kern — security grade SAFE, quality 69/100

Security audit verdict: SAFE · quality 69/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by getkern · Agent Tool · ★ 418

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is kern safe to install? View the security audit →

About kern

kern: a fast, rootless sandbox and virtual resource runtime. Run any workload in a real container, including an agent's tool-call or AI-generated code. A real, kernel-enforced container in 3.5 ms, out of one static binary with no daemon. 0 RAM at rest · no daemon, no socket, nothing to start · one static binary, its only Rust dependency

ai-agentscgroupscode-executioncode-interpretercontainer-runtimecontainersdaemonlessdockerdocker-alternativelinux

Quick Facts

Stars418
Forks9
LanguageRust
CategoryAgent Tool
LicenseApache-2.0
Quality Score69.3079863017894/100
Last Updated2026-09-22
Created2026-07-18
Platformsdocker, rust
Est. Tokens~26k

Compatible Skills

These tools work well together with kern for enhanced workflows:

  • podman-mcp-server — semantic(0.35)+complementary+rare_topics+similar_pop+shared_platform (66%)
  • nono — semantic(0.21)+complementary+rare_topics+same_lang+similar_pop+shared_platform (62%)
  • zapcode — semantic(0.18)+complementary+rare_topics+same_lang+similar_pop+shared_platform (61%)
  • zerobox — semantic(0.19)+complementary+same_lang+similar_pop+shared_platform (57%)
  • vibepod-cli — semantic(0.22)+complementary+rare_topics+similar_pop+shared_platform (57%)

kern alternative? Top 6 similar tools

Looking for a kern alternative? If you're comparing kern with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • clampdown by 89luca89 · ⭐ 98

    Run AI coding agents in hardened container sandboxes.

  • vibepod-cli by VibePod · ⭐ 165

    Unified CLI for running AI coding agents in isolated containers. Includes built-in local metrics collection, H

  • yoloai by kstenerud · ⭐ 206

    Your agent is a security risk, so treat it like one. yoloAI does AI agent sandboxing right.

  • zapcode by TheUncharted · ⭐ 89

    TypeScript interpreter for AI agents. Written in Rust. 2µs cold start. Sandboxed. Alternative to MCP tool call

  • clawk by clawkwork · ⭐ 973

    Give coding agents a disposable Linux VM, not your laptop

  • mcp-server-code-execution-mode by elusznik · ⭐ 337

    An MCP server that executes Python code in isolated rootless containers with optional MCP server proxying. Imp

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is kern?

kern is a fast, rootless container runtime and sandbox with no daemon. It runs workloads, including agent tool calls and code generated by an LLM, in real containers enforced by the kernel.. It is categorized as a Agent Tool with 418 GitHub stars.

What programming language is kern written in?

kern is primarily written in Rust. It covers topics such as ai-agents, cgroups, code-execution.

How do I install or use kern?

You can find installation instructions and usage details in the kern GitHub repository at github.com/getkern/kern. The project has 418 stars and 9 forks, indicating an active community.

What license does kern use?

kern is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to kern?

The top alternatives to kern on Agent Skills Hub include clampdown, vibepod-cli, yoloai. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools