Why CC GUI Is the Perfect Companion for Running Claude Code and Codex Inside IDEA
The CC GUI plugin brings Claude Code and Codex CLI capabilities directly into JetBrains IDEA, offering a visual workbench that consolidates file references, diff viewing, token cost tracking, and MCP extensions, while comparing its lightweight ACP approach to full‑featured GUI solutions and outlining installation, configuration, and practical usage tips.
CC GUI – Integrated workbench for Claude Code and Codex
CC GUI (MIT‑licensed) is a JetBrains IDE plugin that embeds the CLI capabilities of Claude Code and Codex into a single panel. It provides:
Instant switch between Claude Code and Codex without changing plugins. @file support for attaching files, sending image‑based requirements and rolling back conversations.
Diffs displayed in IDEA’s Diff view with clickable links to the exact line.
History search, bookmarking, export and token‑cost statistics.
Built‑in slash commands and optional MCP server extensions.
Relation to the official ACP integration
JetBrains already supports Claude Code, Codex, Cursor, Gemini CLI and Kimi CLI via the Agent Client Protocol (ACP). ACP keeps the agent lightweight and CLI‑centric. CC GUI adds a full visual workbench with session management, image input, Skills and MCP support. Both can be installed simultaneously; users may use ACP for deep CLI work and switch to CC GUI when they need session history or cost analysis.
Installation (three steps)
Open Settings → Plugins, search for “CC GUI” and install the version with the highest download count (≈385 k downloads). The panel appears on the right side of the IDE.
Configure a provider using one of the following methods:
Create an Anthropic API key in the Anthropic console.
Import the local ~/.claude/settings.json file.
Use the community cc-switch tool.
Specify a custom third‑party endpoint.
Start a conversation from the right‑hand panel, e.g. “Analyze the current project structure”.
/plan mode – design before code
In /plan mode the AI scans the project, reads relevant services (e.g., PaymentService), extracts key points from integration documents and returns a design document that lists:
Files to modify.
New classes to add.
Required SDKs.
Signature handling and callback processing.
After reviewing the plan, switch to /agent to let the AI apply the changes. This two‑stage workflow avoids the high‑risk “code‑first” approach for payment, risk‑control or third‑party SDK integrations.
Token‑cost statistics
CC GUI shows per‑operation token consumption and an approximate USD cost. Sample measurements:
Simple chat (5 rounds) – ~15 K tokens.
Code review of ~100 lines – ~25 K tokens. /plan for a medium‑size project – ~40 K tokens.
Git integration: AI Commit and AI Review
AI Commit generates Conventional Commits messages from staged diffs (up to 5× faster than manual typing). AI Review runs an AI‑driven pre‑review that flags boundary conditions, null‑pointer risks, potential infinite loops and naming inconsistencies.
MCP server configuration
Enter the server address, headers and authentication once; the same mcp.json file is shared with Claude Desktop and Cursor. Installing the Chrome DevTools MCP extension enables the agent to drive front‑end testing directly from the browser.
Comparison with Qoder and CodeBuddy
Nature : CC GUI is a GUI shell for existing CLI agents; Qoder and CodeBuddy are independent AI coding agents.
Open‑source : CC GUI is MIT‑licensed; Qoder and CodeBuddy are closed‑source.
Model : CC GUI works with Claude, Codex and custom endpoints; the others use their own built‑in models.
Entry barrier : CC GUI requires an existing Claude or Codex subscription; Qoder offers a free tier after registration; CodeBuddy provides a free personal tier.
Strengths : CC GUI reuses existing subscriptions and is community‑driven; Qoder is optimized for the Java ecosystem; CodeBuddy integrates tightly with Tencent Cloud services.
All three can coexist; choose the one that matches the existing subscription or ecosystem.
Limitations
Effectiveness depends on three factors:
Accuracy of the supplied context (correct use of @file).
Clarity of project boundaries – the AI lacks business‑logic awareness.
Developer’s ability to review AI‑generated code; generation is easy, review is hard.
For newcomers, start with well‑scoped tasks such as adding unit tests, generating boilerplate, outlining module logic or converting screenshots to initial code.
Project repository
https://github.com/zhukunpenglinyutong/jetbrains-cc-gui
Signed-in readers can open the original source through BestHub's protected redirect.
This article has been distilled and summarized from source material, then republished for learning and reference. If you believe it infringes your rights, please contactand we will review it promptly.
IoT Full-Stack Technology
Dedicated to sharing IoT cloud services, embedded systems, and mobile client technology, with no spam ads.
How this landed with the community
Was this worth your time?
0 Comments
Thoughtful readers leave field notes, pushback, and hard-won operational detail here.
