RunVSAgent
Run selected VS Code coding agents and extensions inside JetBrains IDEs.
- Source repo
- wecode-ai/RunVSAgent
- Stars
- ★ 712
- Last updated
- 1y ago
- License
- Apache-2.0
- Primary language
- Kotlin
- FA score
- 39/100 · Major gaps
At a glance
- How it runs
- Works with
- Platform-specific
- Cost
- Free software; you pay for model usage
- Setup effort
- Medium · a few setup steps
- You'll need
- Typical use
- A Java engineer using IntelliJ IDEA who wants to use Roo Code without moving their project workflow to VS Code.
- Not a fit if
- Developers who do not use JetBrains IDEs or run versions below 2023.1
- Teams needing a standalone CLI or a hosted agent service
- Maintenance
- No commits for 6+ monthslast commit 2025-10-29latest release 0.2.5 (2025-10-30)
- Source review
- 39/100 · Major gaps 3 safety controls not found
What does this agent do, and when should you use it?
RunVSAgent is a cross-IDE integration tool for running VS Code-based coding agents and extensions in JetBrains products such as IntelliJ IDEA, WebStorm, and PyCharm. Its architecture combines a Kotlin JetBrains Plugin with a Node.js Extension Host, communicating through RPC over Unix Domain Sockets or Named Pipes. The Extension Host supplies a VSCode API Layer, Agent Manager, and WebView support for the listed agents: Roo Code, Cline, and Kilo Code. It is delivered as a JetBrains Marketplace plugin, a ZIP release, or a source build. It fits teams that want to keep a JetBrains-centered development environment while using these specified VS Code agent integrations.
The JetBrains Plugin provides IDE integration, UI Integration, and an Editor Bridge, then communicates by RPC with the Node.js Extension Host. The host includes main.ts, extensionManager.ts, rpcManager.ts, and webViewManager.ts, alongside the VSCode API Layer, Agent Manager, and WebView support. This bridge is intended to run VS Code coding agents within a JetBrains IDE; the README names Roo Code, Cline, and Kilo Code. Cline is specifically described as being able to create or edit files, execute commands, and use the browser with permission at every step; that description is evidence for Cline, not a blanket guarantee for every supported agent.
- A Java engineer using IntelliJ IDEA who wants to use Roo Code without moving their project workflow to VS Code.
- A JavaScript or TypeScript team working in WebStorm that needs to bring Cline into its existing IDE.
- A Python developer in PyCharm who wants to run Kilo Code from the same IDE.
- A team standardizing across PhpStorm, RubyMine, CLion, GoLand, DataGrip, Rider, or Android Studio while adopting VS Code-oriented coding agents.
- A contributor debugging the bridge locally by running npm run dev in extension_host and ./gradlew runIde in jetbrains_plugin.
How do you install or deploy this agent?
Recommended: in a compatible JetBrains IDE, open Settings/Preferences → Plugins, search Marketplace for “RunVSAgent,” select Install, and restart when prompted. Alternatively, download the ZIP from GitHub Releases, choose Settings/Preferences → Plugins → the gear menu → Install Plugin from Disk..., select the ZIP, and restart. Source builds require Node.js 18.0+, a JetBrains IDE 2023.1+, Git, and JDK 17+: run git clone https://github.com/your-org/RunVSAgent.git, enter RunVSAgent, then run ./scripts/setup.sh and ./scripts/build.sh. The built plugin is placed in jetbrains_plugin/build/distributions/. The supplied material does not document how to install, configure, or first launch Roo Code, Cline, or Kilo Code after the plugin is installed, nor does it state required credentials.
How do you use this agent?
After installation and IDE restart, the README states that Roo Code, Cline, and Kilo Code can run in JetBrains IDEs, but it does not provide a menu path, configuration keys, extension acquisition procedure, or a first copyable agent invocation. A first agent run therefore cannot be verified from the supplied material. For development, run npm install followed by npm run dev in extension_host, then run ./gradlew runIde in jetbrains_plugin.
What are this agent's strengths and limitations?
- Uses a purpose-built Kotlin JetBrains Plugin plus Node.js Extension Host architecture to bridge JetBrains IDEs and the VS Code extension ecosystem.
- Explicitly uses RPC over Unix Domain Sockets or Named Pipes for local inter-process communication.
- Documents support across a broad set of JetBrains products, including IntelliJ IDEA, WebStorm, PyCharm, CLion, GoLand, Rider, and Android Studio.
- Names Roo Code, Cline, and Kilo Code as supported agents and includes WebView support in the documented architecture.
- Its operating boundary depends on the JetBrains IntelliJ Platform and Node.js, rather than being a standalone CLI or hosted agent service.
- It requires JetBrains IDE 2023.1+; source builds additionally require Node.js 18+, JDK 17+, Git, npm/pnpm, Gradle, and shell scripts.
- The material does not document post-install configuration, how the agent extensions are obtained, a first invocation, or credential setup.
- A known-issues document is referenced but its contents are not supplied, so common failure modes, limitations, and recovery guidance cannot be assessed.
How does this agent compare with similar options?
Compared with running these coding agents directly in VS Code, RunVSAgent is positioned as a bridge that brings specified VS Code agents and extensions into JetBrains IDEs through a JetBrains Plugin, Node.js Extension Host, and VSCode API Layer. No feature or performance benchmark is provided.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| RunVSAgent This agent | 39 · Major gaps | IDE extensionFree + model costs | ★ 712 | 1y ago | Kotlin | — |
| Kilo Code — The Open-Source All-in-One Coding Agent | 61 · Some gaps | IDE extensionFreemium | ★ 28k | 1d ago | TypeScript | — |
| Cline | 60 · Some gaps | CLIFree + model costs | ★ 72k | today | TypeScript | OpenAI API · Claude API |
| CC GUI (Claude, Codex and More) | 55 · Major gaps | IDE extensionFree + model costs | ★ 7.7k | 5d ago | Java | Codex · Claude Code |
How does FollowAgents rate this agent?
Why each dimension lost points
The source binds the extension host to a temporary port on 127.0.0.1, showing limited local exposure. The README says Cline asks permission at every step, but that statement concerns a supported downstream agent; the packet does not show RunVSAgent enforcing confirmations, so least privilege and confirmation each score 1. The architecture diagram and entry point describe the basic communication among the JetBrains plugin, extension host, and VSCode agents, earning 1 for data-flow transparency. There is no evidence of sensitive-data handling, secret protection, or dependency security review, so those criteria score 0. Process startup and termination are shown, but no rollback or recovery mechanism is documented; external effects score 1 and rollback 0. Copyright headers and the Apache license provide traceable attribution, scoring 2.
The entry point uses development identifiers and hard-codes Roo Code activation, while the README describes generic compatibility with multiple agents; implementation and product description only partly align, so self-consistency scores 1. The README lists Node.js, JDK, and IDE prerequisites and npm setup, but the packet has no dependency lock or availability evidence, so dependency availability scores 1. Connection, initialization, and loading failures are logged to the console, but user-facing recovery guidance is limited, so failure messages score 1.
The README identifies JetBrains IDE users and several development scenarios, and lists multiple IDEs and agents, scoring 2 for audience and scenarios. It does not clearly define permission, support, or compatibility boundaries, so capability boundaries score 1; no precise applicability trigger is shown, so trigger precision scores 1. IDE version, Node.js, and JDK requirements and JetBrains installation steps are provided, scoring 2 for environment fit.
The README covers features, architecture, installation, project structure, issue reporting, and contribution guidance, scoring 2 for information architecture. Marketplace, release package, and source installation steps are fairly clear, though the clone example uses a your-org placeholder URL, so install notes score 2. Names such as RunVSAgent, extension host, and JetBrains plugin are generally understandable, with some mismatch between generic documentation and the sampled implementation, so naming stability scores 1. The README points to a known-issues document whose contents are absent from the packet, and provides no FAQ or concrete usage example, so examples and FAQ score 1. Apache-2.0 metadata, the full LICENSE text, and README statement agree, scoring 3 for license. The packet contains no version history or changelog, scoring 0. The README identifies WeCode-AI Team, GitHub Issues, and a website as maintenance responsibility and contact paths, scoring 2.
The goal of bringing VSCode agents into JetBrains IDEs and the supported IDE/agent lists indicate practical utility, but the packet does not show a user-inspectable result format or usage output, so output usability scores 1. Using VSCode agents across IDEs is a clear added value, scoring 2. Building requires Node.js, JDK, Gradle/npm, and both the plugin and extension host, while the packet gives no quantified cost or benefit evidence, so cost-benefit scores 1.
The README's installation requirements, architecture description, and license can be partly checked against the listed files, but compatibility and 'seamless' operation lack supporting implementation detail or corroboration, so claim traceability scores 1. The packet includes README, entry point, CLI, and LICENSE, allowing limited cross-checking of the stack and licensing, but no tests or other sources corroborate functional claims, so cross-source corroboration scores 1. The README separates support claims from installation requirements, and the entry point confirms some static facts; however, the packet does not fully distinguish broad compatibility claims from demonstrated capabilities, so fact-inference separation scores 1.
- Not found in source: sensitive-data handlingUse dedicated, low-privilege, revocable API keys — never production credentials — and keep secrets out of logs.
- Not found in source: dependency securityPin versions and run a dependency audit (npm audit, pip-audit) before installing; prefer running it in a container.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- The sampled entry point hard-codes Roo Code activation; do not infer that every agent on the README list is available from that list alone.
- The README attributes step-by-step permission to the supported Cline agent; the packet does not show equivalent confirmation or sensitive-data protections in RunVSAgent itself.
- The static packet does not show compatibility validation, dependency security review, or rollback and recovery procedures.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
Release notes excerpt
* fix incompatible error with IntelliJ IDEA Ultimate IU-253.27864.23View on GitHub ↗
FAQ
Which IDEs are supported?
Which coding agents are supported?
Can it execute commands or change files?
Does it require payment or API keys?
Is RunVSAgent free?
Is RunVSAgent open source?
Is RunVSAgent safe to use?
Is RunVSAgent still maintained?
Who makes RunVSAgent?
Thanks — we use this to improve the page.