HelixControl turns operator intent into safe infrastructure actions: a LangGraph agent plans, MCP tools execute against Kubernetes, and guardrails keep autonomous operations within bounds.
Part of my . Built on the "" model.
# 1. Clone
git clone https://github.com/Kimosabey/helix-control.git
cd helix-control
# 2. Install
# (see docs/GETTING_STARTED.md for the full setup)
# 3. Run
docker compose up- Intent → plan → action agent loop
- MCP tools for real infra operations
- Kubernetes-native actions
- Guardrails and approval gates
%%{init: {'theme':'base','themeVariables':{'primaryColor':'#ffffff','lineColor':'#2563eb','mainBkg':'#ffffff'}}}%%
graph LR
A([Intent])
B([LangGraph Agent])
C([MCP Tools])
D([K8s Actions])
A --> B
B --> C
C --> D
style A fill:#eff6ff,stroke:#2563eb,stroke-width:2px,color:#1e40af
style B fill:#eff6ff,stroke:#2563eb,stroke-width:2px,color:#1e40af
style C fill:#eff6ff,stroke:#2563eb,stroke-width:2px,color:#1e40af
style D fill:#eff6ff,stroke:#2563eb,stroke-width:2px,color:#1e40af
Letting an agent act on infrastructure while keeping it provably safe with guardrails and approvals.
See docs/ARCHITECTURE.md for the full HLD/LLD and design decisions.
| Layer | Technology | Role |
|---|---|---|
| LangGraph | LangGraph |
Stateful multi-agent orchestration |
| MCP | MCP |
Model Context Protocol tooling |
| Kubernetes | Kubernetes |
Container orchestration |
- Architecture — high- and low-level design, decision log
- Getting Started — prerequisites, setup, environment
- Failure Scenarios — fault analysis and recovery
- Interview Q&A — deep-dive walkthrough
- Dry-run planning
- Policy-as-code guardrails
- Audit trail of agent actions
Released under the MIT License.
Harshan Aiyappa Senior Full-Stack Hybrid AI Engineer Voice AI • Distributed Systems • Infrastructure
