Tag
Sente Labs open-sourced extensible-mcp, an MCP proxy that dynamically loads MCP servers without polluting the LLM context while enforcing zero-trust policy controls (Rego, CEL, and now Cedar) over tool calls. Tool definitions live in a queryable vector store, and policies and credentials are kept outside the LLM's reach, distinguishing user intent from granted rights.
Sapien is a stateful policy engine that enforces contextual security policies on autonomous AI agents by specifying permitted tool-call sequences with stateful predicates. It maintains near-unconstrained agent utility while blocking 93-95% of attacks on AgentDojo and 62-85% on Toolathlon, outperforming static tool allowlists on long-horizon tasks.
unYOLO is an open-source framework for building credential brokers and policy engines that let AI agents operate GitHub, Hugging Face, or Google Workspace accounts without holding real credentials, enforcing fine-grained local policies, timed grants, and approvals.
The author open-sourced the risk/authorization layer from their live trading system as a standalone fail-closed policy engine that evaluates agent actions before execution, and is seeking agent builders to pilot it.
Microsoft open-sourced the Agent Governance Toolkit, a governance layer for AI agents that enforces policies, identity, sandboxing, and audit logs to ensure safe and compliant autonomous agent operations.
The author argues that current AI agent safety measures like guardrails and monitoring are insufficient, proposing 'external admission' as a stricter pattern where execution authority is withheld until an external authority explicitly allows high-impact actions.