CodeGPT: Chat & AI Agents

Abstracts 20+ AI provider APIs (OpenAI, Anthropic, Google, Mistral, Groq, DeepSeek, Azure, Bedrock, etc.) behind a single VS Code chat interface, allowing users to switch between models without changing workflow. Routes requests to selected provider's official API using user-supplied keys or CodeGPT's credit system, handling authentication, request formatting, and response parsing transparently.

Generates new code files or code snippets by accepting project context via #file-name syntax, allowing developers to reference specific files as context without manually copying/pasting. The agent mode creates files directly in the project workspace with user confirmation, using the selected AI model to synthesize code based on included context and natural language prompts.

Allows users to supply their own API keys for 20+ AI providers (OpenAI, Anthropic, Google, Mistral, Groq, DeepSeek, Azure, Bedrock, Nvidia, Cohere, Fireworks, Perplexity, Cerebras, Grok, etc.), enabling direct API calls without CodeGPT intermediary. Users configure API keys in extension settings, and CodeGPT routes requests to provider endpoints using user credentials. Supports any model available from configured provider.

Displays proposed code changes in a diff view before application, allowing developers to review modifications line-by-line and accept or reject changes. Used by /Fix, /Refactor, and agent file creation features to show what will change before committing. Integrates with VS Code's native diff viewer for familiar UX.

Enables AI agent mode that can create new files, modify existing files, and perform project-level operations based on natural language instructions. Agent analyzes project structure and context, then executes file operations directly in the workspace. Smart Diff preview shows changes before application, and user confirmation is required (mechanism undocumented).

Analyzes selected code or entire files for bugs, logic errors, and potential issues, then generates fixes with explanations. The /Fix command sends code to the selected AI model, which identifies problems and proposes corrections. Smart Diff preview shows proposed changes before application, allowing developers to review and accept/reject modifications.

Generates human-readable explanations of selected code or entire functions using the /Explain command, breaking down logic, identifying patterns, and clarifying intent. Also provides /Document command to auto-generate documentation (docstrings, comments, README sections) based on code analysis, using the selected AI model to synthesize descriptions from code structure and context.

Analyzes selected code and suggests refactoring improvements using the /Refactor command, targeting readability, maintainability, and adherence to best practices. The AI model identifies code smells, suggests design pattern applications, and proposes structural improvements. Smart Diff preview shows refactored code before application.

Generates unit tests for selected functions or entire files using the /Unit Testing command, analyzing code structure and logic to create test cases covering common scenarios, edge cases, and error conditions. The AI model synthesizes tests in the project's testing framework (Jest, pytest, JUnit, etc.) based on code analysis and context.

Provides a chat sidebar in VS Code where developers can ask questions, request code generation, and discuss code with the selected AI model. Supports #file-name syntax to include specific files as context, allowing the model to understand project structure and provide relevant answers. Chat maintains conversation history within a session, enabling multi-turn interactions.

Provides inline code completion suggestions as developers type, using the selected AI model to generate context-aware completions based on surrounding code, file context, and project patterns. Integrates with VS Code's IntelliSense system to offer completions alongside built-in suggestions, allowing developers to accept or dismiss AI suggestions.

Enables use of locally-hosted AI models through integration with Ollama, LM Studio, and Docker, allowing developers to run inference without sending code to external APIs. Users configure local model endpoints in CodeGPT settings, and the extension routes requests to local endpoints instead of cloud providers. Supports any model compatible with these platforms (Llama, Mistral, etc.).

Provides access to proprietary AI models (Claude Opus 4.6, GPT-5, Gemini 2.5 Pro) through a credit-based subscription system, where users purchase credits and consume them per API call. No API key required for credit-based access — users sign into CodeGPT account and credits are deducted per request. Pricing is transparent per-model, with different credit costs for different models.