Containarium
Open-source agent runtime with SSH-native isolation and network sandboxing
Visit containarium.dev ↗What is Containarium?
Containarium is an open-source runtime environment designed for AI agents that need to execute code safely and persistently. Each agent receives an isolated Linux box running on Kubernetes or LXC, with SSH access, real filesystem capabilities, and network isolation enforced via eBPF policy. The platform includes an MCP server built into each box, allowing agents like Claude Code, Cursor, and Cline to drive operations through structured tools rather than terminal commands.
The project targets scenarios where agents shouldn't run on a developer's laptop—long-running coding sessions, ephemeral CI environments per pull request, and multi-tenant agent fleets. It is self-hostable on any Ubuntu VM under the Apache 2.0 license, or available as a managed cloud service. According to build evidence, the project was developed using Claude Code.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered Containarium automatically. Evidence: GitHub FootprintAI/Containarium; repo has CLAUDE.md. View source.
Similar vibe-coded apps
#1 this weekOpen-source local voice cloning, dubbing, transcription, and audiobook creation
#2 this week
#5 this weekSlash commands and agents for engineers using AI without compromising standards
#6 this week523 free lessons building AI systems from math and first principles
#8 this week
#10 this weekAI-powered design intelligence toolkit for building professional interfaces
Manage teams of AI agents to run your business from one dashboard
Persistent memory for AI agents across Claude Code, Cursor, and MCP clients