Price
$0 software; you run it
$0 software; you run it
$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
Partial: Partly
Partial: Partly
Partial: Partly
Confirmed: Yes
Run commands and tests
Partial: Partly
No: No
Partial: Partly
Confirmed: Yes
Use the agent inside VS Code or JetBrains
Partial: Partly
Partial: Partly
Partial: Partly
Confirmed: Yes
Connect tools and data through MCP
Partial: Partly
Partial: Partly
Partial: Partly
Confirmed: Yes
Write commits and pull requests
No: No
Partial: Partly
Partial: Partly
Confirmed: Yes
Run the agent headless in scripts or CI (GitHub Actions)
Partial: Partly
Partial: Partly
Partial: Partly
Confirmed: Yes
Jobs covered
5 of 6 jobs
5 of 6 jobs
6 of 6 jobs
All 6
Popularity and activity (from GitHub)
Stars
36,290
219,699Top
91,499
—
Gain this week
Unknown
Unknown
Unknown
—
Signal
Building history
Building history
Building history
—
Commits / 4 wk
0
986Top
345
—
Latest release
v2.0.0-vscode · 2026-06-19
v1.19.3 · 2026-10-16
v1.30.0 · 2026-10-22Top
—
Commits / 12 wk
0
2,164
740
—
People committing / 12 mo
78+
420+
54+
—
Issues opened / closed, 30 days
28 / 192
3742 / 4694
464 / 367
—
Facts, with sources on each project page
Runs on my machine?Differs
Confirmed: Yes, runs inside your IDE or terminal on your own machine
Confirmed: Yes, CLI and desktop app
Confirmed: 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
Confirmed: Apache-2.0
Confirmed: MIT
Confirmed: MIT
—
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: Apache-2.0 allows commercial use
Confirmed: Yes, MIT code
Confirmed: Yes, MIT allows commercial use
—
Paid services needed?Differs
Partial: Not required with local models via Ollama; cloud model API keys are optional
Partial: Needs a model provider: local models via Ollama, LM Studio or llama.cpp, or a paid API
Partial: Not required with local models (LM Studio, Ollama, vLLM, SGLang); cloud model APIs and OpenHands Cloud are optional
Subscription
HardwareDiffers
Confirmed: No stated needs for the extension or CLI; the Ollama guide asks for 8GB RAM minimum (16GB+ recommended) for local models
Unknown: No hardware requirements documented in the README or docs (checked 2026-10-21)
Partial: 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
Confirmed: Windows, macOS and Linux (VS Code and JetBrains); the CLI shell installer is macOS/Linux, npm install elsewhere
Confirmed: Windows, macOS and Linux; on Windows the docs recommend WSL for the CLI, and there is a Windows desktop app
Confirmed: macOS, Linux and Windows (PowerShell or WSL2); the CLI and per-conversation Docker sandboxes need WSL on Windows
—
Setup effortDiffers
Confirmed: Easy; install the extension from the VS Code Marketplace, then add a model
Confirmed: Easy; one-line install script, npm, Homebrew, Chocolatey or Scoop, then add a model provider
Confirmed: Medium; install Node.js 24 and uv then the npm package, or run the Docker image, then add a model
—