AI IDE List
Back to Blog
On This Page8 sections

Editorial snapshot from September 2026. Prices, models and interface labels may change; this is a practical guide, not a live product feed.

A terminal coding agent with provider choice, task modes, MCP and skills.

Coding agent · Kilo · macOS · Windows · Linux

Suitable workflows

Developers who want to choose models and switch between planning, debugging and implementation.

Limitations and billing

Current documentation targets CLI 1.0+; older CPUs may need a baseline binary.

Capabilities we verified

Agent workflow · CLI surface · MCP · Skills · Bring your own key

This is an evidence-based shortlist, not an exhaustive feature inventory. Omitted capabilities have not been checked for this record.

Pricing & usage

See official pricing

Provider usage or Kilo service billing. The cost of metered usage or an external agent can be separate from the subscription.

Models & access

Connect a supported model provider; available models and prices follow that provider.

Install and start the CLI

npm or an official standalone binary; check CPU architecture before downloading.

npm install -g @kilocode/cli

Open your project folder in a terminal, then run:

kilo

Account and authentication

Run /connect to configure provider credentials before selecting a model.

Project configuration and tools

Use kilo models to inspect access, kilo mcp for tool connections and kilo stats for usage.

First task to try

Choose a planning mode, examine the proposed steps, then move to implementation.

Script usage

This example asks for a project summary. Tool permissions still apply; a prompt is not a sandbox.

kilo run "Summarize the project structure without modifying files."

All AI CLI tools →

OpenCode — An open-source coding agent with a terminal UI and configurable model providers.

Cline CLI — Cline’s terminal agent for interactive work, headless tasks and configurable providers.

Qwen Code — Qwen’s open-source terminal agent for repository work and configurable model access.

Project evaluation checklist

  1. Open a small, familiar project and confirm that your essential language tooling works.
  2. Give the agent one bounded change with an observable acceptance criterion.
  3. Review the diff, run the project’s checks and compare the result with your current workflow.
  4. Inspect usage after the task. Estimate a month of similar work, including any separate model or agent bill.
Share this article

Referenced Tools

Browse entries that are adjacent to the topics covered in this article.

Explore directory