Zed is a code editor built from scratch in Rust, designed to make full use of multiple CPU cores and your GPU. The result is an editor that feels noticeably faster than most alternatives at startup, during file navigation, and while typing. It comes from the team behind Atom and Tree-sitter, and that experience shows in how carefully each feature is implemented.

The AI integration goes well beyond a chat sidebar. Zed lets you run multiple agents in parallel across different projects, delegate tasks and watch changes happen live, and bring in models from providers like Anthropic, OpenAI, or others via ACP. If you prefer a lighter touch, the inline assistant lets you send selected code directly to a model for transformation without breaking your flow. Edit prediction, powered by Zeta (an open-weight model), anticipates your next edit as you type. Tools like Aider take a similar agentic approach, but Zed does it natively inside the editor itself.

Collaboration is built in at a deep level. You can code with teammates in real time, share your screen and project, and chat without leaving the editor. Remote development is also supported: the UI runs locally while the actual codebase lives on a remote server.

Key capabilities include:

• Multibuffer editing: compose excerpts from across the codebase into one editable surface
• Native Git support: stage, commit, diff, pull, and push without plugins
• Debugger: built on the Debug Adapter Protocol with multi-language support
• LSP support: full language server integration for diagnostics, completions, and more
• Vim and Helix modes: first-class modal editing with text objects and marks
• Built-in REPL: run code interactively through Jupyter kernels
• Dev Containers: consistent environments across machines
• Extensions ecosystem: hundreds of extensions for language support, themes, and tooling

Zed targets developers who've felt the sluggishness of Electron-based editors and want something that keeps up with how fast they think. It's a strong alternative to editors like CodeEdit for macOS users who want a native feel, but with broader platform support (macOS, Linux, and Windows) and a more mature feature set. The combination of raw speed, real-time collaboration, and deep AI tooling in a single editor is what makes it stand apart.

CodeEdit is an exciting new code editor written entirely and unapologetically for macOS. Develop any project using any language at speeds like never before with increased efficiency and reliability in an editor that feels right at home on your Mac.

It is not meant to replace Xcode but rather supplement it for projects not intended for Apple platforms. We believe every type of developer deserves a great experience and excellent performance.

Key features:

• macOS Native: Harness the full power of your Mac, something only possible with our completely native architecture developed in Swift.
• Lightweight Yet Powerful: Designed to be lean with limitless potential.
• Completely Open Source: CodeEdit is developed for you by developers like you. Don't like something? Want a new feature? Just create an issue or submit a PR.
• Extensible & customizable: Make CodeEdit your own, tailored to your needs.
• Familiar & Intuitive User Interface: Our user interface is designed to be familiar for ease-of-use and productivity.
• Better tools to get the job done: Feel connected to the code you are writing with tools to keep you on track.

ForgeCode is a terminal-native AI coding agent that sits directly inside your ZSH shell. It's built for developers who want AI assistance without leaving the command line or abandoning their existing setup. Your custom aliases, Oh My Zsh plugins, and shell workflows stay intact. Type : and you're talking to ForgeCode.

What sets it apart from other AI coding tools is how it handles context. Rather than dumping your entire codebase into one prompt, ForgeCode uses a multi-agent architecture with specialized sub-agents for research, planning, and execution. Each agent works on minimal, relevant context, which keeps local models on track and results reliable.

Key capabilities:

• Model mixing per task. Use a thinking model to plan, a fast model to write code, and a large-context model for big files, all within a single session without restarting.
• Codebase understanding at scale. A context engine built for large repos, with fast tool corrections that prevent local models from drifting off course.
• Skills at scale. Handles thousands of skills without bloating the context window.
• Broad LLM support. Connects to hundreds of providers and models natively from the shell.
• Rigorous evaluation. Every change runs through thousands of evaluations across coding tasks and models before shipping.

ForgeCode ranks #1 on TermBench 2.0 with 81.8% accuracy, a benchmark designed specifically for terminal-based coding agents. It processes over 38 billion tokens and 24 million lines of code per day across its user base.

It's fully open source, with over 7,300 GitHub stars and 354 releases, backed by an active community. For teams already living in the terminal, it's a practical alternative to browser-based or IDE-embedded AI coding environments.