AI Coding Guides

A terminal-native AI coding agent from Anthropic that autonomously understands codebases, edits files, runs commands, and completes multi-step development tasks.

An official command-line AI coding assistant from OpenAI, built on the GPT model family and optimized for code generation and development workflows.

An open-source command-line AI coding assistant with deep Git integration—every change is auto-committed and can be rolled back in one step.

The world's first AI software engineer launched by Cognition Labs, capable of completing software engineering tasks end-to-end.

An autonomous AI software engineer agent developed by the Princeton NLP team, focused on resolving GitHub issues.

An open-source general-purpose AI software engineer agent platform, formerly known as OpenDevin.

An open-source autonomous AI agent framework capable of autonomously completing complex multi-step tasks.

ByteDance's AI-native IDE—the first of its kind in China—deeply integrates LLMs such as Doubao and DeepSeek, supporting natural-language interaction and multimodal collaboration.

A next-generation AI code editor from Anysphere with a built-in Composer agent that can run multiple coding tasks in parallel.

An AI-native IDE from Codeium with a built-in Cascade agent that deeply couples the terminal and editor.

A high-performance code editor built by the Atom team, with built-in AI features and real-time collaboration.

A free AI code completion tool that supports multiple IDEs and programming languages.

A privacy-focused AI code completion tool that supports local deployment and custom model training.

AWS's AI programming assistant, deeply integrated with AWS services and best practices.

An AI programming assistant from Sourcegraph, skilled at understanding large codebases.

AI tools built into the Replit platform, providing code completion, chat, deployment, and other features.

An AI coding assistant co-developed by GitHub and OpenAI, offering code completion, chat, and an Agent mode.

An open-source AI coding plugin that supports VS Code and the entire JetBrains suite, connects to any model, and lets you build a private AI assistant.

An open-source VS Code AI coding agent that autonomously edits multiple files, runs terminal commands, and browses the web.

A framework for orchestrating role-playing AI agents, enabling multiple agents to collaborate on complex tasks.

An open-source framework for building LLM applications, providing a complete toolchain and component library.

A data framework focused on RAG applications, connecting LLMs with private data.

An open-source LLM application development platform, providing visual building and deployment capabilities.

A tool for running large language models locally, simplifying model deployment and usage.

A high-performance LLM inference and serving engine, providing extreme inference speed.

An AI community platform providing models, datasets, applications, and a complete toolchain.

The technique of designing and optimizing LLM prompts to improve AI output quality.

An AI Agent is an intelligent system that uses an LLM as its brain and can autonomously perceive, reason, plan, and call tools to complete multi-step tasks.

A Large Language Model (LLM) is a deep neural network based on the Transformer architecture, containing tens of billions of parameters and trained on massive amounts of text.

A Skill is a capability flow, defined in Markdown, that an Agent can invoke; it builds on Function Calling and is more advanced than a single tool.

MCP is an open standard introduced by Anthropic in November 2024 that provides a unified interface for LLM applications to connect to external data and tools.