全部项目

reflex

ursuciprian/reflex

Pre-execution risk gate for AI coding agents (Claude Code, Codex, opencode, pi, Hermes). Blocks or asks on risky shell commands, guards against prompt injection in what agents read, escalates to System 2 and a human queue. Optional TypeSafe Jev.

JavaScript
星标
4
派生
0

收录依据

结合确定性命令规则与可选 Jev 引擎、用六个类型化风险问题检查执行前操作的代理 hook。策略保留执行权,不认证安全宣传。

相关项目

  • jev-advisor-gateway

    Local gateway that routes coding-agent tool decisions through Jev and can attach a read-only advisor (GPT or Claude).

    共同主题: claude-code, codex

  • agent-fastpath

    Jev MCP server: a decision layer for coding agents, built on TypeSafe Jev (System One model). Ship gates, risk checks, file triage that keeps files out of context, and a safe headless browser, with calibrated confidence. For Claude Code, Codex, Cursor.

    共同主题: claude-code, codex

  • agent-chaperone

    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.

    共同主题: agent-security, claude-code