| Instructor ↗ | 14,029 | — | 2026-10-10 |
| Portkey AI Gateway ↗ | 13,214 | — | 2026-05-25 |
| Guardrails AI ↗ | 7,529 | Apache License 2.0 | 2026-08-26 |
| Superagent ↗ | 6,766 | — | 2026-08-25 |
| Agent Governance Toolkit ↗ | 6,435 | MIT | 2026-10-18 |
| Failproof AI ↗ | 5,560 | MIT | 2026-10-16 |
| coucou ↗ | 5,468 | — | 2026-10-16 |
| Archestra ↗ | 4,373 | AGPL-3.0 by default, with enterprise-licensed files | 2026-10-18 |
| Mercury Agent ↗ | 3,433 | — | 2026-10-18 |
| Metorial ↗ | 3,367 | — | 2026-10-16 |
| ToolHive ↗ | 2,293 | — | 2026-10-16 |
| Agent Safehouse ↗ | 2,110 | — | 2026-10-17 |
13 repos. Stars and licence come from each repo, checked when the listing was last verified.
FAQ
What are the best AI tools for agent security and safety focused on guardrails and policies?
We list 20. The first three by GitHub stars and featured status are 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.; Instructor: Library for getting validated structured outputs from any LLM, built on Pydantic with retries and type safety.; 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.
Are there free or open-source options?
Yes: 13 open source, 1 source-available, 1 paid, usage-based or enterprise, 5 pricing on the maker's site. Pricing is as each maker states it.
More from agent security and safety
Tools are grouped by what each says it does. Missing one? Submit it free.