Submit a project
agent-chaperone
By agent-chaperone
Source description: Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.
Repository description
The repository describes its purpose as: Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.
Source evidence
The daily check found an explicit Jev / TypeSafe AI connection in the original README and implementation files at the same commit.
Each screen combines deterministic rules in code with a small battery of typed, calibrated judgments from [Jev](https://docs.typesafe.ai), TypeSafe's System One model.
Automatically source-checked: public repository, pinned README, and implementation files. Not run, benchmarked or security-audited.
