Best tools for Refactoring

High-performance Rust JavaScript toolchain

Oxc is a high-performance collection of JavaScript and TypeScript tools written in Rust by the VoidZero team. It includes a parser, linter, formatter, transpiler, minifier, and module resolver that run 50x faster than their JS equivalents. Oxc powers Rolldown and integrates with Vite, forming the backbone of a unified Rust-based toolchain. With 20K+ GitHub stars and MIT license, it provides drop-in replacements for ESLint, Prettier, and Babel with dramatic speed gains.

Markdown WYSIWYG editor with live preview

TOAST UI Editor is a full-featured Markdown and WYSIWYG editor by NHN that supports GFM standard syntax with extensible chart and UML rendering. It offers dual editing modes with seamless switching, live preview with scroll sync, syntax highlighting, and a plugin architecture for adding color pickers, table merging, code highlighting, and diagram support. The editor ships with React, Vue, and vanilla JavaScript wrappers and supports 20+ languages.

Component toolkit for live code playgrounds

Sandpack is a component toolkit by CodeSandbox for building live-running code editing experiences directly in the browser. It bundles a full in-browser JavaScript bundler, CodeMirror editor, and preview pane into embeddable React components with npm dependency support, hot module reloading, and error overlays. Sandpack powers the interactive examples on the official React documentation and supports templates for React, Vue, Svelte, and vanilla JavaScript.

Full-lifecycle AI agent optimization and monitoring

CozeLoop is an open-source AI agent optimization platform from ByteDance's Coze ecosystem providing full-lifecycle management from development to production monitoring. It enables developers to debug agent prompts, evaluate agent performance across test cases, optimize reasoning processes, and monitor deployed agents in real-time. Built on Go and React with SDKs for Go, Python, and Node.js, CozeLoop is designed for enterprise-grade AI agent development and operation.

Plan-first AI coding agent that designs before implementing

Traycer is a YC-backed AI coding agent that takes a plan-first approach to software development. It creates detailed implementation plans with architectural decisions and dependency analysis before writing code. The agent reasons about project structure and constraints to produce coherent, well-organized changes rather than incremental patches. Focused on reducing rework from poorly planned AI-generated code.

Open-source AI coding agent with self-hosted deployment option

Refact.ai is an open-source AI coding agent that handles engineering tasks end-to-end with code completion, refactoring, and context-aware chat. It ranks #1 on SWE-bench Verified among open-source agents. Supports self-hosted on-premise deployment, BYOK with 20+ LLMs, and RAG-powered codebase understanding. Available for VS Code and JetBrains IDEs with integrations for GitHub, Docker, and PostgreSQL.

Blazing-fast PHP linter, formatter, and static analyzer in Rust

Mago is a comprehensive PHP toolchain written in Rust that unifies linting, formatting, and static analysis into a single binary. It enforces PER-CS formatting standards, catches code smells with 100+ lint rules, and performs deep type inference for semantic analysis. Inspired by Clippy and OXC from the Rust ecosystem, it delivers performance orders of magnitude faster than PHPStan and Psalm while requiring no PHP runtime to execute.

Find unused files, dependencies, and exports in JavaScript and TypeScript projects

Knip is an open-source CLI tool that detects unused files, dependencies, devDependencies, and exports in JavaScript and TypeScript codebases. It analyzes the full dependency graph to identify dead code that accumulates over time — especially relevant for AI-generated codebases where unused artifacts pile up faster than manual cleanup can handle. With over 10,800 GitHub stars, it has become a standard code hygiene tool in the JS/TS ecosystem.

Use Neovim like Cursor with AI-driven code assistance and one-click apply

avante.nvim is a Neovim plugin that brings Cursor-style AI coding assistance to the Vim ecosystem. It provides inline code suggestions, AI chat with codebase context, one-click diff application, and multi-model support including Claude, GPT, Gemini, and local models. With 12,000+ GitHub stars and active development, it is the leading AI coding plugin for Neovim users who want IDE-level AI features without leaving their editor.

Rust-powered JavaScript linter that is 50-100x faster than ESLint

Oxlint is an extremely fast JavaScript and TypeScript linter built as part of the OXC (Oxidation Compiler) toolchain written in Rust. It runs 50-100x faster than ESLint by parsing and analyzing code in a single optimized pass without requiring any plugins or configurations. Oxlint ships with 520+ built-in rules covering correctness, performance, and style checks, and is designed to run alongside ESLint during migration. Part of Evan You's VoidZero initiative, OXC has over 20,000 GitHub stars.

Extremely fast Python linter and formatter written in Rust

Ruff is a Python linter and code formatter written in Rust by Astral that runs 10-100x faster than existing tools like flake8, isort, and Black. It implements over 800 lint rules from dozens of popular plugins in a single binary, handles auto-fixing for most violations, and includes a built-in formatter compatible with Black. Adopted by FastAPI, Hugging Face, Pandas, and Apache Airflow, Ruff has over 38,000 GitHub stars and processes entire codebases in milliseconds.

Non-agent approach to automated software engineering via localize-and-repair

Agentless takes a deliberate non-agent approach to LLM-powered software engineering. Instead of autonomous agents making tool calls, it uses a structured localize-then-repair pipeline: first narrowing down which files and functions are relevant, then generating targeted patches. Achieved competitive SWE-Bench results at $0.34 average cost per issue. Adopted by OpenAI for o3 evaluations. 3,000+ GitHub stars, MIT licensed. A counterpoint to the agent-heavy trend in AI coding tools.

Instant AI API documentation from code snippets

DevDocsAI is a fast-utility AI documentation generator where developers paste code snippets and receive structured API documentation in 30 seconds. It targets individual makers and small teams who need quick documentation for specific code segments without the overhead of setting up a full documentation platform, providing rapid turnaround for function and endpoint documentation.

AI-powered marketing-ready READMEs from code

PitchDocs is an AI documentation generator that scans codebases to produce marketing-ready READMEs, changelogs, and AI context files like llms.txt. It bridges the gap between raw source code and consumer-ready technical communication, targeting the growing need for high-quality README files that serve both human developers and AI agents accessing documentation.

IDE documentation that stays synced with code

Swimm uses AI to keep code documentation in sync with real-time code changes, providing interactive walkthroughs directly in VS Code and JetBrains IDEs. It solves the stale documentation problem by making docs part of the development workflow rather than a separate artifact, automatically detecting when code changes invalidate existing documentation and suggesting updates.

Developer-focused documentation with AI assistance

Archbee is a developer-focused documentation platform with AI assistance for writing technical guides, API documentation, and internal knowledge bases. Built specifically for engineering teams rather than general content writers, it provides specialized code blocks, team collaboration spaces, API reference generators, and version-controlled documentation alongside AI-powered writing suggestions.

AI documentation generator from code repositories

DocuWriter.ai creates technical documentation from code repositories by scanning files, understanding patterns, and generating structured documentation including API references, function descriptions, and architectural overviews. It supports batch processing for entire repositories, serving as a zero-to-one documentation tool for undocumented codebases that need initial documentation coverage quickly.

AI-powered Stripe-style API documentation

Theneo is a Y Combinator-backed tool that generates high-quality, Stripe-style API documentation in seconds using AI. It transforms OpenAPI specs, Postman collections, or raw code into interactive developer portals with code playgrounds, multi-language SDK examples, and beautiful visual design, helping API-first teams create professional documentation without spending weeks on manual writing.

AI documentation for legacy codebases

Kodesage is an AI platform designed for navigating and documenting legacy systems, consolidating knowledge from code, issue tickets, and wikis to generate function-level documentation. It creates AST-based code maps that help teams understand complex 20-year-old codebases in plain English, with on-premises and air-gapped deployment options for high-security enterprise environments.

ETL for LLMs — preprocess any document format

Unstructured is an open-source ETL library that preprocesses and transforms documents from diverse formats into clean, structured data ready for LLM ingestion and RAG pipelines. It handles PDF, HTML, Word, PowerPoint, and many other file types through partitioning, cleaning, and chunking operations. The library offers connector-based architecture for integrating with various data sources and destinations, making it a key component in document processing workflows for AI applications.

Get your documents ready for gen AI

Docling is an open-source document processing toolkit by IBM Research that converts complex documents into structured formats optimized for generative AI applications. It parses PDF, DOCX, PPTX, XLSX, HTML, images, audio, and LaTeX with advanced PDF understanding including layout analysis, reading order detection, and table structure recognition. Docling exports to Markdown, HTML, JSON, and DocTags, and integrates natively with LangChain, LlamaIndex, and other AI frameworks for RAG workflows.

Convert any file to Markdown for LLM pipelines

MarkItDown is a lightweight Python utility by Microsoft that converts files into clean Markdown optimized for LLM pipelines and text analysis. It supports PDF, Word, Excel, PowerPoint, HTML, images with OCR, audio with transcription, and text formats like CSV, JSON, and XML. The tool preserves document structure including headings, tables, lists, and links while keeping output token-efficient. It offers a CLI, a four-line Python API, Docker support, and a plugin architecture for extensions.

Opinionated code formatter for web projects

Prettier is an opinionated code formatter with 50K+ GitHub stars that enforces a consistent style by parsing and reprinting code with its own rules. Supports JavaScript, TypeScript, CSS, HTML, JSON, Markdown, YAML, GraphQL, and more. Eliminates style debates in code reviews by making formatting automatic and deterministic. Features minimal configuration by design, editor integration for format-on-save, and pre-commit hooks via husky. The de facto formatting standard for web development.

Pluggable JavaScript and TypeScript linter

ESLint is the standard open-source linter for JavaScript and TypeScript with 26K+ GitHub stars. Statically analyzes code to find problems, enforce coding conventions, and automatically fix issues. Features a pluggable rule architecture with 300+ built-in rules and thousands of community plugins for React, Vue, Angular, Node.js, and more. Flat config system in ESLint v9 simplifies configuration. Integrates with every major editor, CI/CD pipeline, and build tool in the JavaScript ecosystem.