Question: Do you know of a code assistant that can be customized with different large language models and contexts for enterprise-scale development?

Tabnine is an AI-powered code assistant that accelerates and simplifies software development while keeping code private and secure. It generates AI code, automates tedious tasks, and offers AI chat support throughout the software development life cycle. Tabnine supports popular programming languages, libraries, and IDEs and is highly customizable. It allows users to create custom models trained on their own codebase, making it suitable for individual developers as well as large enterprise teams.

Another strong option is Continue, which embeds AI code assistants into developers' workflows to boost productivity and automate many tasks. It provides open-source extensions for VS Code and JetBrains and supports a variety of large language models. For larger-scale use, Continue Enterprise adds features like GitOps-based configuration, in-house LLM proxy management, and vector database management, making it ideal for enterprise environments.

CodeComplete offers a self-hosted solution with enterprise-ready functionality and user management to enhance developer productivity. It provides a suite of coding tools, including code generation, code chat, automated unit test generation, and refactoring. The tool ensures code and data protection through self-hosted options and uses permissively-licensed repositories to minimize legal risks, making it a secure and customizable choice for enterprise needs.

Refact is an open-source AI coding assistant that supports several Large Language Models (LLMs) including GPT-4 and Code LLama. It offers features like fast code completion, code improvement tools, and built-in chat. Refact is designed to protect user privacy with self-hosted versions and customizable privacy settings, making it a flexible and secure tool for enterprise-scale development.