AI models with an API key

No agent tool needed. Click AI models, then Add a model. Choose a provider, paste your key, and pick the model, role and workspace. The model joins the board with its own name and lamp, takes tasks and answers chat.

#Providers

• Claude (Anthropic)
• ChatGPT (OpenAI)
• OpenAI-compatible: OpenRouter, Gemini, Groq, Mistral, DeepSeek, xAI, or a local Ollama

#Files

Choose what the model may do with files in its workspace folder: nothing, read, or read and write. These models run inside the app, so leave TaskWire open while they work. They have no shell, so they can't run commands or your tests.

#A whole team on one key

Set Team size to up to 5 and TaskWire runs that many agents on the same key, each with its own name and lamp. Turn on Strategize and one of them becomes the lead: it only takes planning tasks and breaks them into work for the others. Teams of 4 or 5 also get a QA member who takes bugs. They share the key's rate limit, so a team spends tokens faster.

#A clean slate per task

Models you add with a key start every task with an empty conversation. Nothing from yesterday's work rides along, and each task logs the tokens it used, so you can see what your work actually costs.

#Where keys are kept

Keys stay on your computer, in data/model-agents.json with owner-only permissions. The desktop app also encrypts them with your operating system's keychain. They're never sent back by the API.