Connect and work with coding agents
Vortex brings your connected coding agent into the project conversation. Your provider account supplies model access and its allowance; Vortex supplies the surrounding project workflow, preview and tools. Start by confirming installation, sign-in and one successful project run.
Connect the provider you already use
Open AI providers in Settings, inspect installation status and complete the supported account flow. An executable being present is different from a verified account. Choose the provider in a new conversation and ask it to inspect the selected project before requesting edits.
Guide a run without losing the thread
Choose the access mode for the work, answer approvals in the owning run and send a bounded follow-up when requirements change. A provider can accept steering during the active turn or retain it for the next one. Read the queue state before repeating an uncertain instruction.
Choose the next work step
Type @ in chat to choose @architect, @ux, @design, @ui, @security or @qa. These mentions guide the current agent; they do not automatically create another agent or expand its permissions. Request parallel delegation when the work benefits from independent tasks.
Keep the account limits understandable
Conversation context, external provider quota and cloud storage are different measures. Models and usage reports vary between providers. Missing quota information is not unlimited usage, and Vortex does not include an AI-token allowance.
Follow the detailed guides
- Connect Codex
Connect a Codex account profile and choose it for a conversation. Keep multiple provider profiles distinct from your Vortex sign-in.
- Connect Claude Code
Connect a Claude Code account profile and choose it for a conversation. Keep multiple provider profiles distinct from your Vortex sign-in.
- Connect Google Antigravity
Connect Google Antigravity, then choose it for a conversation. The provider's current login is separate from your Vortex sign-in.
- Connect Grok Build
Connect Grok Build, then choose it for a conversation. The provider's current login is separate from your Vortex sign-in.
- Connect Kimi Code
Connect Kimi Code, then choose it for a conversation. The provider's current login is separate from your Vortex sign-in.
- Connect Cursor
Install Cursor, connect a provider account and use it for a project conversation with approvals and review.
- Connect OpenCode
Connect a local OpenCode coding agent to its API provider and distinguish it from direct OpenRouter generation.
- Connect Muse Code
Install Muse Code from Meta, sign in with a device code and use it as a coding agent in Vortex. Learn how its access modes, usage windows and capabilities differ.
- Choose what your agent can do
Auto runs authorized ordinary reads and scoped changes directly through native tools. Learn how provider file edits, tool confirmations and read-only Plan mode differ.
- Add an instruction while work continues
You can add a detail while your agent is working. Keep the new instruction specific enough that the agent can tell whether it changes the current task or comes next.
- Choose a model and read its usage
Choose the provider account and model for each conversation. Fast mode starts off in new chats; read provider usage separately from conversation context.
- Show the agent what you mean
A screenshot or sketch can explain a design change better than a paragraph. Attach it to the draft or conversation, then say which part the agent should use.
- Dictate a message or talk with Voice
Use local or cloud dictation, choose a conversation voice, configure start and stop phrases, and manage microphone access in Settings → Voice.
- Computer use and system permissions
Choose app access and saved permissions, check operating-system requirements and verify agent actions on your computer.
- Use GPT through an SSH server
For enabled accounts, connect a Linux server, complete the supported provider sign-in and choose the GPT through SSH account in chat.