BLA
BLA (Blind LLM Agents) is the open-source Blue Defense MCP and CLI built to protect software artifacts against automated AI reverse-engineering workflows.
翻译准备中
个人 GitHub 账号下公开仓库的所有者可以登录并验证所有权,自行管理介绍,无需管理员批准。
登录并生成验证文件,在 30 分钟内将其提交到此仓库的默认分支。其他分支或分叉仓库中的文件无效。然后在下方检查文件,即可无需管理员批准直接管理项目。请保留文件以维持管理权限。
如需登录,将前往登录页面。登录后请回到此处,再次点击所选的验证按钮。
在项目文件夹中运行 /nomorevibe verify,即可验证所有权并自行管理介绍。
一分钟完成验证Give your AI agents a valet key, not your master key. Local credential broker for AI agents (MCP) on macOS: Touch ID per credential, proxy calls, audit log.
翻译准备中
取自仓库 README
正在加载完整 README。 以下为已保存的摘录。
Give your AI agents a valet key, not your master key.
KeyValet lets Claude Code, Cursor and other AI agents use your API keys and OAuth accounts — without ever seeing them. You approve each credential with Touch ID, KeyValet makes the call, and every use is logged.
macOS, Node.js 20+ (nodejs.org or nvm) and Xcode Command Line Tools. You'll be asked for your password once. Claude Code is configured automatically; for other MCP clients see the guide.查看完整 README ↗Keys in the chip. Approval in your hand.
Let AI agents use any API, on any machine, without ever holding a secret. KeyValet keeps your API keys and OAuth accounts in a hardware-protected vault that only a system service can read — not the agent — and makes each call for the agent after you say yes.
Install · Website · Guide · Security · 简体中文
Works with Claude Code, Codex, Cursor, Gemini CLI, Grok, Devin — any MCP client or HTTP SDK — on macOS, Linux and Windows 11.
Most "the agent never sees the key" tools run the broker as the agent's own user, with the master key in a file or an environment variable. A prompt-injected agent can read both. KeyValet is built so it can't:
What it doesn't do: protect you from a compromised root/SYSTEM on the same machine, or verify what an agent says it's doing. The complete list is in SECURITY.md.
curl -fsSL https://keyvalet.dev/install.sh | sh
Then just talk to your agent:
/keyvalet:add openai— a native dialog asks you for the key; it never passes through the chat."Use KeyValet to list my OpenAI models." — one Touch ID, and the agent gets the response, not the key.
"Connect my GitHub account through KeyValet and create a repo called demo." — OAuth, refresh tokens and private keys stay in the vault; the agent only ever holds a short-lived token.
Pasted a key into the chat anyway? The hooks catch it and store it in KeyValet instead of a .env file.
Under the hood: ~50 service templates, OAuth 2.0 with automatic refresh, Google service accounts, GitHub Apps, JWT, TOTP, AWS STS, a streaming gateway for SDKs (OPENAI_BASE_URL=…), keyvalet scan to pull existing secrets out of .env files, and approval modes from per-call to "remember for 8 hours".
| Requirements | Details | |
|---|---|---|
| macOS | Apple Silicon, macOS 14+. Signed and notarized. | Guide |
| Linux | systemd, polkit, sudo; tpm2-tools for TPM 2.0, or explicit --software without a TPM. x64 and ARM64. | Linux |
| Windows 11 | 24H2+, Windows Hello. Unsigned x64/ARM64 release packages; signing is optional for local and remote features. | Windows · WSL |
The one-line installer above picks the right package, asks for your password once, and configures the agents it finds (Claude Code, Codex, Cursor, Grok, Devin CLI). Uninstall: curl -fsSL https://keyvalet.dev/install.sh | sh -s -- --uninstall. Key protection, recovery and platform limits: protection matrix.
Today you approve on the machine the agent runs on. Next, agents run on machines nobody is sitting at — a Linux server, a headless Mac mini, an overnight job — and the approval comes to whatever is in your hand: a phone app (iOS + Android), or the laptop you're already using.
Status: in development. The protocol, relay and helper checks are on main with software tests; the end-to-end pair → phone approval path and the phone app distribution are not finished. Design: architecture · product · open items.
Guide · Security model · Contributing · Code of Conduct · Governance · Trademark
Apache-2.0 · by Simvito Limited