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.
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
Before using ONE WARE Agents, install ONE WARE Studio and the ONE AI Extension.
The ONE AI tools and workflow are identical across all providers. Choose how you want to run ONE WARE Agents:
- ONE WARE Account
- GitHub Copilot
- Self-Hosted / BYOK
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.
- Open View → Tool Windows → AI Chat in ONE WARE Studio.
- Select ONE WARE Agents in the provider selector at the bottom of the chat and sign in with your ONE WARE Cloud account.
- Pick a model, set the mode to Agent, and describe your task:
"Create an project that finds scratches on metal parts."
Use the models included in your existing GitHub Copilot subscription at no extra chat cost.
- Open View → Tool Windows → AI Chat in ONE WARE Studio.
- Select GitHub Copilot in the provider selector at the bottom of the chat and click Sign in with GitHub.
- Pick a model, set the mode to Agent, and describe what you want to build.
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.
- Open Settings → AI Chat → Copilot CLI in ONE WARE Studio.
- Set Model Provider to OpenAI Compatible (BYOK) or Anthropic (BYOK).
- Enter your BYOK Endpoint (for example
http://localhost:11434/v1for a local Ollama server orhttps://api.openai.com/v1). - Enter the API Key Environment Variable name (for example
OPENAI_API_KEY). Your key is read from the environment and never stored in settings. - Select GitHub Copilot in the provider selector at the bottom of the chat.
What the Agent Can Do
The agent is connected to ONE WARE Studio and ONE AI through more than 45 tools:
Projekte & Einstellungen
Richtet Ihr ONE AI Projekt ein und findet die passenden Einstellungen für Ihre Aufgabe und Ihre Zielhardware.
Labels & Bildverarbeitung
Legt fest, was Ihr Modell finden soll und wie Ihre Bilder für das Training vorbereitet werden.
Datensatz & Import
Bringt Ihre Daten ins Projekt und stellt sicher, dass sie bereit fürs Training sind.
Auto-Labeling & Prüfung
Labelt Ihre Bilder automatisch, sodass Sie das Ergebnis nur noch prüfen und korrigieren müssen.
Synthetische Daten
Erzeugt Trainingsdaten, wenn Sie wenige oder keine echten Bilder haben, sodass Sie sofort ein erstes Modell trainieren können.
Training, Test & Export
Trainiert Ihr Modell in der OneWare Cloud und liefert ein getestetes, einsatzbereites Modell.
Automatisierungsskripte
Macht aus Ihrem Modell eine Anwendung mit OneWare Automation.
Dateien & Terminal
Arbeitet mit Dateien und Tools in ONE WARE Studio wie ein Entwickler.
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.