Skip to main content
WT

A local CLI coding agent powered by your web AI account

WTAgent is an open-source local coding agent that routes tasks through web versions of ChatGPT, Claude, DeepSeek, Gemini, Grok, Kimi, or GLM. It opens a dedicated Chrome profile, uses your signed-in account rather than an API key, and can work with local files and run commands from the terminal.

Agenticness = how independently a tool can take action, scored across 9 dimensions. Scored independently by David Kooi, Skylark Creations — see full rubric → Last re-evaluated 21 September 2026.

See pricing ↓

Desktop
Code Execution
File Access
B2B
CLI
Computer Use
Model Agnostic
Visit WTAgent

Is this your tool? Claim this listing to manage your content and analytics.

Ask about WTAgent

Get answers based on WTAgent's actual documentation

Try asking:

About

What It Is

WTAgent is a local, open-source coding agent for developers who want an agentic command-line workflow without supplying an AI API key. You install it with npm, open a project directory, and give it a task in the terminal; the tool uses a dedicated...

What to Know

The key distinction is that WTAgent relies on browser-based access to consumer web AI products rather than their APIs. That can be useful for people whose existing subscriptions include web access or quotas, but it also means the experience depends...

Key Features
Installs globally through npm with `npm install -g wtagent`
Accepts coding tasks from a terminal in the current project directory
Uses a dedicated Chrome profile for web-AI sign-in
Works with ChatGPT Web, including ChatGPT Pro accounts
Supports Claude, DeepSeek, Gemini, Grok, Kimi, and GLM as selectable web providers
Use Cases
Use an existing ChatGPT or Claude web account to carry out coding tasks from a project terminal
Ask an agent to create a small program, save it locally, and execute it
Switch among supported web AI providers for a local command-line coding workflow
Agenticness: Guided Assistant

Executes tasks you assign, one step at a time, within narrow domains.

High evidence
Last evaluated: Sep 21, 2026
This tool has strong action capabilities but limited safety controls. Use with appropriate oversight.

Dimension Breakdown

Action Capability
Autonomy
Planning
Adaptation
State & Memory
Reliability
Interoperability
Safety
Operator Sovereignty

Categories

Pricing
  • Free / open source — full functionality available at no cost.
Details
AddedSeptember 21, 2026
RefreshedSeptember 21, 2026
Agenticness
Quick Facts
DeploymentOn-device / local
AutonomySemi-autonomous
Model supportMulti-model
Open sourceYes
MCP supportNo
Team supportIndividual only
Pricing modelFree / open source
Interfacecli, browser
Sources
Last updated September 21, 2026
Free daily brief

When WTAgent changes its pricing, we catch it the next morning

We recrawl every tool in this directory daily. AI Insider is the 3-minute brief on what actually changed — pricing, features, score moves on our 36-point rubric — often before any press coverage. Sent daily. Skipped when nothing happened.

I use AI for:
Similar tools

Related Tools