HN Showcase
Back to browse
GitHub Repository

Local control plane for running AI agents with sandboxes, approvals, guardrails, credentials, and runtime health.

51 starsTypeScript

Armorer – A secure local control plane to sandbox AI agents in Docker

by cristianleo·May 9, 2026·3 points·2 comments
Visit ProjectView on HN

AI Analysis

●●SolidShip ItNiche Gem

Docker sandboxing for agents when most runners just trust whatever the LLM outputs.

Strengths
  • •Uses Docker containers to isolate agent execution and prevent host system damage.
  • •Includes a local UI for monitoring agent health and logs in real time.
  • •Installation script designed to be run directly by coding agents like Claude Code.
Weaknesses
  • •Agent orchestration logic is thin; mostly wraps Docker rather than coordinating complex workflows.
  • •Competes with established sandboxing tools like E2B and Modal that offer more features.
Target Audience

Developers building or testing multi-agent systems

Similar To

E2B · Modal · Docker

Similar Projects

Developer Tools●●●Banger

Agentctl, a local control plane for coding agents

Replaying past sessions against stricter policies beats guessing rules before you know the risks.

Solve My ProblemDark Horse
chocks
3027d ago
Security●●Solid

Runtime security for AI agents(injection,tool abuse, data exfiltration)

OPA-based policy engine for AI agents blocking injection and tool abuse.

Solve My Problem
dshapi
121mo ago
Security●●●Banger

A security scanner for AI Agent Skills

Docker sandbox execution catches runtime threats static analysis alone misses.

Big BrainBold Bet
mayziem
501mo ago