SafeAgents: an open-source proxy that checks every tool call your coding agent makes before it runs
英文标题:SafeAgents: an open-source proxy that checks every tool call your coding agent makes before it runs
SafeAgents is a small local proxy that sits between a coding agent and its model server. It checks each tool call in the model's response before the harness receives it. A call it flags is replaced with a short text notice, so the harness gets a plain text reply and runs nothing. You point the
打开原文相关 8 · 机会 4
中文
SafeAgents is a small local proxy that sits between a coding agent and its model server. It checks each tool call in the model's response before the harness receives it. A call it flags is replaced with a short text notice, so the harness gets a plain text reply and runs nothing. You point the
中文全文翻译正在补齐,可先查看下方英文原文。
English / 原文
SafeAgents is a small local proxy that sits between a coding agent and its model server. It checks each tool call in the model's response before the harness receives it. A call it flags is replaced with a short text notice, so the harness gets a plain text reply and runs nothing. You point the