hexr build

Usage

hexr build <agent_file> --tenant <tenant> [options]

Arguments

path

required

Path to your Python agent file.

hexr build my_agent.py --tenant acme-corp
hexr build agents/content_crew.py --tenant acme-corp

Options

string

required

Tenant identifier. Maps to Kubernetes namespace tenant-{tenant}.

string

Override the agent name (default: extracted from @hexr_agent(name=...) or filename).

string

default:"development"

Target environment: development, staging, or production.Affects OPA policies, resource limits, and security scanning levels.

string

Container registry base URL.

hexr build agent.py -t acme --registry us-central1-docker.pkg.dev/my-project/images

string

Private PyPI URL for SDK installation in agent pods.Default: https://pypi.hexr.cloud/simple/

string

default:"3.11"

Python version for the container.

string

default:"python:3.11-slim"

Base Docker image.

string

Comma-separated cloud providers for credential exchange.

hexr build agent.py -t acme --multi-cloud aws,gcp,azure

flag

Enable subprocess role management for multi-process agents.

flag

Enable security scanning during build (dependency audit).

path

default:".hexr"

Output directory for generated artifacts.

flag

Generate manifests only — skip container image build.

flag

Show what would be generated without creating files.

string

default:"demo.hexr.dev"

SPIFFE trust domain for identity generation.

What Gets Generated

.hexr/
├── Dockerfile                    # Multi-stage build with SDK injection
├── requirements.txt              # Auto-detected from imports
├── agent-pod.yaml                # Pod spec with 4 containers
├── namespace.yaml                # tenant-{name} namespace
├── rbac.yaml                     # ServiceAccount + RoleBindings
├── agent-card.yaml               # ConfigMap for A2A discovery
├── process-contexts/             # Per-process SPIFFE context
│   ├── researcher.json
│   ├── writer.json
│   └── editor.json
└── hexr-manifest.json            # Build metadata

AST Analysis

The build command performs ~2,900 lines of AST analysis to:

Detect the framework — CrewAI, LangChain, AutoGen, Strands, Swarm, or pure Python
Discover agents — Find all @hexr_agent decorators and framework-specific agent declarations
Map sub-agents — Identify roles (researcher, writer, editor) for per-process identity
Infer resources — Detect hexr_tool() calls to determine required cloud permissions
Detect A2A — Find A2AClient usage and a2a=True parameters
Build coordination graph — NetworkX analysis of agent relationships

Examples

Basic Agent

$ hexr build research_agent.py --tenant acme-corp

Analyzing research_agent.py...
  Framework: pure_python
  Agents: 1 (research-agent)
  Resources: aws_s3
  A2A: disabled

Generated .hexr/ (5 files)

CrewAI with A2A

$ hexr build content_crew.py --tenant acme-corp --multi-cloud aws,gcp

Analyzing content_crew.py...
  Framework: crewai
  Agents: 3 (researcher, writer, editor)
  Resources: aws_s3, gcp_bigquery
  A2A: enabled
  Subprocess support: auto-detected

Generated .hexr/ (8 files, 3 process contexts)

Production Build

$ hexr build agent.py -t acme --target production --security-scan \
    --registry us-central1-docker.pkg.dev/hexr-prod/images \
    --trust-domain hexr.cloud

CLI Overview

Commands

Usage

Arguments

Options

What Gets Generated

AST Analysis

Examples

Basic Agent

CrewAI with A2A

Production Build

​Usage

​Arguments

​Options

​What Gets Generated

​AST Analysis

​Examples

​Basic Agent

​CrewAI with A2A

​Production Build

Usage

Arguments

Options

What Gets Generated

AST Analysis

Examples

Basic Agent

CrewAI with A2A

Production Build