# Install & Configure: CodeGPT VS Code Plugin: In-Editor AI Chat with Codebase Context
## What This Is
CodeGPT is a VS Code extension that embeds AI chat directly in your editor sidebar with full codebase indexing. Unlike GitHub Copilot Chat, it supports multiple LLM backends (OpenAI, Anthropic, Ollama) and lets you create "agents" with custom system prompts per project.
Source: https://github.com/nickytonline/codegpt
## Before You Start
Scan my workspace and analyze:
- The project language, framework, and directory structure
- Existing agent configuration (check for .claude/, .codex/, CLAUDE.md, settings.json, commands/, skills/ directories)
- Whether this repository or a similar tool is already cloned or installed
Then ask me before proceeding:
1. Do I need to configure any service credentials for this plugin (database, API keys, etc.)?
2. Should this be project-scoped or global?
## Fetch the Source
Clone or inspect the repository to understand what needs to be installed:
```bash
gh repo clone nickytonline/codegpt
```
Review the README, directory structure, and any install instructions before proceeding.
## What to Implement
This is an **Agent Plugin** — typically an MCP server or capability bundle.
- Install any required npm/pip packages from the source repository
- Register the MCP server in `.claude/settings.json` under the `mcpServers` key with the correct command and args
- Configure any required environment variables or credentials
- Verify the server starts correctly by checking its expected output
## Additional Context
- Install CodeGPT from the VS Code marketplace, connect your preferred LLM API key, then use "Index Workspace" to give it full codebase context.
- Create a project-specific agent by clicking "New Agent" and pasting your project conventions — this persists across sessions unlike ad-hoc chat.
- Use @file references in chat to pull specific files into context: "@src/auth/middleware.ts explain the token validation flow".
## Guidelines
- Adapt everything to my existing project — do not assume a specific stack or directory layout
- Review any fetched code for safety before installing or executing it
- After setup, run a quick verification and show me a summary of exactly what was installed, where, and how to use it