OpenHands vs OpenAI Codex CLI vs goose

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.

OpenHandsOpenHands/OpenHands

OpenAI Codex CLIopenai/codex

gooseaaif-goose/goose

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

Partly

Yes

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

Partly

Yes

Jobs covered

6 of 6 jobs

5 of 6 jobs

6 of 6 jobs

All 6

Popularity and activity (from GitHub)

Stars

91,499

130,321Top

55,514

—

Gain this week

Unknown

—

Signal

Building history

—

Commits / 4 wk

345

892Top

139

—

Latest release

v1.30.0 · 2026-10-22Top

rust-v0.163.0 · 2026-10-15

v1.55.0 · 2026-10-16

—

Commits / 12 wk

740

3,490

657

—

People committing / 12 mo

54+

377+

77+

—

Issues opened / closed, 30 days

464 / 367

7371 / 1498

314 / 237

—

Facts, with sources on each project page

Runs on my machine?Differs

Yes; Agent Canvas and the agent server run on your machine by default, or on your own Docker host, VM or Kubernetes cluster

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

Yes, desktop app and CLI run on your computer

Hosted by the vendor

Code licenceDiffers

MIT

Apache-2.0

—

Model weights licence

No separate model weights

—

Commercial useDiffers

Yes, MIT allows commercial use

Allowed under Apache-2.0

Yes, Apache-2.0 allows commercial use

—

Paid services needed?Differs

Not required with local models (LM Studio, Ollama, vLLM, SGLang); cloud model APIs and OpenHands Cloud are optional

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

Not required with local models (Ollama, LM Studio, Docker Model Runner, Ramalama) or free tiers such as Groq; paid APIs are optional

Subscription

HardwareDiffers

No requirements given for Agent Canvas itself; the recommended local model needs a 24GB GPU or an Apple Silicon Mac with 64GB memory

Not documented in the README or CLI docs

No hardware requirements documented in the README or install docs (checked 2026-10-21)

—

Operating systemsDiffers

macOS, Linux and Windows (PowerShell or WSL2); the CLI and per-conversation Docker sandboxes need WSL on Windows

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

Desktop app and CLI for macOS, Linux and Windows; the Windows CLI runs natively in Git Bash, MSYS2 or PowerShell, or in WSL

—

Setup effortDiffers

Medium; install Node.js 24 and uv then the npm package, or run the Docker image, then add a model

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

Easy; download the desktop app, or install the CLI with a one-line script or Homebrew, then pick a provider

—

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.

OpenHands vs OpenAI Codex CLI vs goose (as alternatives to Claude Code)
Figures from RepoQuarry, 22 Oct 2026. Sources: https://repoquarry.dev/compare?ids=openhands,codex-cli,goose&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
OpenHands: free software; does 6 of 6 Claude Code jobs
OpenAI Codex CLI: free software; does 5 of 6 Claude Code jobs
goose: free software; does 6 of 6 Claude Code jobs

- OpenHands: 91,499 GitHub stars, 740 commits in 12 weeks, licence MIT
- OpenAI Codex CLI: 130,321 GitHub stars, 3,490 commits in 12 weeks, licence Apache-2.0
- goose: 55,514 GitHub stars, 657 commits in 12 weeks, licence Apache-2.0

Where they differ:
- Runs on my machine?: OpenHands Yes; Agent Canvas and the agent server run on your machine by default, or on your own Docker host, VM or Kubernetes cluster; OpenAI Codex CLI Yes, a command-line agent that runs on your computer; cloud models run on OpenAI's servers unless you use --oss; goose Yes, desktop app and CLI run on your computer
- Code licence: OpenHands MIT; OpenAI Codex CLI Apache-2.0; goose Apache-2.0
- Commercial use: OpenHands Yes, MIT allows commercial use; OpenAI Codex CLI Allowed under Apache-2.0; goose Yes, Apache-2.0 allows commercial use
- Paid services needed?: OpenHands Not required with local models (LM Studio, Ollama, vLLM, SGLang); cloud model APIs and OpenHands Cloud are optional; 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; goose Not required with local models (Ollama, LM Studio, Docker Model Runner, Ramalama) or free tiers such as Groq; paid APIs are optional
- Hardware: OpenHands No requirements given for Agent Canvas itself; the recommended local model needs a 24GB GPU or an Apple Silicon Mac with 64GB memory; OpenAI Codex CLI Not documented in the README or CLI docs; goose No hardware requirements documented in the README or install docs (checked 2026-10-21)
- Operating systems: OpenHands macOS, Linux and Windows (PowerShell or WSL2); the CLI and per-conversation Docker sandboxes need WSL on Windows; OpenAI Codex CLI macOS, Linux and Windows (native PowerShell with a Windows sandbox, or WSL2); goose Desktop app and CLI for macOS, Linux and Windows; the Windows CLI runs natively in Git Bash, MSYS2 or PowerShell, or in WSL
- Setup effort: OpenHands Medium; install Node.js 24 and uv then the npm package, or run the Docker image, then add a model; OpenAI Codex CLI Easy; one-line install script, npm or Homebrew, then sign in with ChatGPT; goose Easy; download the desktop app, or install the CLI with a one-line script or Homebrew, then pick a provider

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. OpenHands/OpenHands ↗openai/codex ↗aaif-goose/goose ↗

OpenHands vs OpenAI Codex CLI vs goose

Stars over time

Notes for a video or post

Cookie preferences

Report a problem