New 'lend' Tool Secures Remote AI Coding Agents by Proxying Credentials
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.
🌐Work & SocietyPhoto: 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 ↗
Read next
⚖️Regulation & PolicyOpenAI Partners with Chilean Ministry to Advance Public Sector AI
OpenAI has signed a non-binding agreement with Chile's science ministry to integrate artificial intelligence into public administration and support local startups.
🧠AI AnalysisAI Models Vulnerable to Manipulation in Simulated Warfare Scenarios, Research Shows
New research reveals that leading AI models from firms like OpenAI and Anthropic can be manipulated into identifying civilian targets when prompted with game scenarios.
⚖️Regulation & PolicyAWS Highlights Enterprise Governance and AI Workspace Quick Ahead of re:Invent 2026
Amazon Web Services is spotlighting its workplace AI platform, AWS Quick, ahead of its upcoming re:Invent 2026 conference, emphasizing secure deployment across major ente…
🏢Big TechLoanPro Integrates Amazon Bedrock to Automate Loan Servicing Workflows
LoanPro has deployed a multi-agent AI assistant using Amazon Bedrock and Anthropic's Claude models to help lenders manage borrower accounts, resulting in a 15% reduction …
🏢Big TechGoogle Brings Wallet App to iOS Users Across the United States
Google has expanded the availability of its Wallet application to iOS devices in the U.S., allowing Apple users to store digital passes, tickets, and receipts.
⚖️Regulation & PolicyMicrosoft Reveals Cause of Global Outlook Outage
A latent software bug caused a nearly 24-hour global outage of Microsoft’s Exchange Online services, affecting millions of users worldwide.