The tool, called lend, sits directly in front of the local SSH agent socket to evaluate signature and command requests against strict policies. When an agent needs elevated privileges, such as invoking the GitHub CLI, the command executes entirely on the user's host laptop without transferring secrets to the remote machine. Users must authenticate each specific request using biometric Touch ID checks before it is permitted to run. This proxy functions alongside herdr and Ovis, enabling multi-agent coordination and mobile approval tracking.
Key points
Running autonomous agents on disposable virtual machines limits direct exposure to sensit…: Running autonomous agents on disposable virtual machines limits direct exposure to sensitive password vaults and local keys.
Proxying commands back to the host machine avoids the security pitfalls of traditional, u…: Proxying commands back to the host machine avoids the security pitfalls of traditional, unmonitored SSH forwarding.
Integrating mobile clients like Ovis allows developers to review and approve agent reques…: Integrating mobile clients like Ovis allows developers to review and approve agent requests remotely via push notifications.
Sources checked by our analysis pipeline: 1
Table of Contents
- Background
- herdr
- Ovis
- The credential problem
- lend
- What lend doesn't protect against
- Prior art
- Trying it
I built lend to let remote agents use tools on my laptop with my approval. Here's how it fits into my workflow.
Background #
I use agents heavily these days as part of my toolchain. I usually have a few going at once: Claude Code working in one repo, Codex reviewing a branch in another, and something long-running in the background. I often have them review each other's work too. None of them run on my laptop. They run on VMs I can throw away, and my laptop keeps the stuff I care about: my SSH keys, my 1Password vault, and the gh
and cloud CLIs that are logged in as me.
This works great until an agent needs one of those things. In this post I'll go over how I run agents in parallel with herdr and Ovis, and the tool I wrote to deal with credentials, lend.
The landmark workplace safety dispute arose after electrical devices posed explosion hazards at a hazardous material facility in Victoria. Although the dismissed worker alleged the termination was unlawful retaliation for internal complaints, the federal court affirmed the employer's absolute right to strictly enforce critical industrial protocols. The legal precedent arrives amid broader nationwide scrutiny over wearable cameras in sensitive and public environments.
Corporate targets are facing a heightened risk of compromise as deceptive digital correspondence serves as the vehicle for unauthorized access. Cybersecurity specialists at the tech firm uncovered the campaign, warning that organizations are being actively sought out to infiltrate their internal environments. Vigilance regarding incoming communications remains critical to preventing potential security breaches.
Anticipation for Rockstar's upcoming launch is rippling across global infrastructure and labor markets as players prepare for day-one access. Telecommunications providers are boosting network capacity to handle massive digital downloads, while employers face tens of thousands of workplace absences tied directly to release day. Even military recruiters have leveraged the game's cultural footprint by using dedicated playing time as an incentive for service commitments.