Overview
[Product intro] OneCLI is an open-source security layer for AI agents. Transparent proxying stops Agents from touching raw API keys by inserting an encrypted credential-injection layer between the agent and target services. The idea: grant Agents access without exposing private keys. Local encrypted storage gives AI workflows an auditable, controlled trust base so individuals and enterprises can prevent mis-ops and secret leaks during autonomous runs. [Features] Zero-code integration: set proxy env vars for automatic credential injection—no code changes or heavy SDKs. Encrypted credential isolation: AES-256-GCM storage so Agents can call APIs but never read raw keys. Fine-grained access control: block specific endpoints and set per-Agent rate limits. Full audit: log every API call—which Agent, when, which service. Broad ecosystem: native fit for OpenClaw, NanoClaw, n8n, and Dify.
Connected profiles
Sources · 0Sources & provenance
English text is maintained separately from the original record. Consult the original source before citing a fact.
No source links are available for this profile.
Original source text
Names may use phonetic renderings when no English name is supplied. The original wording is retained below.
【产品介绍】OneCLI 是一款专为 AI 智能体设计的开源安全层工具它通过透明代理技术解决了 Agent 直接接触原始 API 密钥带来的安全风险该工具在智能体与目标服务之间建立了一个加密的凭据注入层其核心理念在于“赋予 Agent 访问权限而非暴露私钥”项目支持本地加密存储，旨在为 AI 工作流提供可审计且受控的信任底座无论是个人开发者还是企业，都能通过其有效防止 Agent 在自主运行中出现误操作或敏感信息泄露【产品功能】零代码侵入集成：通过设置代理环境变量即可实现凭据自动注入，无需修改现有代码或引入复杂 SDK加密凭据隔离：采用 AES-256-GCM 高强度加密存储，确保 Agent 仅能发起调用而无法获取原始密钥内容精细化访问控制：支持配置规则拦截特定 API 端点，并能针对不同 Agent 设置请求速率限制以保障安全全量操作审计：实时记录所有 API 调用日志，清晰展示每个 Agent 在何时调用了何种服务，方便回溯与管理广泛的生态兼容：原生适配 OpenClaw、NanoClaw、n8n 及 Dify 等主流 Agent 框架