Govern your AI agents. Before they break prod.

Security, model routing, overnight maintenance, knowledge graphs, and self-improvement. Five shell-native tools. One install. No cloud lock-in.

Components

Five tools. One stack.

Each solves a real problem standalone. Together they create compound capabilities none has alone.

Integration

Better together

Individual tools solve individual problems. The stack creates compound capabilities.

Dangerous command detected

Solo: GuardRail blocks it.

Stack: GuardRail blocks it. Autonomie OS learns the pattern. Night Shift adds a regression test.

New API endpoint added

Solo: Graphify maps it.

Stack: Graphify maps it. Model Router picks the right LLM for review. GuardRail validates auth middleware.

Lint error in staging

Solo: Night Shift patches it.

Stack: Night Shift patches it. GuardRail validates the fix. Graphify updates the knowledge graph.

Choosing an LLM for a task

Solo: Model Router picks one.

Stack: Router picks based on Graphify's complexity score. Autonomie OS remembers which models worked best.

Get started

One command. All five tools.

curl -fsSL https://raw.githubusercontent.com/FvdHMBAI/agent-stack/main/install.sh | bash

Requires bash 4+, git, curl, jq. Linux and macOS.

Or: docker compose up

Pricing

Open source. Paid plans back soon.

All 5 tools are open source (MIT). The paid Team and Enterprise plans are paused. GuardRail Pro and DSGVO/GDPR Shield Starter are available individually.

Starter
0 EUR / open source

For solo developers and small teams.

  • All 5 components (MIT)
  • 14 GuardRail core guards
  • 6-tier model routing
  • Community support (GitHub)
Get Started
Team
Back soon

Paid plan, sales paused.

  • GuardRail Pro
  • DSGVO/GDPR Shield
  • Email support
Team Plan: back soon
Enterprise
Back soon

Paid plan, sales paused.

  • Everything in Team
  • EU AI Act compliance report
  • Setup support
Enterprise: back soon