Price
$0 software; you run it
$0 software; you run it
$0 software; you run it
Free plan with limited AI use; Plus $8/month, Premium $30/month, Super $100/month, Ultra $200/month; third-party models billed separately by usage
source ↗ Code in an AI-first editor
No: No
No: No
Partial: Partly
Confirmed: Yes
Multi-line tab completion and next-edit prediction
No: No
No: No
Partial: Partly
Confirmed: Yes
Let an agent plan and edit across many files
Partial: Partly
Partial: Partly
Partial: Partly
Confirmed: Yes
Run terminal commands and tests from the agent
Partial: Partly
No: No
Partial: Partly
Confirmed: Yes
Ask questions about your whole codebase
No: No
No: No
Partial: Partly
Confirmed: Yes
Connect tools and data through MCP
Partial: Partly
Partial: Partly
Partial: Partly
Confirmed: Yes
Run agents in the cloud in the background
No: No
No: No
No: No
Confirmed: Yes
Jobs covered
3 of 7 jobs
2 of 7 jobs
6 of 7 jobs
All 7
Popularity and activity (from GitHub)
Stars
130,321
219,699Top
92,013
—
Gain this week
Unknown
Unknown
Unknown
—
Signal
Building history
Building history
Building history
—
Commits / 4 wk
892
986Top
453
—
Latest release
rust-v0.163.0 · 2026-10-15
v1.19.3 · 2026-10-16
v1.25.2 · 2026-10-21Top
—
Commits / 12 wk
3,490
2,164
1,417
—
People committing / 12 mo
377+
420+
312+
—
Issues opened / closed, 30 days
7371 / 1498
3742 / 4694
413 / 484
—
Facts, with sources on each project page
Runs on my machine?Differs
Confirmed: Yes, a command-line agent that runs on your computer; cloud models run on OpenAI's servers unless you use --oss
Confirmed: Yes, CLI and desktop app
Confirmed: Yes, a desktop editor installed on your computer
Hosted by the vendor
Code licenceDiffers
Confirmed: Apache-2.0
Confirmed: MIT
Confirmed: GPL-3.0-or-later for most code, with some Apache-2.0 components (LICENSE-GPL and LICENSE-APACHE)
—
Model weights licenceDiffers
Confirmed: No separate model weights
Partial: No single bundled model licence. OpenCode connects to models/providers; their individual terms apply.
Confirmed: No separate model weights
—
Commercial useDiffers
Confirmed: Allowed under Apache-2.0
Confirmed: Yes, MIT code
Confirmed: Allowed; GPL-3.0 is copyleft, so changes you distribute must stay GPL
—
Paid services needed?Differs
Partial: 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
Partial: Needs a model provider: local models via Ollama, LM Studio or llama.cpp, or a paid API
Partial: 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
Subscription
HardwareDiffers
Confirmed: 4 GB RAM minimum, 8 GB recommended; models run in OpenAI's cloud, so no GPU needed
Partial: No GPU needed when models run via the provider API; needs a modern terminal emulator and provider API keys; local models are optional and bring their own needs; no RAM figures documented
Confirmed: 64-bit OS; Windows needs a DirectX 11 GPU, Linux a Vulkan 1.3 driver, Macs from about 2015 on; local models need more
—
Operating systemsDiffers
Confirmed: macOS, Linux and Windows (native PowerShell with a Windows sandbox, or WSL2)
Confirmed: Windows, macOS and Linux; on Windows the docs recommend WSL for the CLI, and there is a Windows desktop app
Confirmed: macOS (10.15+, Intel and Apple Silicon), Windows 10 1903+ and 11, Linux x86_64 and Arm64; no web version
—
Setup effortDiffers
Confirmed: Easy; one-line install script, npm or Homebrew, then sign in with ChatGPT
Confirmed: Easy; one-line install script, npm, Homebrew, Chocolatey or Scoop, then add a model provider
Confirmed: Easy; download installer, Homebrew, winget or a one-line Linux script, then add an API key or local model
—