RepoAlerts
SponsorGet alerts

Cygnux-Labs/Tracekit-box

Get alerts like thisView on GitHubShare on X

Can I trust it?

Worth a closer look before you use it.

  • Warnings Check

    Very new: it was created 5 days ago. Wait a little before installing it.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change 2 days ago.

  • Licence OK

    MIT: you can use it for free, also in a commercial product. Keep the licence notice.

Quick checks from public data. They help, but they are no guarantee.

What it is

Runs AI agent jobs in isolated Firecracker micro-VMs with no network card. Network access, secrets, commands and code changes pass through host-side gates, and each job produces a signed, offline-verifiable record.

Who it's for

DevOps, SRE and platform engineers running AI agents in CI or production that change real systems

How to use it

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up Cygnux-Labs/Tracekit-box in my project. Follow its README: https://github.com/Cygnux-Labs/Tracekit-box. Explain each step and check it is safe before running anything.

Read the README

Star curve

42From 0 to 42 stars between 25 Oct 2026 and 30 Oct 2026.

Get alerts for repos like this

We'll email you when something in AI agents starts rising. Free, once a week, only what matches.

22,784 GitHub repos watched and ranked every hour. Figures as of 30 October 2026.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![Cygnux-Labs/Tracekit-box on RepoAlerts](https://repoalerts.com/badge/Cygnux-Labs/Tracekit-box.svg)](https://repoalerts.com/repo/Cygnux-Labs/Tracekit-box?ref=badge)
Share on X
  • Cygnux-Labs/Tracekit

    Tamper-evident tracing and policy gating for AI agents. It checks each tool and model call before it runs, signs calls and decisions into a hash chain, and writes one verifiable file per run that can

    LibraryAI agentsPython · 357 stars · +207 this week · 34 days old

  • karthikponna/tryboxi

    Runs disposable Linux microVMs on the local machine as sandboxes for AI agents. Commands run inside each VM, with stdout, stderr and exit code returned, and results come back to the host only through

    AppAI agentsGo · 71 stars · +71 this week · 10 days old

  • jnh12/agent-microvm

    Python SDK, CLI and MCP server that create and manage isolated Firecracker microVM sandboxes on AWS Lambda MicroVMs, provisioned with boto3. Sandboxes support fast snapshot-based start, suspend and re

    LibraryAI agentsPython · 48 stars · +2 this week · 9 days old

  • microsoft/nvx

    Ultra-light micro-VM sandbox for running untrusted workloads with hardware-enforced isolation. Built on OpenVMM, it runs Linux as a guest on KVM, MSHV or Windows Hypervisor Platform, with a Python har

    AppDev infrastructureRust · 794 stars · +51 this week · 64 days old

  • solongate/agent-security

    Open-source Go security gateway for AI coding agents such as Claude Code and Codex. It checks tool calls against allow/deny policies before they run, detects and can redact or block secrets, applies r

    AI agentsGo · 158 stars · +2 this week · 33 days old

  • perplexityai/SPACE

    A sandbox platform that runs code in isolated Firecracker microVMs. Applications use its HTTP API to create sandboxes from templates, run commands in sessions, collect output over a separate data-plan

    AppDev infrastructureRust · 2,003 stars · +116 this week · 29 days old