16 个仓库
AI-powered translation of source code logic into natural language descriptions.
Distinct from AI Coding Assistant Guidance: Existing candidates focused on model classification or tabular data, not source code logic explanation.
Explore 16 awesome GitHub repositories matching artificial intelligence & ml · Code Explanation. Refine with filters or upvote what's useful.
This project is an AI-powered IDE extension and LLM coding assistant that provides a conversational interface for generating, refactoring, and debugging code. It functions as an AI agent framework and a Model Context Protocol client, connecting AI models to external data sources and tools to automate complex development tasks. The system is distinguished by its use of autonomous AI agents capable of multi-step task execution, including the ability to read files, modify code, and run terminal commands iteratively. It supports recursive agent orchestration through subagent delegation and employ
Provides natural language explanations of selected blocks of code to help developers understand logic.
Intel XPU LLM Acceleration Library is a toolkit designed to accelerate large language model inference and finetuning on Intel CPUs, GPUs, and NPUs. It provides a distributed inference engine for scaling models across multiple accelerators, a multimodal model runtime for vision and speech tasks, and a low-bit model quantization tool for converting weights into INT4, FP8, and GGUF formats. The project features a parameter-efficient finetuning framework that enables model adaptation using QLoRA and DPO on Intel hardware. It distinguishes itself by providing specialized optimizations for Intel XP
Analyzes source code to generate plain English descriptions of the underlying logic.
CodeGeeX is an open-source code model and multilingual large language model designed to generate, translate, and complete source code across multiple programming languages. It functions as an AI coding assistant and a cross-lingual code translator that produces executable code and technical documentation. The project enables natural language programming by turning plain English descriptions into functional programs. It also provides the ability to convert source code from one programming language to another while preserving the original logic and functionality. The system covers a range of c
Translates complex source code logic into natural language explanations to provide automated documentation.
LLM4Decompile 是一个用于二进制到源代码翻译的工具集和框架。它利用大语言模型将机器代码转换为可读的源代码,并恢复编译后可执行文件的原始逻辑。 该项目包含一个专门的流水线,通过将源代码转换为汇编对来生成合成训练数据集。它提供了一个微调框架,用于在这些二进制到源代码数据集上优化深度学习模型,从而提高代码恢复的准确性。 该系统还具有细化反编译伪代码的功能。此过程侧重于恢复二进制文件的结构骨架和变量名,以提高反汇编逻辑的可读性。
Employs a language model to improve the readability and accuracy of existing decompiled pseudo-code.
Identifies errors in code and produces corrected versions alongside a description of the fix.
Marks a commit with the fix type to indicate a patch-level bug fix in the codebase.
CodeCompanion is a Neovim plugin that brings large language model capabilities directly into the editor, enabling turn-based conversations with AI models in a dedicated chat buffer. It provides a comprehensive interface for interacting with LLMs, supporting multiple providers through a flexible adapter system that can route requests to various hosted or local language model services. The plugin distinguishes itself through its extensive context-sharing capabilities, allowing users to send buffer contents, visual selections, git diffs, LSP diagnostics, terminal output, quickfix lists, and view
Sends selected code to an LLM to produce a plain-language explanation of how it works.
Documentation.js is a multi-purpose documentation tool that parses JSDoc annotations from JavaScript and TypeScript source files to generate formatted API documentation. It functions as both a documentation generator and a JSDoc linter, scanning source code for non-standard or incorrect annotations and returning human-readable warnings to enforce documentation quality. The tool operates through a pipeline-based architecture that parses JSDoc comments into an abstract syntax tree, validates annotations against style and correctness rules, and outputs documentation through interchangeable plugi
Submits a pull request with a tested implementation to add a missing feature or fix a bug in the project.
本项目是一个全面的 Python 编程教育材料合集,包括教程、练习与精选代码示例。它作为一个学习课程与软件工程工具包,利用 Jupyter Notebooks 将可执行代码与描述性教育文本相结合。 该仓库提供了构建大语言模型应用的实践指南,例如检索增强生成(RAG)系统、有状态 AI 代理与机器学习工作流。它通过提供结构化的代理编码工作流脱颖而出,涵盖了上下文窗口蒸馏、与提供商无关的模型路由以及模式强制的结构化输出。 这些材料涵盖了广泛的软件工程能力,包括使用分布式任务队列的异步编程、使用 REST API 的 Web 应用开发以及数据分析工作流。它还包括用于掌握面向对象设计、实现 CI/CD 流水线以及应用专业 Linting 与格式化标准的资源。
Provides detailed breakdowns of code logic to help users understand complex code blocks.
auto-dev 是一款 AI 原生软件工程工具和多代理开发平台,旨在自动化整个软件开发生命周期。它作为一个自主编排器,通过声明式代理链管理 AI 驱动的编码、测试和基础设施配置。该项目基于 Kotlin Multiplatform AI 框架构建,允许代理逻辑在不同的环境和设备界面上运行。 该平台实现了模型上下文协议,以与外部 AI 服务交换工具和项目信息。它通过使用检索增强生成管道和基于树的代码图分析脱颖而出,这些分析抽象语法树和调用链以压缩项目上下文并减少幻觉。交互式开发画布提供 UML 图、OpenAPI 规范和代码差异的实时同步。 功能领域涵盖自主软件开发,包括动态任务规划、迭代测试驱动修复和遗留代码迁移。该系统还处理 Docker 和 CI/CD 配置的基础设施即代码自动化、AI 驱动的代码审查,以及跨团队协调共享 AI 个性和提示规范。 核心逻辑使用 Kotlin Multiplatform 实现,以确保跨平台代理部署的一致性。
Troubleshoots errors and provides natural language explanations of source code logic and smells.
该项目是一个开发人员工具,作为人工智能驱动的数据库查询管理助手。它提供了一个交互式界面,用于在自然语言和结构化数据库代码之间进行转换,简化了编写、调试和维护复杂查询的过程。 该工具通过结合模式感知上下文注入脱颖而出,这使其能够将生成的查询与特定的表定义和关系元数据对齐。通过维护有状态的对话历史并利用大语言模型提示,它使用户能够迭代地优化查询,并接收考虑到其数据库环境特定逻辑和结构的解释。 除了核心翻译外,该工具还支持分析现有代码以识别语法错误,并提供复杂查询逻辑的通俗易懂的分解。它还包括用于格式化数据库代码和管理本地翻译日志历史记录的功能,以促进过去工作的重用。
Provides plain-English summaries and breakdowns of complex database query logic for better code understanding.
GLM-4.5 is a multimodal large language model and advanced reasoning system. It functions as an AI coding assistant, an autonomous AI agent, and a multimodal content generator capable of processing and generating text, images, audio, and video within a single unified system. The project is distinguished by its deep reasoning capabilities, utilizing chain-of-thought processing to solve complex mathematical, logical, and technical problems. It features an agentic architecture that allows for autonomous task execution, long-horizon goal planning, and the ability to interact with external tools an
Processes error messages and codebase context to locate bugs and generate precise architectural or logic fixes.
Gepetto is an IDA Pro plugin that integrates large language models directly into the reverse engineering workflow. It functions as a multi-provider LLM client, allowing users to explain decompiled functions, rename variables, and add comments to pseudocode, all while supporting multiple language model backends and a localized interface. The plugin distinguishes itself through a plugin-based architecture that abstracts multiple LLM providers behind a unified interface, enabling hot-swapping between providers and models without restarting IDA Pro. It also features a command-line interface bridg
Sends decompiled pseudocode to a language model and returns plain-English descriptions of what the code does.
Remix is a comprehensive blockchain development environment and Ethereum smart contract IDE. It provides a complete workspace for writing, compiling, deploying, and debugging smart contracts across simulated and public blockchain networks. The project distinguishes itself as a specialized toolchain for EVM debugging and analysis, offering opcode-level transaction stepping and state memory analysis. It also includes a dedicated zero-knowledge proof toolchain for compiling ZK circuits and generating cryptographic proofs, alongside an AI-powered coding assistant for code generation and explanati
Analyzes code blocks and compiler errors to provide natural language explanations and troubleshooting steps.
This project is a Git-based AI session tracker and context manager designed to record AI agent interactions, transcripts, and tool usage directly into Git repositories. It functions as a system for capturing and indexing the reasoning behind code changes, linking AI prompts and responses to specific code commits to preserve developer intent. The tool distinguishes itself by using Git as a primary storage layer for session metadata, utilizing shadow branches and checkpoints to track agent state without polluting the main commit log. It includes specialized capabilities for auditing AI contribu
Traces functions or files back to the original session to reveal the underlying purpose.
Granite Code Models is a family of transformer-based foundational models designed for software engineering and logical reasoning tasks. These models are trained on high-quality programming datasets to interpret natural language prompts and generate functional source code, explain complex logic, repair code defects, and produce technical documentation. The project distinguishes itself through specialized training methodologies that align model behavior with complex programming instructions and mathematical problem-solving. By utilizing chain-of-thought reasoning and instruction-tuned parameter
Analyzes code blocks to provide human-readable summaries that clarify underlying structure and logical flow.