neuron-explorer
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
翻译准备中
在代理操作执行前阻止风险行为,并可在手机上批准。兼容 OpenClaw、Hermes、Claude Code、Codex 和 MCP。每项决策均记录在签名账本中。
AI 翻译
Stop risky agent actions before they run and approve them from your phone. Works with OpenClaw, Hermes, Claude Code, Codex and MCP. Every decision lands in a signed ledger.
开发工具TypeScript · JavaScriptGitHub @ucsandman在线运营者未确认
试用过了吗? 点一下就好,无需登录。
远程批准、策略检查和执行证据,适用于无人值守的 AI 代理。
AI 翻译
Remote approvals, policy checks, and execution evidence for unattended AI agents.
取自仓库 README
正在加载完整 README。 以下为已保存的摘录。
With a supported enforcement integration, when your AI agent (OpenClaw, Hermes, Claude Code, Codex) tries something destructive or expensive, DashClaw catches it before it runs and asks you first, even when you are not at the keyboard. Every decision lands in a signed ledger.
Run agents unattended without giving them unconditional authority.查看完整 README ↗目前无法加载完整 README。请通过原文链接阅读。 以下为已保存的摘录。
With a supported enforcement integration, when your AI agent (OpenClaw, Hermes, Claude Code, Codex) tries something destructive or expensive, DashClaw catches it before it runs and asks you first, even when you are not at the keyboard. Every decision lands in a signed ledger.
Run agents unattended without giving them unconditional authority.查看完整 README ↗