AI tools for evaluating agents: guardrails and policies
Guardrails, policy engines and permission layers that limit what agents are allowed to do. Of the 110 tools on our evaluating agents page, 10 fit this narrower job. By pricing: 7 open source, 1 source-available, 1 paid, usage-based or enterprise, 1 pricing on the maker's site. The most-starred open repos here are Guardrails AI (7,529 stars), Superagent (6,766 stars), Agent Governance Toolkit (6,435 stars). Most come from the evals & observability (5), MCP & infra (4), coding (1) categories.
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
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
Altmetric MCP
Altmetric's MCP server for tracking research attention across news, policy documents and social media.
Added
NVIDIA Open Agent Safety Platform
Reference stack pairing OpenShell with NVIDIA Sentry on BlueField-4 DPUs for hardware-level agent monitoring.
Added
Zenity
Security and governance for AI agents across enterprise platforms.
Added
GitHub repos (7)
| Repo | GitHub stars | Licence | Last push |
|---|---|---|---|
| Guardrails AI ↗ | 7,529 | Apache License 2.0 | 2026-08-26 |
| Superagent ↗ | 6,766 | — | — |
| Agent Governance Toolkit ↗ | 6,435 | MIT | 2026-10-18 |
| Failproof AI ↗ | 5,560 | MIT | 2026-10-16 |
| coucou ↗ | 5,468 | — | — |
| Metorial ↗ | 3,367 | — | — |
| ToolHive ↗ | 2,293 | — | — |
7 repos. Stars and licence come from each repo, checked when the listing was last verified.
FAQ
What are the best AI tools for evaluating agents focused on guardrails and policies?
We list 10. The first three by GitHub stars and featured status are Guardrails AI: Open-source framework for validating LLM inputs and outputs with configurable guardrails.; Superagent: SDK for AI agent safety that blocks prompt injections and unsafe tool calls, redacts PII and secrets, and runs red-team scenarios.; Agent Governance Toolkit: Microsoft toolkit for policy enforcement, identity and sandboxing for AI agents.
Are there free or open-source options?
Yes: 7 open source, 1 source-available, 1 paid, usage-based or enterprise, 1 pricing on the maker's site. Pricing is as each maker states it.
More from evaluating agents
Tools are grouped by what each says it does. Missing one? Submit it free.