nowfound

AI · March 31, 2026

Greywall

Local agent sandbox with real-time network control dashboard

What it does

AI agents run on your machine, with your credentials, making network requests you never see. Greywall puts a deny-by-default layer in front of any CLI agent. Run greywall -- claude and it restricts file access, blocks outbound connections, and shows you a live dashboard of what the agent is trying to reach. You decide what to allow. Nothing is containerized. Your workflow stays the same but safer. It runs on Linux and macOS and costs nothing.

Does the same job

all alternatives →
  • ST
    Skill that lets Claude Code/Codex spin up VMs and GPUsFeb 2026 · cloudrouter.dev · ▲138

    I've been working on CloudRouter, a skill + CLI that gives coding agents like Claude Code and Codex the ability to start cloud VMs and GPUs. When an agent writes code, it usually needs to start a dev server, run tests, open a browser to verify its work. Today that all happens on your local machine. This works fine for a single task, but the agent is sharing your computer: your ports, RAM, screen. If you run multiple agents in parallel, it gets a bit chaotic. Docker helps with isolation, but it still uses your machine's resources, and doesn't give the agent a browser, a desktop, or a GPU to…

  • CoastyFeb 2026 · ▲96

    Computer Using Agents on Secure Cloud VMs That Run Forever

  • FS
    Fence – Sandbox CLI commands with network/filesystem restrictionsJan 2026 · github.com · ▲78

    Hi HN! Fence wraps any command in a sandbox that blocks network by default and restricts filesystem writes. Useful for running semi-trusted code (package installs, build scripts, unfamiliar repos) with controlled side effects, or even just blocking tools that phone home. > fence curl https://example.com # -> blocked > fence -t code -- npm install # -> template with registries allowed > fence -m -- npm install # -> monitor mode: see what gets blocked One use-case is to use it with AI coding agents to reduce the risk of running agents with fewer interactive permission prompts: >…

  • RunwallJul 2026 · runwall.vercel.app · ▲9

    A Runtime security layer that lets AI agents execute safely

  • CE
    CargoWall – eBPF Firewall for GitHub ActionsMar 2026 · github.com · ▲14

    We just open-sourced CargoWall - a lightweight eBPF firewall for GitHub Actions. We originally built it to stop LLM agents from connecting to untrusted domains. After recent GitHub Actions supply chain compromises like the Trivy attack, we realized it'd work well for blocking untrusted connections from CI runners too. It uses iptables DNAT to redirect all outbound port 53 traffic to a local DNS proxy, which checks each query against a hostname allowlist before forwarding. Resolved IPs from allowed responses are inserted into eBPF LPM trie maps, and a TC egress classifier attached to the…

  • Agent WallFeb 2026 · ▲3

    Security firewall for AI agents. Cloudflare for MCP.

More ai this month

the category →
  • I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.

    AI · 17d ago · simedw.com

  • Astute585

    Automate your B2B brand going viral, with new media creators

    AI · 18d ago · company-app.joinastute.com

  • Grok Bot547

    AI teammates that you can give real work to

    AI · 25d ago · x.ai

  • Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…

    AI · 27d ago · cactuscompute.com

  • Monid474

    OpenRouter for agent tools

    AI · 6d ago · monid.ai

  • Turn website visitors into qualified pipeline

    AI · 19d ago · clarasdr.ai

Launched alongside, March 2026

the whole month →
  • AI-native CRM that builds itself and does work for you

    AI · Mar 2026 · lightfield.app

  • Tobira.ai730

    A network where AI agents find deals for their humans

    AI · Mar 2026 · tobira.ai

  • Switch from ChatGPT to Claude with import memory feature

    AI · Mar 2026 · claude.com

  • The AI assistant that already knows your work

    AI · Mar 2026 · littlebird.ai

  • Your AI Coworker that proactively executes tasks

    AI · Mar 2026 · viktor.com

  • Jupid664

    File your taxes with Claude Code

    Commerce · Mar 2026 · jupid.com