ONE WARE Agents

Try ONE WARE Agents for Free

Want to test ONE WARE Agents on your own Vision AI project? Contact us to unlock a free trial with Compute Credits for your account.

Contact Ussales@one-ware.com

ONE WARE Agents bring leading AI models (GPT, Claude, DeepSeek, and more) directly into ONE WARE Studio. Describe what you want to detect or classify, and the agent sets up the project, prepares and labels the dataset, trains, tests, and exports the model while you stay in control of every step.

Get Started

Haven't installed ONE WARE Studio yet?

Before using ONE WARE Agents, install ONE WARE Studio and the ONE AI Extension.

Setup Software →

The ONE AI tools and workflow are identical across all providers. Choose how you want to run ONE WARE Agents:

ONE WARE Account

Use models provided by ONE WARE Cloud (including EU-only and Global models) with zero setup. Billed via your organization's Compute Credits and requires a PRO Plan, or contact us for a free trial.

1. Open View → Tool Windows → AI Chat in ONE WARE Studio.
2. Select ONE WARE Agents in the provider selector at the bottom of the chat and sign in with your ONE WARE Cloud account.
3. Pick a model, set the mode to Agent, and describe your task:

   "Create an project that finds scratches on metal parts."

GitHub Copilot

Use the models included in your existing GitHub Copilot subscription at no extra chat cost.

1. Open View → Tool Windows → AI Chat in ONE WARE Studio.
2. Select GitHub Copilot in the provider selector at the bottom of the chat and click Sign in with GitHub.
3. Pick a model, set the mode to Agent, and describe what you want to build.

Self-Hosted / BYOK

Run a local model server (such as Ollama) or connect your own OpenAI / Anthropic API key. Pair with a Self-Hosted ONE AI Worker to run 100% on your own hardware.

1. Open Settings → AI Chat → Copilot CLI in ONE WARE Studio.
2. Set Model Provider to OpenAI Compatible (BYOK) or Anthropic (BYOK).
3. Enter your BYOK Endpoint (for example http://localhost:11434/v1 for a local Ollama server or https://api.openai.com/v1).
4. Enter the API Key Environment Variable name (for example OPENAI_API_KEY). Your key is read from the environment and never stored in settings.
5. Select GitHub Copilot in the provider selector at the bottom of the chat.

Follow the Step-by-Step Tutorial →

What the Agent Can Do

The agent is connected to ONE WARE Studio and ONE AI through more than 45 tools:

Projects & Settings

Sets up your ONE AI project and finds the right settings for your task and your target hardware.

Create new projectsChoose classification, detection or segmentationSwitch between Basic and Advanced modeManage configurations for different targetsTune model and hardware settings

Labels & Image Processing

Defines what your model should find and how your images are prepared for training.

Add, rename and recolor labelsClean up unused labelsAdd prefiltersAdd augmentationsReorder the processing pipeline

Dataset & Import

Brings your data into the project and makes sure it is ready for training.

Turn videos into training imagesImport YOLO, COCO, Pascal VOC and mask datasetsFind missing labels and split problemsAnalyze object sizes and class balance

Auto-Labeling & Review

Labels your images automatically, so you only have to check and correct the result.

Label datasets automatically with SAMPre-label images with your trained modelOpen the annotation tool for your review

Synthetic Data

Creates training data when you have little or no real images, so you can train a first model right away.

Generate images from a descriptionAdd defects, change backgrounds and lightingBuild fully labeled synthetic datasetsCreate test videos

Training, Test & Export

Trains your model in OneWare Cloud and delivers a tested, ready-to-use model.

Train in OneWare CloudFollow the training progressExplain failed trainingsTest models with metrics and visualizationsExport and download ONNX models

Automation Scripts

Turns your model into an application with OneWare Automation.

Write automation scriptsBuild operator dashboardsTest dashboards by operating them itselfShow your model live on a camera

Files & Terminal

Works with files and tools in OneWare Studio like a developer would.

Read and edit project filesWrite and run Python scriptsRun commands in the terminal

Models and Privacy

• No prompt storage: ONE WARE Cloud does not store your prompts or responses. Chat history stays on your computer.
• EU & Global models: Models provided by ONE WARE Cloud are labeled EU (processed exclusively in EU data centers) or Global. Organization admins can restrict access to EU models only under Settings → Policies (Organizations).
• 100% local option: When using a local model server (such as Ollama) together with a Self-Hosted ONE AI Worker, no data, prompts, or images ever leave your network.