PyCharm

Visual Studio Code is a free, open-source Microsoft-developed source-code editor and development environment for Windows, macOS, Linux, and the web, built from the Code - OSS repository. It supports code editing, navigation, code understanding, lightweight debugging, integration with existing development tools, and extensibility through extensions. It provides an environment for building with AI agents that plan, modify, and debug code, managing multi-agent workflows, hosting AI coding plugins such as Claude Code, and running workflows such as Spec Kit commands.

Lithe is a lightweight IntelliJ IDEA alternative for Java and Spring Boot development, designed to support AI-assisted coding workflows. It provides project browsing and editing, symbol navigation, search, Maven management, run configurations, breakpoint debugging, Git side-by-side diffs, local snapshot history, and database workspaces. Language servers, terminals, build tools, debuggers, and database helpers start on demand; the application also provides process-free basic completion and enables richer completion, hover, and semantic navigation through optional language services. It can detect entry points and run Spring Boot, Java, Maven, Gradle, npm, Cargo, Go, Python, Make, Docker Compose, Procfile, and shell projects. The macOS version is the current reference product, while Windows uses an independent React/Tauri implementation; both share command and contract definitions through a Rust core. It supports macOS 13 and later, Windows x64, and Java features require JDK 17 or newer.

PI-Desktop is a local-first desktop workspace for AI coding agents, built with Electron, a Rust host core, and the pi Agent Harness. It lets users open local projects, connect cloud or local models through providers such as OpenAI-compatible APIs, manage projects and long-running sessions, and review file changes and command output. Its architecture separates the React renderer, Electron desktop orchestration, Rust-managed permissions, filesystem access, SQLite persistence and secrets, and a pi Agent sidecar responsible for the agent loop, model interaction, and streaming. Agent, Plan, and Goal modes provide different approval boundaries; agents can read and edit files, run commands, and delegate exploration, implementation, research, testing, or review to background Subagents. The workspace supports MCP servers, Skills, installable Plugins, model and provider switching, session imports, notifications, context checkpoints, and a plugin marketplace. Conversations are stored locally as JSONL with a SQLite index, settings and logs remain on the machine, credentials use the operating-system keychain, and model requests go directly to the configured provider or endpoint. Plugin processes are permission-gated and isolated from the renderer, but plugins remain user-trusted code rather than a complete operating-system sandbox. It is an early-preview cross-platform application distributed for macOS, Windows, and Linux under the GNU Lesser General Public License v3.0.

Kiro is a proprietary agentic integrated development environment and command-line interface from Amazon Web Services. It supports specification-driven development, steering files, hooks, and cloud deployment, and uses Anthropic models through Amazon Bedrock.