Zed Editor
Integrate Zed Editor with AI Studio as a custom AI provider for coding agents.
This quickstart guide shows you how to integrate Zed Code Editor with Hyperstack AI Studio using OpenAI-compatible APIs. You’ll learn how to authenticate with AI Studio, configure Hyperstack as a custom AI provider inside Zed, and test AI-powered coding agents directly within your editor.
This setup enables Zed to interact with any model hosted in AI Studio, including base or fine-tuned models, using OpenAI-style endpoints.
For the complete guide that includes architectural details, configuration screenshots, model selection strategy, and advanced workflows, see How to Integrate Hyperstack AI Studio with Zed Code Editor for Powerful Coding Agents.
Why Integrate Zed with Hyperstack AI Studio
Zed is a high-performance, collaborative code editor built in Rust. Designed for sub-millisecond latency and real-time collaboration, it supports AI-powered development workflows through configurable coding agents.
Hyperstack AI Studio is an enterprise-grade generative AI platform that provides:
- OpenAI-compatible APIs
- Hosted base and fine-tuned models
- Scalable inference infrastructure
- Model fine-tuning and deployment
- Usage tracking and cost monitoring
Because Hyperstack exposes OpenAI-compatible endpoints, Zed can connect directly without requiring additional middleware or proxy servers.
By combining Zed’s performance with Hyperstack’s scalable AI backend, developers can:
- Generate code snippets instantly
- Refactor complex logic
- Debug with reasoning-capable models
- Use custom fine-tuned models trained on internal repositories
- Monitor usage and optimize model performance through the Hyperstack dashboard
To explore the integration architecture and deeper implementation concepts, see the full Zed integration tutorial.
How to Install and Connect Zed to Hyperstack AI Studio
Follow these steps to install Zed, retrieve your Hyperstack credentials, and configure a custom AI agent. For additional context and screenshots, refer to the complete integration guide.
-
Install Zed Editor
Download Zed from the official website:
https://zed.devInstall the editor for your operating system and launch it.
On first launch, you may be prompted to:
- Choose a theme
- Configure font and layout preferences
- Sign in with GitHub (required for AI features in current Zed builds)
-
Get API Credentials from Hyperstack AI Studio
Generate the credentials required to authenticate Zed with Hyperstack.
a. Log in to the Hyperstack Console
b. Navigate to the AI Studio Playground
c. Select your desired model (for example:openai/gpt-oss-120b)
d. Select the API tab to retrieve your Base URL and Model ID
e. Visit the API Keys page
f. Click Generate New Key, name it (e.g.,zed-integration-key), and securely store the generated API key -
Open Zed AI Agent Settings
Zed allows you to configure custom AI providers through its Agent Settings panel.
Open the Command Palette:
- Windows/Linux:
Ctrl + Shift + P - macOS:
Cmd + Shift + P
Search for:
agent: settingsSelect it to open the AI configuration panel.
- Windows/Linux:
-
Add Hyperstack as a Custom AI Provider
In the Agent Settings panel:
- Click Add Custom AI Provider
- Select OpenAI (or Custom OpenAI-compatible provider, depending on your Zed version)
Enter the following configuration values:
-
Base URL:
https://console.hyperstack.cloud/ai/api/v1
Zed automatically appends/chat/completions, so only the base URL is required. -
Model Name:
openai/gpt-oss-120b
You can replace this with any base or fine-tuned model deployed in AI Studio. -
API Key: Paste the key generated from Hyperstack.
Save the configuration.
Ensure your newly created Hyperstack provider is selected as the active AI agent before testing.
Zed will now recognize Hyperstack AI Studio as a valid AI provider.
-
Run and Test
Open a new file in Zed and activate the AI agent using:
- The AI Edit button, or
- The Agent Chat panel
Try sending a prompt such as:
Write a Python function that prints "Hello, World!"If configured correctly, you should receive a valid response from your Hyperstack-hosted model.
Example output:
# This function prints a simple greeting
def hello_world():
print("Hello, World!")Accept the suggestion to insert the generated code into your file.
If the response appears successfully, your integration is complete.
To track usage, token consumption, and performance metrics, visit the Usage Dashboard in the Hyperstack Console.
Next StepsFor troubleshooting and additional configuration options, see the full guide: How to Integrate Hyperstack AI Studio with Zed Code Editor for Powerful Coding Agents.