Ceres - Open Copilot with Voice Understanding - Visual Studio Marketplace

Skip to content

| Marketplace

Sign in

Visual Studio Code>Programming Languages>Ceres - Open Copilot with Voice UnderstandingNew to Visual Studio Code? Get it now.

Ceres - Open Copilot with Voice Understanding<br>Andreas Express

278 installs<br>| (0) | Free<br>Get predictable AI help in your IDE with voice input, file and selection chat, with support for OpenAI, DeepSeek, Ollama, and more.<br>Installation<br>Launch VS Code Quick Open (Ctrl+P), paste the following command, and press enter.<br>Copy<br>Copied to clipboard

More Info

OverviewVersion HistoryQ & ARating & Review<br>Ceres

Focused AI assistance for the code in front of you.

Ceres is an AI sidebar for VS Code that helps with the code, files, errors, terminal output, Git changes, and debugger state.

It is built for developers who want AI nearby, not AI taking over. Instead of turning every request into a full autonomous run, Ceres keeps the workflow explicit: ask questions, get context-aware suggestions, it is that simple.

Why Ceres?

Many AI coding tools are designed around large agent runs. That can be powerful, but it can also be expensive, noisy, and hard to control.

Ceres takes a smaller, more predictable path:

Send files or selection, errors, terminal output, or even debugger state.

Use OpenAI-compatible APIs, perfect for budget models and local model cases.

Keep the assistant inside your normal editor workflow.

Avoid spending tokens on context you did not ask for.

Get instant suggestions without waiting for a long task to complete.

Tools included in Ceres

Ceres is a practical AI assistant inside VS Code and the browser

Use it directly or @attach any context from your environment without leaving the editor.

@Search the internet<br>@Workspace problems<br>@Git changes<br>@Incoming changes<br>@Git history<br>@Terminal activity<br>@Debug snapshot<br>@Console logs (Browser)<br>@Recent history (Browser)<br>@Files<br>@Functions<br>@Tabs (Browser)

Then get one-click suggestions you can review and insert at the selected block or apply with AI. ;)

What Ceres Is Not

Ceres is not designed to take over your whole repository.

It does not try to silently crawl every file, plan a large autonomous task, and rewrite your project on its own. If you want a full end-to-end coding agent that works independently for a long session, tools like Cursor, Copilot agents, Cline/Kilo, Claude Code, Codex, or other agent platforms may be a better fit.

Ceres is strongest when you already know the area you want to work on and want focused AI help without handing over the entire workflow.

Features

AI sidebar inside VS Code : Chat with AI without leaving the editor.

Add selected code to chat : Send only the code selection you care about.

Add files from editor or explorer : Attach a file when the assistant needs broader context.

Active file context : Ask from the file currently open in the editor.

Workspace Problems : Send diagnostics and errors from VS Code Problems.

Git overview : Read current staged and unstaged changes or summarize pull requests.

Terminal activity : Use recent shell-integrated terminal commands and output as context.

Debugger snapshot : Read paused debug sessions, stack frames, variables, scopes, and exception details.

Voice input : Dictate prompts and commands when typing is slower.

Insert suggestions : Place suggestions directly into the active editor.

Run terminal suggestions : Send supported command suggestions to a VS Code terminal.

Speech synthesis : Listen to AI responses read aloud with text-to-speech.

Custom providers and local models : Use OpenAI-compatible endpoints, OpenRouter, DeepSeek, Ollama, LM Studio, and other compatible providers.

Local And Budget Models

Ceres is provider-flexible by design. You can use hosted models when you need stronger reasoning, or local and budget models for everyday development work.

Typical setups include:

Ollama

LM Studio

OpenAI-compatible APIs

OpenRouter

DeepSeek

OpenAI

Other compatible model providers

This makes Ceres useful for developers who care about cost, privacy boundaries, experimentation, or avoiding lock-in.

Context Control

Ceres works best when the developer chooses the right context.

Instead of assuming the whole repository is relevant, Ceres lets you send focused material:

A code selection

A full file

Current editor context

Workspace diagnostics

Git diffs

Terminal output

Debugger state

URLs, PDFs, images, audio, and other supported inputs

Better context usually means better answers, lower token usage, and fewer hallucinations.

Common Workflows

Explain Or Improve A Selection

Select code, run Add Selection to Ceres , and ask for an explanation, refactor, review, or bug check.

Default shortcut:

Ctrl+Alt+L

On macOS:

Cmd+Alt+L

Ask About A Problem

Use the Ceres action on an error or warning to send the diagnostic and nearby code context into chat.

Review Before Pulling

Ask Ceres to inspect incoming Git changes before...