LIVE
OpenAI Partners with Chilean Ministry to Advance Public Sector AI Ambience Healthcare Expands Clinical AI Suite for Hospital Operations AI Models Vulnerable to Manipulation in Simulated Warfare Scenarios, Research Shows AWS Highlights Enterprise Governance and AI Workspace Quick Ahead of re:Invent 2026 LoanPro Integrates Amazon Bedrock to Automate Loan Servicing Workflows Google Brings Wallet App to iOS Users Across the United States Microsoft Reveals Cause of Global Outlook Outage AWS Outlines Phased Roadmap for Responsible Agentic AI Governance Google updates Gemini settings to separate chat history from AI model training Uber Eats and Zipline launch autonomous drone food delivery in Houston OpenAI Partners with Chilean Ministry to Advance Public Sector AI Ambience Healthcare Expands Clinical AI Suite for Hospital Operations AI Models Vulnerable to Manipulation in Simulated Warfare Scenarios, Research Shows AWS Highlights Enterprise Governance and AI Workspace Quick Ahead of re:Invent 2026 LoanPro Integrates Amazon Bedrock to Automate Loan Servicing Workflows Google Brings Wallet App to iOS Users Across the United States Microsoft Reveals Cause of Global Outlook Outage AWS Outlines Phased Roadmap for Responsible Agentic AI Governance Google updates Gemini settings to separate chat history from AI model training Uber Eats and Zipline launch autonomous drone food delivery in Houston

New 'lend' Tool Secures Remote AI Coding Agents by Proxying Credentials

🌐 Work & Society 2 min read 👁 11

A developer has introduced 'lend,' a security-focused tool that allows remote AI agents to execute commands using local credentials without exposing sensitive keys or tokens.

New 'lend' Tool Secures Remote AI Coding Agents by Proxying Credentials🌐Work & Society

Photo: Hacker News Front Page

Key points

  • Lend acts as a proxy to execute commands locally, preventing the need to store sensitive credentials on remote VMs.
  • The system requires biometric approval for each command, ensuring the user maintains control over agent actions.
  • The workflow integrates with herdr and Ovis to manage multiple agents and provide mobile notifications for pending approvals.

As AI agents become more integrated into software development workflows, managing security for remote execution has become a significant challenge. Developers often rely on virtual machines (VMs) to run agents like Claude Code or Codex, but these agents frequently require access to sensitive local credentials, such as SSH keys or API tokens, to perform tasks like CI monitoring or Git operations. Traditionally, this has required either copying credentials to the VM or using SSH agent forwarding, both of which pose security risks by potentially exposing tokens or granting agents unrestricted access to keys.

To address this, a new tool called lend has been developed to act as a secure proxy. Instead of transferring credentials, lend keeps them on the user's local machine. When a remote agent needs to execute a command, it sends a request through the proxy. The local machine then prompts the user for biometric authorization via Touch ID, displaying the specific command and arguments before execution. Once approved, the command runs locally, and the output is returned to the agent, ensuring the actual credentials never leave the developer's laptop.

The developer also utilizes herdr, a terminal multiplexer designed for managing multiple AI agents, and Ovis, a mobile client that provides push notifications for approval requests. By combining these tools, users can maintain a secure development environment where agents operate on remote VMs while the underlying security tokens remain protected under strict local policy control.

Source Hacker News Front Page — blog.antonio.cx/running-agents-with-lend ↗

Contact the newsroom

Got a tip, a proposal or a partnership question? Write to us and we will reply shortly.