Skip to main content

CROAK Overview

Computer Recognition Orchestration Agent Kit

CROAK is an open-source agentic framework that guides you through the complete lifecycle of building and deploying object detection models. It operates as a specialized "team" of AI agents callable from modern coding assistants like Claude Code.

When your model croaks, CROAK helps you figure out why.

Installation

Requires Node.js 18+.

# Initialize a new CROAK project with interactive setup
npx croak-cv init

# Or install globally for repeated use
npm install -g croak-cv
croak init

Option 2: pip (Python Package)

pip install croak-cv
croak init

Option 3: From Source

git clone https://github.com/vfrog-ai/croak.git
cd croak
./install.sh # Unix/macOS
# or
./install.ps1 # Windows PowerShell

Quick Start

# 1. Initialize a new project
croak init

# 2. Check your environment (Python, GPU, vfrog CLI, etc.)
croak doctor

# 3. Add images to data/raw/ and scan them
croak scan

# 4. Follow the guided workflow
croak annotate # Annotate via vfrog SSAT or import from external tools
croak train # Train locally, on Modal.com, or on vfrog platform
croak evaluate # Evaluate model performance & diagnostics
croak deploy # Deploy to vfrog inference, Modal, or edge

How It Works

CROAK provides structured workflows through five specialist agents:

AgentRoleWhat It Does
DispatcherPipeline CoordinatorRoutes requests to specialists, tracks pipeline state
ScoutData EngineerValidates datasets, manages annotations (vfrog SSAT or classic)
CoachTraining SpecialistConfigures and executes training across local GPU, Modal, or vfrog
JudgeEvaluation SpecialistAnalyzes model performance with actionable diagnostics
ShipperDeployment SpecialistDeploys to vfrog inference API, Modal serverless, or edge devices

Each agent has guardrails to prevent common mistakes, a knowledge base for domain expertise, and handoff contracts for passing context between pipeline stages.

Annotation Paths

CROAK supports two annotation workflows. You are never locked into one path.

Iterative auto-annotation powered by the vfrog CLI. Upload dataset images, create a reference object, run SSAT iterations, review labels in HALO, and train on vfrog's managed platform.

croak vfrog setup           # Login and select organisation/project
croak annotate # Guided SSAT workflow
croak train --provider vfrog

Classic (Full Control)

Import annotations from external tools (CVAT, Label Studio, Roboflow, etc.) in YOLO, COCO, or VOC format. Train on your own GPU or on Modal.com.

croak annotate --method classic --format yolo --path ./annotations
croak train --provider local # or --provider modal

Comparison

vfrog SSATClassic
AnnotationAuto-annotation + HALO reviewExternal tools (CVAT, Label Studio, etc.)
Trainingvfrog managed platformLocal GPU or Modal.com
Deploymentvfrog inference APIEdge (ONNX, TensorRT) or Modal
Setupcroak vfrog setupBring your own annotations
Best forGetting started quicklyFull control over pipeline

Training Providers

ProviderCommandDescription
Localcroak train --provider localTrain on your own NVIDIA GPU
Modalcroak train --provider modalServerless GPU via Modal.com
vfrogcroak train --provider vfrogManaged training on vfrog platform (requires vfrog annotations)

Deployment Targets

TargetCommandDescription
vfrogcroak deploy vfrogManaged inference API with auto-scaling
Edgecroak deploy edgeExport to ONNX, TensorRT, CoreML, or TFLite
Modalcroak deploy modalServerless inference via Modal.com

Requirements

  • Node.js 18.0.0+ (for CLI installer)
  • Python 3.10+ (for training and evaluation)
  • Git (recommended)
  • vfrog CLI (optional but recommended for SSAT annotation and vfrog deployment)
  • vfrog.ai account (for vfrog SSAT and inference)
  • NVIDIA GPU (optional — can use Modal.com for cloud GPU)

Environment Variables

VariableDescriptionRequired
VFROG_API_KEYvfrog.ai API key for inferenceOnly for croak deploy vfrog
MODAL_TOKEN_IDModal.com token (via modal setup)For cloud GPU training
note

VFROG_API_KEY is only needed for inference. Annotation, training, and other vfrog operations use CLI authentication (croak vfrog setup).

Project Structure

After running croak init, your project will have:

your-project/
├── .claude/ # Claude Code integration
│ └── skills/
│ ├── croak-router/ # /croak-router skill
│ ├── croak-data/ # /croak-data skill
│ └── ... # Other agent skills
├── .croak/ # CROAK configuration
│ ├── config.yaml # Project configuration
│ ├── pipeline-state.yaml # Pipeline progress tracking
│ ├── agents/ # Agent YAML definitions
│ ├── workflows/ # Workflow specifications
│ ├── knowledge/ # Knowledge base
│ └── contracts/ # Handoff contracts
├── CLAUDE.md # Project context for Claude Code
├── data/
│ ├── raw/ # Raw images
│ └── processed/ # Processed datasets
├── training/
│ ├── configs/ # Training configurations
│ ├── scripts/ # Training scripts
│ └── experiments/ # Experiment outputs
├── evaluation/
│ └── reports/ # Evaluation reports
└── deployment/
└── edge/ # Edge deployment packages

Next Steps