VEKTOR CLI · CODING AGENT

A new way
to create with code.

Meet VEKTOR: the agent that explores your project, works with your tools and brings your ideas to the terminal.

Your models. Your terminal.OpenAIAnthropicOpenRouterDeepSeekGroqOpenCode Go

CONTEXT THAT CONTINUES

Your project. Your session.

Pick up where you left off.

YOU STAY IN CONTROL

Plan. Review. Approve.

Permissions for every stage.

CLI + terminal editor · Windows x64 preview

BUILT FOR THE WAY YOU CODE

Persistent sessionsYour choice of modelsSubagentsMCP + LSP

MEET VEKTOR CLI

Your workspace,
in conversation.

Explore a repository, plan a change or delegate research in the same session. Choose an example to see the experience.

vektorcli / your-projectExample session
Ready for review

Explain how authentication works in this project.

I’ll review the authentication flow and its references before proposing changes.

Explore files and references

src/auth.ts

src/session.ts

tests/auth.test.ts

The flow starts in auth.ts and stores the session in session.ts. We can review credential renewal together.

READY FOR YOUR NEXT STEP

ONE WORKSPACE

Code at the center. Your agent alongside.

Browse files, edit and review changes without leaving the terminal.

Vektorworkspace / project F3 files F4 agent
1import { createSession } from './agent'
2
3export async function start(project: string) {
4 const session = await createSession({
5 cwd: project,
6 permissions: 'ask',
7 })
8
9 return session
10}
UTF-8 Ctrl+S save · F6 review
AGENT
Review authentication in this project.

Vektor

I’ll review the sign-in flow and its tests before proposing changes.

read_file auth.test.ts
Your next instruction…↵

Illustrative view. Tabs show sample files; the actual editor is in the CLI.

A WAY INTO YOUR WORKSPACE

Start the CLI in your terminal, pointed at your project directory.

$ vektorcli --cwd ./my-project

Windows x64 preview available below. macOS, Linux and npm publication are coming later.

AN OPEN ECOSYSTEM

Choose the intelligence.
VEKTOR connects the rest.

Use your ChatGPT or Claude account through compatible agents, or connect your own API keys. Choose your connection with /connect.

WITH YOUR ACCOUNT

Codex

Sign in with ChatGPT. Requires a compatible plan.

WITH YOUR ACCOUNT

Claude Code

Sign in with Claude. Requires a compatible plan.

OR CONNECT YOUR OWN API KEY

Your account or API key
VEKTORContext · permissions · tools
Your code and terminal

ALSO THROUGH OPENCODE GO

More models for the way you work.

Choose from these families in the OpenCode Go catalog. Availability and access depend on the provider and your plan.

  • DeepSeek
  • GLM
  • Kimi
  • MiniMax
  • Hunyuan
  • MiMo
  • LongCat
  • Step

ACP

Connect an external agent.

Use an Agent Client Protocol compatible agent inside VEKTOR. Each agent keeps its own configuration and authentication.

MCP

Bring your own tools.

Connect local MCP servers over stdio to make their tools available to the VEKTOR agent.

Each provider manages access, limits and billing. Subscriptions require a plan that supports Codex or Claude Code; API usage is billed separately.

THE VEKTOR ENGINE

More context for
every decision.

Capabilities already implemented in the project. Built around everyday work with code.

PROVIDERS

Choose your model

Connect compatible providers and change models or reasoning levels within the session.

SESSIONS

Return to your work

Conversations and tabs persist per workspace so you can pick up the context when you return.

SUBAGENTS

Delegate exploration

Use subagents to investigate in parallel and bring their findings back into your conversation.

PERMISSIONS

Decide what runs

The plan, ask and accept-edits modes let you decide when to review and approve an action.

MCP + SKILLS

Connect your tools

Add MCP servers, skills and custom tools to work with the context of your project.

LSP

Follow the code

Query definitions, references and diagnostics through your configured language servers.

MEASURED ENGINEERING

Performance with
the data in view.

We measure the work of the client and local harness. Model and network speed are evaluated separately.

1.43ms

Session reconstruction

8,010 history rows. Median of three warmed runtime runs.

20.26ms

Terminal repaint · p50

Real ConPTY, a restored 8,010-row session and ten full repaints.

150

Rendered rows

An initial 150-row window keeps the initial drawing work bounded when opening a long session.

Local measurement · Windows x64 · Bun 1.4.2 · Nov 16, 2026

View methodology and results

The runtime benchmark reconstructs history and processes 2,000 synthetic chunks in 40 ms bursts. Each run takes the best replay of three internal iterations; the displayed value is the median of three runs. The terminal test uses a compiled binary, one 120×40 ConPTY run and ten keypresses per repaint class. No models or network requests are involved.

The first paint of that restored session took 1.77 s. Full repaint measured 23.94 ms p95. These are local idle-session results, not model generation latency.

Runtime report (JSON)Terminal report (JSON)

Architecture changes the path.

VEKTOR can run its own agent or connect to an external agent through ACP. Here is how each part of the system changes.

ArchitectureVEKTOR localVEKTOR + ACP
Where the loop livesInside the TUI processIn the configured external agent
Main interfaceNative terminalThe same VEKTOR terminal
CommunicationDirect in-process callsJSON-RPC with the agent process
Comparable timingsLocal reports availablePending the same workload
Reference documentationACP

Architecture alone does not determine which is faster. Model, provider and workload also matter.

GET STARTED

Your next session,
in your terminal.

Download the Windows x64 preview. The editor, files and agent share one workspace.

Download for Windows x64

Preview 0.2.0 · ZIP · Unsigned executable

macOS and Linux: public distribution coming later. This preview does not require Bun to run the CLI.

SHA-256
  1. 01

    Open your project

    Extract the ZIP and run the command in PowerShell. Use your project path.

    .\vektorcli.exe --cwd C:\ruta\mi-proyecto
  2. 02

    Connect your account

    Choose Codex or Claude Code. The first connection installs its adapter and needs Node.js 22+ and npm. The provider handles sign-in.

    /connect
  3. 03

    Work with your code

    F3 opens files, Ctrl+S saves, F4 returns to the agent and F6 shows Git changes. In a wide terminal, code and agent sit side by side.

    F3 files F4 agent F6 review
Can I use my subscription?

Yes, through the Codex and Claude Code adapters, with a plan that includes access to those products. VEKTOR does not turn a chat subscription into an API key.

Does it also work with API keys?

Yes. OpenAI, Anthropic, OpenRouter, DeepSeek, Groq and OpenCode Go are available through API connections. The provider bills that usage separately.

Is this a complete IDE?

The preview combines a local editor, explorer, tabs, Git review and agent in the terminal. The editor does not yet offer semantic completion or an integrated debugger.

Who controls changes?

You choose the agent permission mode. The editor saves when you ask and detects whether another process changed the file before overwriting it.

THE NEXT CHAPTER

The terminal is
the beginning.

VEKTOR CLI is the current product. The IDE will be the next interface to keep building in the same direction.

Let’s talk about VEKTOR
COMING NEXT

VEKTOR IDE

A new space for working with code. More details when it is ready.

THE TEAM BEHIND IT

VEKTOR has
a direction.

At Vektorial Labs, we are building tools for coding with agents. VEKTOR brings that vision together: project context, connected tools and decisions in the hands of the person creating.

GET IN TOUCH

Let's
talk.

Want to talk about VEKTOR, collaborate or learn about what we are building?

Your email app will open. Review and send the message there. hello@vektoriallabs.com