Zed vs goose vs OpenHands

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.

Zedzed-industries/zed

gooseaaif-goose/goose

OpenHandsOpenHands/OpenHands

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

3 of 6 jobs

6 of 6 jobs

All 6

Popularity and activity (from GitHub)

Stars

92,013Top

55,514

91,499

—

Gain this week

Unknown

—

Signal

Building history

—

Commits / 4 wk

453Top

139

345

—

Latest release

v1.25.2 · 2026-10-21

v1.55.0 · 2026-10-16

v1.30.0 · 2026-10-22Top

—

Commits / 12 wk

1,417

657

740

—

People committing / 12 mo

312+

77+

54+

—

Issues opened / closed, 30 days

413 / 484

314 / 237

464 / 367

—

Facts, with sources on each project page

Runs on my machine?Differs

Yes, a desktop editor installed on your computer

Yes, desktop app and CLI run on your computer

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

Hosted by the vendor

Code licenceDiffers

GPL-3.0-or-later for most code, with some Apache-2.0 components (LICENSE-GPL and LICENSE-APACHE)

Apache-2.0

MIT

—

Model weights licence

No separate model weights

—

Commercial useDiffers

Allowed; GPL-3.0 is copyleft, so changes you distribute must stay GPL

Yes, Apache-2.0 allows commercial use

Yes, MIT allows commercial use

—

Paid services needed?Differs

Editor is free; AI works with your own API keys or local models (Ollama, LM Studio, llama.cpp); Zed Pro is optional for hosted models and Zed edit prediction

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

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

Subscription

HardwareDiffers

64-bit OS; Windows needs a DirectX 11 GPU, Linux a Vulkan 1.3 driver, Macs from about 2015 on; local models need more

Native Rust desktop app and CLI; the LLM runs through the provider you configure (cloud API or local); no RAM, CPU or GPU figures documented

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

—

Operating systemsDiffers

macOS (10.15+, Intel and Apple Silicon), Windows 10 1903+ and 11, Linux x86_64 and Arm64; no web version

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

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

—

Setup effortDiffers

Easy; download installer, Homebrew, winget or a one-line Linux script, then add an API key or local model

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

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

—

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.

Zed vs goose vs OpenHands (as alternatives to Claude Code)
Figures from RepoQuarry, 22 Oct 2026. Sources: https://repoquarry.dev/compare?ids=zed,goose,openhands&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
Zed: free software; does 3 of 6 Claude Code jobs
goose: free software; does 6 of 6 Claude Code jobs
OpenHands: free software; does 6 of 6 Claude Code jobs

- Zed: 92,013 GitHub stars, 1,417 commits in 12 weeks, licence GPL-3.0-or-later for most code, with some Apache-2.0 components (LICENSE-GPL and LICENSE-APACHE)
- goose: 55,514 GitHub stars, 657 commits in 12 weeks, licence Apache-2.0
- OpenHands: 91,499 GitHub stars, 740 commits in 12 weeks, licence MIT

Where they differ:
- Runs on my machine?: Zed Yes, a desktop editor installed on your computer; goose Yes, desktop app and CLI run on your computer; OpenHands Yes; Agent Canvas and the agent server run on your machine by default, or on your own Docker host, VM or Kubernetes cluster
- Code licence: Zed GPL-3.0-or-later for most code, with some Apache-2.0 components (LICENSE-GPL and LICENSE-APACHE); goose Apache-2.0; OpenHands MIT
- Commercial use: Zed Allowed; GPL-3.0 is copyleft, so changes you distribute must stay GPL; goose Yes, Apache-2.0 allows commercial use; OpenHands Yes, MIT allows commercial use
- Paid services needed?: Zed Editor is free; AI works with your own API keys or local models (Ollama, LM Studio, llama.cpp); Zed Pro is optional for hosted models and Zed edit prediction; goose Not required with local models (Ollama, LM Studio, Docker Model Runner, Ramalama) or free tiers such as Groq; paid APIs are optional; OpenHands Not required with local models (LM Studio, Ollama, vLLM, SGLang); cloud model APIs and OpenHands Cloud are optional
- Hardware: Zed 64-bit OS; Windows needs a DirectX 11 GPU, Linux a Vulkan 1.3 driver, Macs from about 2015 on; local models need more; goose Native Rust desktop app and CLI; the LLM runs through the provider you configure (cloud API or local); no RAM, CPU or GPU figures documented; OpenHands No requirements given for Agent Canvas itself; the recommended local model needs a 24GB GPU or an Apple Silicon Mac with 64GB memory
- Operating systems: Zed macOS (10.15+, Intel and Apple Silicon), Windows 10 1903+ and 11, Linux x86_64 and Arm64; no web version; goose Desktop app and CLI for macOS, Linux and Windows; the Windows CLI runs natively in Git Bash, MSYS2 or PowerShell, or in WSL; OpenHands macOS, Linux and Windows (PowerShell or WSL2); the CLI and per-conversation Docker sandboxes need WSL on Windows
- Setup effort: Zed Easy; download installer, Homebrew, winget or a one-line Linux script, then add an API key or local model; goose Easy; download the desktop app, or install the CLI with a one-line script or Homebrew, then pick a provider; OpenHands Medium; install Node.js 24 and uv then the npm package, or run the Docker image, then add a model

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. zed-industries/zed ↗aaif-goose/goose ↗OpenHands/OpenHands ↗

Zed vs goose vs OpenHands

Stars over time

Notes for a video or post

Cookie preferences

Report a problem