AI IDEs

AI-Native IDEs & Editors

Full standalone editors built from the ground up with AI at the core.

37 tools · 37 with full reviews · 13 free or open source · Updated Sep 7, 2026

Cursor Freemium

Anysphere Cursor is an AI-native code editor and fork of Visual Studio Code designed to handle complex, multi-file software development tasks. It centers the development workflow around autonomous agents that can index entire codebases, plan refactors, run terminal commands, and perform code reviews.

Cognition Devin is an autonomous software engineering agent that plans, writes, tests, and ships production code within an isolated cloud sandbox. It functions like a remote contractor that takes a ticket and delivers a finished pull request, rather than an interactive coding assistant.

ByteDance Trae is an AI-native IDE built by ByteDance as a fork of VS Code, offering both a traditional editor experience and agentic coding capabilities. It features an autonomous agent called SOLO that can plan, scaffold, and build full-stack applications from natural-language prompts.

Zed Industries Zed is a high-performance, GPU-accelerated code editor built in Rust, designed for low-latency editing and native-speed performance. It features deep AI integration via parallel agents and built-in real-time multiplayer collaboration, serving as a privacy-conscious, performant alternative to VS Code.

PearAI Freemium

PearAI PearAI is an open-source, AI-first code editor built as a fork of VS Code that integrates a modular suite of tools like Roo Code, Continue, and Mem0. It provides developers the flexibility to either use a managed subscription for premium models or leverage their own API keys and local models for full control.

Antigravity Freemium

Google Google Antigravity is an agentic development platform designed to manage and orchestrate multiple autonomous AI agents for complex engineering tasks. It operates as a standalone command center that supports project-based workflows, parallel agent execution, and integration with IDEs like VS Code.

Void Void was an open-source, privacy-first AI code editor forked from VS Code that allowed developers to connect directly to any LLM provider without a proprietary backend. As of June 2026, the project is officially deprecated, archived, and no longer receiving updates or maintenance.

Verdent Freemium

Verdent Verdent is an AI-native agentic coding platform designed for professional software development, focusing on plan-before-code workflows and parallel agent execution. It provides an environment where users can plan, verify, and execute tasks across multiple models in isolated workspaces to ensure reliable, reviewable output.

Pochi Pochi is an open-source AI coding agent designed as a VS Code extension that executes tasks like code generation and refactoring using your own LLM provider. It leverages Git worktrees to run parallel agents in isolated environments, ensuring context separation while performing complex development workflows.

Qoder Qoder is an autonomous development platform and IDE that uses agentic coding workflows to handle end-to-end tasks from planning to deployment. It supports a multi-model strategy, allowing users to choose between various frontier AI models or use automatic routing to balance quality and cost.

Z Code Freemium

Z ZCode is an agentic development environment (ADE) designed specifically for the GLM-5.3 model, organizing the coding workspace around an autonomous agent rather than a traditional IDE layout. It provides a unified environment for planning, executing, and verifying long-running coding tasks across files, terminals, and web previews.

Batrachian AI Toad is a unified terminal user interface designed to provide a cohesive, high-fidelity front-end for various AI coding agents. It integrates a fully functional shell with an agentic workflow, allowing developers to manage multiple AI tools like OpenHands and Claude Code seamlessly in one environment.

Nimbalyst Freemium

Nimbalyst Nimbalyst is an open-source visual workspace designed for developers to run and manage coding agents like Claude Code and Codex. It provides a centralized interface for parallel agent sessions, visual editing, and task management, keeping project context deeply linked.

Superset Freemium

Superset Superset is a desktop terminal for orchestrating multiple AI coding agents in parallel, each running within its own isolated Git worktree. It acts as an orchestration layer rather than a coding agent, allowing developers to manage complex, multi-feature tasks without branch or file conflicts.

archestra Freemium

Archestra Inc. Archestra is an enterprise AI platform that provides governance, security, and orchestration for AI agents, specifically focusing on the Model Context Protocol (MCP). It acts as a secure middle layer that manages data access, agent runtime, and observability, allowing organizations to deploy agents that interact with sensitive internal data.

codex-profiles Open Source

Chai Pin Zheng A Bash-based wrapper that manages multiple accounts by isolating CODEX_HOME directories and Electron user data for the ChatGPT desktop app. It allows users to switch between personal, work, and test accounts without copying or migrating authentication tokens.

Reasonix Freemium

ESEngine Reasonix is a DeepSeek-native, open-source AI coding agent engineered for long-running terminal sessions. Its architecture is built around prefix-cache stability to minimize token costs by maintaining context across turns.

MiniMax Code Freemium

MiniMax MiniMax Code is a desktop AI agent application for macOS and Windows designed for software development, automation, and remote collaboration. It functions as a local workspace that integrates chat, file operations, terminal sessions, a built-in browser, and multi-agent teams to manage complex, multi-step workflows.

Meta Muse Freemium

Meta Meta Muse Spark is a high-intelligence, multimodal reasoning model designed for agentic coding workflows. It powers Muse Code, a CLI-native coding agent that supports multi-agent orchestration, whole-repository context, and replayable event logs.

HKUDS DeepCode is an open-source, general-purpose autonomous coding agent designed for real-world software engineering that handles tasks from understanding and implementation to verification. It features a persistent, goal-driven loop architecture that allows the agent to continuously work, test, and repair code until a task is verified.

FWDAI Fletch is a macOS IDE designed for agentic engineering, providing a deterministic workspace to chain, sandbox, and supervise AI coding agents. It focuses on reliability by isolating each agent in its own clone and enforcing repeatable, gated workflows from planning through testing.

Factory AI Freemium

Factory Factory is an agent-native software development platform that deploys autonomous Droid agents to handle end-to-end engineering tasks like coding, testing, and security reviews. It provides an orchestrated system where AI agents operate within sandboxed environments to execute tasks, manage missions, and maintain repository readiness.

AntigmaLabs Ante is a self-contained, terminal-based coding agent built in Rust that features native local inference capabilities and multi-agent orchestration. It is designed to be a lightweight, cellular-native harness that operates with zero runtime dependencies and minimal system resource footprint.

unsloth Freemium

unsloth Unsloth is an open-source framework and desktop application designed to accelerate LLM training and inference on local consumer hardware. It provides a unified interface for fine-tuning, running models, and connecting agents, featuring optimizations that significantly reduce VRAM usage and increase training speed.

bb bb is an agentic IDE designed to function as a self-modifying software factory where AI agents can build and customize the environment itself. It acts as an orchestration layer, allowing users to coordinate multiple coding agents like Claude Code, Codex, and Cursor across a unified interface of threads, web, desktop, and CLI.

OpenChamber Free

OpenChamber OpenChamber is an open-source agentic development environment that functions as a supervision layer for the OpenCode SDK. It enables users to manage, automate, and review AI-driven coding tasks across desktop, web, and mobile platforms.

EGOIST Waku is a fast, native desktop application built in Rust and GPUI that provides a unified, local-first control plane for various coding agent CLIs. It normalizes disparate agent interfaces into a single, GPU-accelerated workspace that supports session management, transcripts, and Git-backed task checkpoints.

Jeremy Huang Jcode is an open-source, high-performance terminal coding agent harness written in Rust that focuses on extreme resource efficiency and parallelism. It enables developers to run dozens of concurrent agent sessions, coordinate multi-agent swarms with conflict detection, and maintain long-term context via a semantic memory graph.

Grok Bot Freemium

X Grok Bot is an always-on AI agent that runs on a persistent cloud-hosted Linux virtual machine, allowing it to interact with websites and software through a real browser and terminal. Unlike traditional chat-based assistants, it operates autonomously across your existing apps, learns workflows through demonstration, and persists even when your local devices are offline.

OpenRouter Ori is a command-line tool suite from OpenRouter consisting of Ori Harness, which auto-configures popular agent CLIs for optimal gateway use, and Ori Eval, an agentic testing framework. It allows developers to standardize agent performance, optimize token usage, and automatically select the best model for their specific application needs.

AgentOne Freemium

BestCodes AgentOne is a desktop-native AI automation agent that executes complex, multi-step tasks across thousands of apps and services. It functions as an autonomous workspace, allowing users to coordinate workflows across their software stack while maintaining local data privacy and multi-model support.

OneCLI Freemium

OneCLI OneCLI is an open-source sandboxed agent harness for teams that provides every employee with a secure, personal AI agent. It uses a network gateway to inject credentials on-demand, ensuring real API keys never touch the agent's sandbox environment.

Termy Open Source

Lasse Termy is a high-performance, GPU-accelerated terminal emulator built with Rust and the GPUI framework. It emphasizes a minimal, native experience across macOS, Linux, and Windows while providing modern features like tabs, splits, and tmux integration.

getpaseo Paseo is a self-hosted control plane and orchestration layer that enables users to manage multiple coding agents from a unified interface across desktop, mobile, web, and CLI. It connects to a local daemon on your machine, allowing you to run agents in isolated environments while maintaining full access to your local tools, git worktrees, and credentials.

OpenWorker Freemium

Andrew Ng OpenWorker is a local-first, open-source AI desktop coworker that executes multi-step tasks across local files and integrated applications. Rather than just providing chat responses, it delivers finished work like documents, reports, and calendar updates while requiring human approval for consequential actions.

Nick MonoCode is a desktop GUI for coding agents, providing a unified interface to run Claude Code, Codex, Cursor, and OpenCode if they are installed and logged in.

Emdash Open Source

generalaction Emdash is an open-source agentic development environment (ADE) that runs multiple coding agents in parallel, each isolated in its own Git worktree, with support for local and remote SSH projects and integration with various CLI agents like Claude Code, Codex, and Cursor.

FAQ

What are the best AI IDEs tools?

The most complete AI IDEs listings on ai.dosa.dev include Cursor, Devin, Trae. Every tool has a detail page with pricing, key features, and a verdict - see the full list of 37 tools below.

Are AI IDEs tools free?

13 of the 37 AI IDEs tools listed here are free or open source. Others offer freemium or paid plans - check each tool's detail page for current pricing.

How is this list curated?

ai.dosa.dev is manually curated from community submissions and editorial review. Entries are enriched with pricing, features, and reviewer notes, and the directory is updated continuously.