Kilo Code vs Gemini CLI vs OpenAI Codex CLI

Side by side, as alternatives to Claude Code. Rows that differ are highlighted; the strongest value in a row is marked. Unknown means no source yet.

Kilo CodeKilo-Org/kilocode

Gemini CLIgoogle-gemini/gemini-cli

OpenAI Codex CLIopenai/codex

Claude Codepaid product

Cost and coverage

Price

$0 software; you run it

Included with Claude Pro ($20/month, or $17/month billed annually), Max (from $100/month), Team and Enterprise; not on the free plan source ↗

Edit code across a repo from the terminal with an AI agent

Partly

Yes

Run commands and tests

Partly

Yes

Use the agent inside VS Code or JetBrains

Partly

Yes

Connect tools and data through MCP

Partly

Yes

Write commits and pull requests

Yes

Run the agent headless in scripts or CI (GitHub Actions)

Partly

Yes

Jobs covered

5 of 6 jobs

All 6

Popularity and activity (from GitHub)

Stars

27,695

107,492

130,321Top

—

Gain this week

Unknown

—

Signal

Building history

—

Commits / 4 wk

940Top

892

—

Latest release

v7.8.15 · 2026-10-19

v0.65.0 · 2026-10-20Top

rust-v0.163.0 · 2026-10-15

—

Commits / 12 wk

5,236

194

3,490

—

People committing / 12 mo

442+

82+

377+

—

Issues opened / closed, 30 days

318 / 231

123 / 206

7371 / 1498

—

Facts, with sources on each project page

Runs on my machine?Differs

Yes, the extension and CLI run on your machine; an optional hosted Cloud Agent also exists

Yes, the CLI runs in your terminal; the Gemini models themselves run on Google's servers

Yes, a command-line agent that runs on your computer; cloud models run on OpenAI's servers unless you use --oss

Hosted by the vendor

Code licenceDiffers

MIT

Apache-2.0

—

Model weights licence

No separate model weights

—

Commercial useDiffers

MIT allows commercial use with attribution

Allowed under Apache-2.0

—

Paid services needed?Differs

Not required with local models via Ollama (no API key needed); Kilo Gateway credits, cloud model keys, Cloud Agent and Code Reviews are optional

A paid service is required since June 18, 2026; the free Google-account tier moved to Antigravity CLI. No local model support

Not required with local models (--oss with Ollama or LM Studio) or the limited ChatGPT Free plan; paid ChatGPT plans and OpenAI API keys are optional

Subscription

HardwareDiffers

No stated needs with cloud models; local models via Ollama need a GPU with 24GB+ VRAM or a Mac with 32GB+ unified RAM

4GB+ RAM for short sessions, 16GB+ for large codebases; needs Node.js 20+ and an internet connection

Not documented in the README or CLI docs

—

Operating systemsDiffers

CLI binaries for Windows, macOS (Apple Silicon and Intel) and Linux (x64 and ARM); extensions run wherever VS Code or JetBrains IDEs run

Windows 11 24H2+, macOS 15+ and Ubuntu 20.04+

macOS, Linux and Windows (native PowerShell with a Windows sandbox, or WSL2)

—

Setup effortDiffers

Easy; install the VS Code or JetBrains extension from the marketplace, or the CLI with one npm or curl command

Easy; run with npx or install with npm, Homebrew or MacPorts, then sign in or set an API key

Easy; one-line install script, npm or Homebrew, then sign in with ChatGPT

—

Stars over time

Switch to Growth % to compare projects of different sizes fairly.

The chart appears after a few nightly checks.

Notes for a video or post

A plain summary with today's date and a link to the sources. Check each project page before you publish.

Kilo Code vs Gemini CLI vs OpenAI Codex CLI (as alternatives to Claude Code)
Figures from RepoQuarry, 22 Oct 2026. Sources: https://repoquarry.dev/compare?ids=kilo-code,gemini-cli,codex-cli&product=claude-code

Claude Code: Included with Claude Pro ($20/month, or $17/month billed annually), Max (from $100/month), Team and Enterprise; not on the free plan
Kilo Code: free software; does 5 of 6 Claude Code jobs
Gemini CLI: free software; does 5 of 6 Claude Code jobs
OpenAI Codex CLI: free software; does 5 of 6 Claude Code jobs

- Kilo Code: 27,695 GitHub stars, 5,236 commits in 12 weeks, licence MIT
- Gemini CLI: 107,492 GitHub stars, 194 commits in 12 weeks, licence Apache-2.0
- OpenAI Codex CLI: 130,321 GitHub stars, 3,490 commits in 12 weeks, licence Apache-2.0

Where they differ:
- Runs on my machine?: Kilo Code Yes, the extension and CLI run on your machine; an optional hosted Cloud Agent also exists; Gemini CLI Yes, the CLI runs in your terminal; the Gemini models themselves run on Google's servers; OpenAI Codex CLI Yes, a command-line agent that runs on your computer; cloud models run on OpenAI's servers unless you use --oss
- Code licence: Kilo Code MIT; Gemini CLI Apache-2.0; OpenAI Codex CLI Apache-2.0
- Commercial use: Kilo Code MIT allows commercial use with attribution; Gemini CLI Allowed under Apache-2.0; OpenAI Codex CLI Allowed under Apache-2.0
- Paid services needed?: Kilo Code Not required with local models via Ollama (no API key needed); Kilo Gateway credits, cloud model keys, Cloud Agent and Code Reviews are optional; Gemini CLI A paid service is required since June 18, 2026; the free Google-account tier moved to Antigravity CLI. No local model support; OpenAI Codex CLI Not required with local models (--oss with Ollama or LM Studio) or the limited ChatGPT Free plan; paid ChatGPT plans and OpenAI API keys are optional
- Hardware: Kilo Code No stated needs with cloud models; local models via Ollama need a GPU with 24GB+ VRAM or a Mac with 32GB+ unified RAM; Gemini CLI 4GB+ RAM for short sessions, 16GB+ for large codebases; needs Node.js 20+ and an internet connection; OpenAI Codex CLI Not documented in the README or CLI docs
- Operating systems: Kilo Code CLI binaries for Windows, macOS (Apple Silicon and Intel) and Linux (x64 and ARM); extensions run wherever VS Code or JetBrains IDEs run; Gemini CLI Windows 11 24H2+, macOS 15+ and Ubuntu 20.04+; OpenAI Codex CLI macOS, Linux and Windows (native PowerShell with a Windows sandbox, or WSL2)
- Setup effort: Kilo Code Easy; install the VS Code or JetBrains extension from the marketplace, or the CLI with one npm or curl command; Gemini CLI Easy; run with npx or install with npm, Homebrew or MacPorts, then sign in or set an API key; OpenAI Codex CLI Easy; one-line install script, npm or Homebrew, then sign in with ChatGPT

Stars show popularity, not quality. Check each project page before publishing.

Want share images and a ready video description? Open a project's creator kit.

Numbers: GitHub, fetched nightly. Facts: read from each project's own documentation, with the source on its page. How we check. Kilo-Org/kilocode ↗google-gemini/gemini-cli ↗openai/codex ↗

Kilo Code vs Gemini CLI vs OpenAI Codex CLI

Stars over time

Notes for a video or post

Cookie preferences

Report a problem