Agent governance and mandates

Python framework that runs input and output guards to detect and mitigate specific risks, and can also extract structured data from model output.

guardrails, validation, policy

Contextual security layer that checks an agent trace against declarative rules for tool calls, data flow, secrets, and looping.

guardrails, policy, traces

Guard API that screens an agent conversation in one call, including tool definitions, tool calls, and tool results, against a project policy.

guardrails, tool-calls, policy

Open source proxy that enforces personal, team, and agent spend budgets on model calls when a database is connected, and can attach guardrails.

budgets, spend-limits, guardrails

Open source toolkit for programmable rails that block, alter, or validate user inputs, model responses, and tool calls.

guardrails, policy, tool-calls

Open source policy engine. An application sends structured input and OPA returns a decision from Rego policy, separate from the code that enforces it.

policy, mandates, rego