An open source platform for building, deploying, securing, and governing AI agents on Kubernetes.
Built on open standards:
- rossoctl - Main installer, UI, and documentation (Python)
- operator - Kubernetes operator for deploying and lifecycle management of agents and tools (Go)
- cortex - Kubernetes security extensions for zero-trust agent authentication (Go) — install stats (estimated from GitHub download counts, not from user machines)
- examples - Sample agents and tools (Python)
- .github - Project website and documentation (Docusaurus/HTML)
- automation - Automated org maintenance tooling using a scanner/fixer pattern (Shell)
- agent-skills - Reusable agent skills for org automation, such as link-health, automated pull request reviewing, and dependency scanning (Shell)
- rossoctl-cli - Command-line interface for Rossoctl (Go)
- mcp-gateway - Envoy-based MCP Gateway (Go) — hosted under Kuadrant org
- capture-the-flag - Capture the flag scenarios to demonstrate and test Rossoctl's security posture
- workload-harness - Benchmarking and load-generation harness for evaluating agents on the Rossoctl platform (Shell)
- context-guru - Context engineering for agentic systems — compacts and summarizes LLM context to cut cost and latency while preserving accuracy (Go)
- aiac - AI-based Access Control — translates natural-language policy into enforced PDP rules for AI agents on Kubernetes (Python)
- 📖 Start with the CONTRIBUTING guide
- 👥 Meet the maintainers
- 🌐 Learn more at rossoctl.dev
- 💬 Or just come say hi in the Rossoctl Slack
