VS CODE EXTENSION

BLACKBOX AI inside your editor.

Get inline completions, chat-driven edits, and multi-agent execution directly in VS Code — with no change of tools.

IN THE EDITOR

Completions and chat, in one panel.

route.ts — blackbox-app
Visual Studio Code
route.ts
1import { NextRequest, NextResponse } from "next/server"
2import { auth } from "@/lib/auth"
3
4export async function POST(req: NextRequest) {
5 const session = await auth()
6 if (!session) return NextResponse.json({ error: "Unauthorized" }, { status: 401 })
7
8 const body = await req.json()
9
10 const result = await db.insert(tasks).values({
11 title: body.title,
12 userId: session.user.id,
13 status: "pending",
14 createdAt: new Date(),
15 }).returning()
16
17 return NextResponse.json(result[0])
18}
BLACKBOX AI
Copilot
Ask Blackbox...
mainLn 9, Col 1
TypeScriptUTF-8BLACKBOX AI
WHY IT MATTERS

Built for the way you work.

01

Get intelligent code suggestions as you type — context-aware suggestions that use your open files and project structure.

02

Open the BLACKBOX chat panel and describe changes in natural language. Edits apply as inline diffs.

03

Run /multi-agent from the chat panel to send tasks to many frontier and open-source models at the same time.

CAPABILITIES

What you get.

Inline completions

Get intelligent code suggestions as you type. Completions are context-aware and use your open files, imports, and project structure.

It supports multi-line completions, function generation, and pattern-based suggestions. Press Tab to accept, or Escape to dismiss.

Chat-driven edits

Open the BLACKBOX chat panel and describe changes in natural language. Edits apply as inline diffs that you can review before you accept them.

Reference specific files with the @path syntax. The agent reads your full workspace context and makes changes that follow your architecture.

Multi-agent execution

Run /multi-agent from the chat panel to send tasks to BLACKBOX, Claude Code, Codex, and Gemini. Chairman LLM selects the best result.

Results appear as selectable diffs in the editor. Compare the implementations and select the best one, or combine parts from more than one agent.

FAQ

Common questions.

HOW DO I INSTALL IT?

Search for 'BLACKBOX AI' in the VS Code Extensions Marketplace and click Install. The extension has more than 4.2 million installations and operates like a native VS Code feature.

HOW IS THE EXTENSION LICENSED FOR A TEAM?

Enterprise agreements cover every developer in the organization from one per-token commit, with SSO sign-in — the extension uses your identity provider, and engineers do not manage their own keys. Contact sales to scope a deployment.

DOES IT WORK WITH OTHER EXTENSIONS?

Yes. BLACKBOX AI integrates with existing VS Code extensions, keybindings, and themes. Its keyboard shortcuts and UI are designed to prevent conflicts with your current workflow.

WHAT LANGUAGES ARE SUPPORTED?

All languages that VS Code supports work with BLACKBOX AI. AI features are optimized for TypeScript, Python, Go, Rust, Java, C++, and all major frontend and backend frameworks.

WHICH AI MODELS ARE AVAILABLE?

The extension provides access to frontier and open-source models that include Claude Opus-4.6, GPT-5.2, Gemini-3, Grok-4, Llama, and Mistral — the same catalog as every other surface, on the same per-token commit.

HOW DOES MULTI-AGENT MODE WORK IN VS CODE?

Run /multi-agent from the chat panel to send the same task to Blackbox, Claude Code, Codex, and Gemini at the same time. Chairman LLM evaluates each implementation, and the results appear as selectable diffs that you can compare and merge.

IS MY CODE SENT TO EXTERNAL SERVERS?

We send code context for AI processing with end-to-end encryption, and on Enterprise, we remove PII before a prompt reaches a closed model. Organizations that cannot route to a third party at all can run a single-tenant deployment of an open-weight model instead, isolated to them.