ChatGPT’s Advanced Research Tool Now Features GitHub Integration for Coding Queries
OpenAI is upgrading its AI-driven “deep research” feature to include the capability to analyze codebases on GitHub.
On Thursday, OpenAI announced what it’s referring to as the first “connector” for ChatGPT deep research, the company’s tool that scours the web and other sources to create comprehensive research reports on a specific topic. Now, ChatGPT deep research can connect to GitHub (currently in beta), enabling developers to pose questions about a codebase and engineering documents.
The connector will be accessible to ChatGPT Plus, Pro, and Team users over the next few days, with support for Enterprise and Edu users coming soon, according to an OpenAI representative.
OpenAI’s ChatGPT Deep Research feature can now link to GitHub.
The GitHub connector for ChatGPT deep research launches as AI companies strive to enhance their AI-driven chatbots by creating ways to integrate them with external platforms and services. For instance, Anthropic recently introduced Integrations, which provides apps with a pathway to its AI chatbot Claude.
In the past, OpenAI offered a plugin capability for ChatGPT but phased it out in favor of custom chatbots known as GPTs.
“I often hear that users find ChatGPT’s deep research agent incredibly valuable and want it to connect to their internal sources in addition to the web,” OpenAI Head of Business Products Nate Gonzalez wrote in a blog post on LinkedIn. “[That’s why] today we’re introducing our first connector.”
Alongside answering questions about codebases, the new ChatGPT deep research GitHub connector allows users to break down product specifications into technical tasks and dependencies, summarize code structure and patterns, and learn how to implement new APIs with real code examples.
Techcrunch Event
Berkeley, CA | June 5
There is a risk of ChatGPT deep research hallucinating, of course — no AI model is completely free from occasionally fabricating information. However, OpenAI is marketing the new feature as a potential time-saver, not a replacement for experts.
An OpenAI spokesperson stated that ChatGPT will respect an organization’s settings, ensuring users only access GitHub content they are authorized to see and codebases that have been explicitly shared with ChatGPT.
OpenAI has been enhancing its tooling for assistive coding, recently rolling out an open-source coding tool for terminals called Codex CLI and updating the ChatGPT desktop app to read code from several developer-focused coding applications. The company views programming as a primary use case for its models. Notably, OpenAI has reportedly reached a $3 billion agreement to acquire the AI-powered coding assistant Windsurf.
In other OpenAI news on Thursday, the company launched fine-tuning options for developers looking to customize its newer models for specific applications. Developers can now fine-tune OpenAI’s o4-mini “reasoning” model using a method OpenAI refers to as reinforcement fine-tuning, which employs task-specific grading to enhance the model’s performance. Fine-tuning has also been made available for the company’s GPT-4.1 nano model.
Only verified organizations can fine-tune o4-mini, as stated by OpenAI. In contrast, GPT-4.1 nano fine-tuning is available for all paying developers.
OpenAI began restricting certain models and developer features behind a verification process in April, which necessitates organizations to submit an ID and other identity documents. The company asserts that this measure is vital to prevent misuse.
