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.
Like agent-chaperone/agent-chaperone, 0 likes 0 Bookmark agent-chaperone/agent-chaperone, 0 bookmarks 0 Your AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they execute.
Like DobermanCore/Doberman-Core, 0 likes 0 Bookmark DobermanCore/Doberman-Core, 0 bookmarks 0 Universal security guardrails and workflow policies for AI coding agents.
Like SumonMSelim/agentguard, 0 likes 0 Bookmark SumonMSelim/agentguard, 0 bookmarks 0 Hooking implementations and supporting tools for various coding agents (Claude, Cursor, Gemini, etc)
Like sondera-ai/sondera-coding-agent-hooks, 0 likes 0 Bookmark sondera-ai/sondera-coding-agent-hooks, 0 bookmarks 0 Security layer for AI coding agents. Works with Claude Code, Cursor, Windsurf, Gemini CLI, OpenCode, Pi Agent and more.
Like safedep/gryph, 0 likes 0 Bookmark safedep/gryph, 0 bookmarks 0 Policy guardrails for coding agents (Claude Code, Codex, Cursor) — every tool call is checked locally, before it runs.
Like LuD1161/agentjail, 0 likes 0 Bookmark LuD1161/agentjail, 0 bookmarks 0 sandbox, guardrails, and audit across your coding agents
Like liwala/sandshell, 0 likes 0 Bookmark liwala/sandshell, 0 bookmarks 0 Auto mode for every coding agent, built on Jev: risk-scores every tool call with session context (deny / ask / allow), flags prompt injection in results, checks skills and plugins. Claude Code, Codex, Copilot, Gemini, Cursor, pi, OpenCode, ACP.
Like leepokai/jev-guard, 0 likes 0 Bookmark leepokai/jev-guard, 0 bookmarks 0 Lightweight Agent Detection & Response (ADR) layer for AI agents — guards commands, files, and web requests. Part of Gen Agent Trust Hub.
Like gendigitalinc/sage, 0 likes 0 Bookmark gendigitalinc/sage, 0 bookmarks 0 
