Best AI Coding Assistants for Linux - Page 3

StarCoder and StarCoderBase are Large Language Models for Code (Code LLMs) trained on permissively licensed data from GitHub, including from 80+ programming languages, Git commits, GitHub issues, and Jupyter notebooks. Similar to LLaMA, we trained a ~15B parameter model for 1 trillion tokens. We fine-tuned StarCoderBase model for 35B Python tokens, resulting in a new model that we call StarCoder. We found that StarCoderBase outperforms existing open Code LLMs on popular programming benchmarks and matches or surpasses closed models such as code-cushman-001 from OpenAI (the original Codex model that powered early versions of GitHub Copilot). With a context length of over 8,000 tokens, the StarCoder models can process more input than any other open LLM, enabling a wide range of interesting applications. For example, by prompting the StarCoder models with a series of dialogues, we enabled them to act as a technical assistant.

Code Llama is a large language model (LLM) that can use text prompts to generate code. Code Llama is state-of-the-art for publicly available LLMs on code tasks, and has the potential to make workflows faster and more efficient for current developers and lower the barrier to entry for people who are learning to code. Code Llama has the potential to be used as a productivity and educational tool to help programmers write more robust, well-documented software. Code Llama is a state-of-the-art LLM capable of generating code, and natural language about code, from both code and natural language prompts. Code Llama is free for research and commercial use. Code Llama is built on top of Llama 2 and is available in three models: Code Llama, the foundational code model; Codel Llama - Python specialized for Python; and Code Llama - Instruct, which is fine-tuned for understanding natural language instructions.

Chat about your codebase and let your AI code assistant update the multiple files right in your favorite IDE! Automatically include all files that you have open in your editor in your next prompt with up to 128,000 tokens in AI context memory size. Let the AI code. You approve the multi-file patch, a part of it, or request any necessary changes. Codebuddy can scan your entire repository and generate a vector database from it. This allows Codebuddy to select files for you, or answer questions about your codebase if you're not familiar with it. This is an AI coding assistant that deeply understands your repository. Generate new files or change multiple existing files with a single prompt. Codebuddy will insert code automatically for you in the form of a familiar unified patch (diff). Take your AI coding to the next level with industry-leading multi-file support.

GPT Pilot is an open-source AI tool that acts as a full AI developer, capable of generating production-ready applications with minimal human input. Unlike simple code autocompletion tools, GPT Pilot can write complete features, debug code, communicate about issues, and even request code reviews. This tool aims to push the boundaries of AI-assisted software development by handling up to 95% of coding tasks, while leaving the final 5% to developers. It’s built to integrate with platforms like VS Code, enabling developers to collaborate seamlessly with AI in real-time.

gpt-engineer is an open-source platform designed to automate software development by enabling users to specify software requirements in natural language. The tool utilizes AI to generate and execute code based on user specifications, making the development process faster and more intuitive. gpt-engineer can also implement requested improvements and handle iterative development, allowing users to focus on high-level tasks rather than manual coding. Built with a terminal-based interface, it is ideal for developers seeking a customizable, hackable solution for experimenting with AI-assisted programming.

smol-developer is an open-source library that enables developers to integrate a powerful AI-powered "junior developer" agent into their applications. This agent uses natural language processing to generate, scaffold, and assist with the development of code. Unlike conventional approaches, smol-developer allows for a more interactive development process, where the AI agent iterates and refines the code based on feedback, making it ideal for building project-specific scaffolds and automating repetitive tasks. Developers can leverage this tool to speed up the development cycle, create customized codebases, and collaborate with AI on development tasks in real-time.

Factory.ai is an agent-native software development platform designed to automate and accelerate engineering workflows. It enables developers to delegate complex tasks like refactoring, migrations, and incident response to AI-powered agents called Droids. The platform integrates seamlessly into existing tools such as IDEs, terminals, and collaboration apps. Developers can continue using their preferred environments like VS Code, JetBrains, or command line interfaces. Factory.ai works across the entire development lifecycle, from coding to CI/CD pipelines. It is built with enterprise-grade security to protect data and intellectual property. Overall, Factory.ai enhances productivity by enabling AI agents to work alongside developers without disrupting workflows.

Leave Artificial Intelligence to AIXcoder. Leave Real Intelligence to Human. The offline version is released! Your code is safe on your computer locally. AiXcoder works in smooth locally with state of art deep learning model compression techniques. The models are trained with a massive amount of open source code. And adapted to several areas. A search window is seamlessly integrated into IDE with the ability to search open-source code on GitHub. Deep learning is used to filter high-quality code as search results. Search API usage and examples. Search similar code to avoid duplicated coding. Project Level Personalized Training: Train models on personal project and computer. Enterprise Level Customized Training: Train models on code base and enterprise server. Based on standard model, personalized and customized training will learn the patterns and rules in your proprietary code.

Mars is a free dev tool for building web and mobile apps out of micro-apps combining no-code and code interfaces. MarsX is a platform that is designed specifically for startups and aims to make their journey easier, bringing more power and flexibility by allowing them to reuse thousands of micro-apps from previous projects built on the platform.

71 handcrafted tools (generators, converters, encoders, etc...), 20 cheat-sheets and 65 code snippets for developers and designers, available in multiple platforms. DevBox works entirely offline, so you never have to worry bout sensitive data since it never leaves the app. All tools respond to your actions instantly, so you can always see the end result without delay. Plenty of viewers are there for you to quickly check out data in varius formats (CSV, JSON, JWT, etc). Formatters and converters are working as you type, download or copy is just one click away. DevBox has 20 cheat-sheets for codes, services and many CLI tools.

An open source, terminal-based AI coding engine that helps you complete large tasks, work around bad output, and maximize productivity. Plandex uses long-running agents to complete tasks that span multiple files and require many steps. It breaks up large tasks into smaller subtasks, then implements each one, continuing until it finishes the job. It helps you churn through your backlog, work with unfamiliar technologies, get unstuck, and spend less time on the boring stuff. Changes are accumulated in a protected sandbox so that you can review them before automatically applying them to your project files. Built-in version control allows you to easily go backwards and try a different approach. Branches allow you to try multiple approaches and compare the results.

The leading open-source AI code assistant. You can connect any models and any context to create custom autocomplete and chat experiences inside the IDE Remain in flow while coding by removing the barriers that block productivity when building software. Accelerate development with a plug-and-play system that makes it easy to get started and integrates with your entire stack. Become a leader in AI by setting up your code assistant to evolve as new capabilities emerge. Continue autocompletes single lines or entire sections of code in any programming language as you type. Attach code or other context to ask questions about functions, files, the entire codebase, and more. Highlight code sections and press a keyboard shortcut to rewrite code from natural language.

Mistral Code is an AI-powered coding assistant designed to enhance software engineering productivity in enterprise environments by integrating powerful coding models, in-IDE assistance, local deployment options, and comprehensive enterprise tooling. Built on the open-source Continue project, Mistral Code offers secure, customizable AI coding capabilities while maintaining full control and visibility inside the customer’s IT environment. It supports over 80 programming languages and advanced functionalities such as multi-step refactoring, code search, and chat assistance, enabling developers to complete entire tickets, not just code completions. The platform addresses common enterprise challenges like proprietary repo connectivity, model customization, broad task coverage, and unified service-level agreements (SLAs). Major enterprises such as Abanca, SNCF, and Capgemini have adopted Mistral Code, using hybrid cloud and on-premises deployments.

Sculptor is a coding agent environment from Imbue that embeds software engineering practices into an AI-augmented development workflow; it runs your code in sandboxed containers, spots issues (e.g., missing tests, style violations, memory leaks, race conditions), and proposes fixes that you can review and merge. You can launch multiple agents in parallel, each operating in its isolated container, and use “Pairing Mode” to sync an agent’s branch into your local IDE for testing, editing, or collaboration. Changes go back and forth in real time. Sculptor also supports merging agent outputs while flagging and resolving conflicts, and includes a Suggestions feature (beta) to surface improvements or catch problematic agent behavior. It preserves full session context (code, plans, chats, tool calls) so you can revisit prior states, fork agents, and continue work across sessions.

Decompute Blackbird is a platform that challenges the traditional centralized approach to artificial intelligence by decentralizing AI compute power. The platform enables teams to train task-specific AI models on their own data, directly where the data resides, rather than relying on centralized cloud services. This approach allows businesses to optimize their AI capabilities by giving different teams the ability to develop and train models more efficiently and securely. Decompute aims to scale enterprise AI by focusing on decentralized AI infrastructure, helping organizations better leverage their data without compromising privacy or performance.

Supermaven lets you write code 2x faster with AI. Chat with GPT-4o, Claude 3.5 Sonnet, GPT-4, and other leading models. Use hotkeys to quickly view diffs, apply changes, start conversations, and switch models. Easily attach recently edited files to your messages - Supermaven Chat links the model's code responses back to your original code to show diffs and apply changes. Fix errors by automatically uploading your code together with compiler diagnostic messages in a single click.

Build apps faster with ML-powered coding companion. Accelerate application development with automatic code recommendations based on the code and comments in your IDE. Empower developers to use artificial intelligence (AI) responsibly to create syntactically correct and secure applications. Generate entire functions and logical code blocks without having to search and customize code snippets from the web. Stay focused and never leave the IDE, with real-time customized code recommendations for all your Java, Python, and JavaScript projects. Amazon CodeWhisperer is a machine learning (ML)–powered service that helps improve developer productivity by generating code recommendations based on their comments in natural language and code in the integrated development environment (IDE). Accelerate frontend and backend development by empowering developers with automatic code recommendations. Save time and effort by using CodeWhisperer to generate code to build and train your ML models.