terax-ai: Open Source IDEs & Code Editors

What is terax-ai?

Terax is a lightweight, open-source, terminal-first AI-native development environment (ADE) for developers who want a fast native workspace with agentic AI assistance, built on Tauri 2, Rust, and React 19, and released under the Apache-2.0 licence.

What it is

Terax is a desktop development environment that puts a native terminal at the centre of the workflow and layers a code editor, file explorer, source control panel, and web preview around it. The application is built on Tauri 2 and Rust with a React 19 front end, uses xterm.js with a WebGL renderer for the terminal and CodeMirror 6 for the editor, and occupies roughly 7-8 MB on disk. It runs on Windows, macOS, and Linux, and ships with no telemetry and no account requirement. An agentic AI side-panel works either against the user's own provider keys or against fully local models.

The concrete problem it solves is tool sprawl in the developer's daily loop. Rather than running a terminal emulator, a separate code editor, a Git GUI client with its own commit graph, and a browser tab for local dev servers as four disconnected programs, Terax consolidates them into one process with shared context. The AI side-panel can read files, attach selections from the explorer, and apply edits as diffs that are accepted or rejected hunk by hunk inside the same editor the user is already reading, which removes the copy-and-paste step between a chat window and the code.

Key capabilities

Block-based terminal using xterm.js with a WebGL renderer, multi-tab with background streaming, horizontal and vertical split panels, inline search, link detection, and true-colour output.
Native PTY backend through portable-pty, supporting zsh, bash, pwsh, fish, and cmd, with per-tab workspace environments on Windows that can target Local or any installed WSL distribution.
CodeMirror 6 editor with inline AI autocomplete, AI edit diffs accepted or rejected per hunk, opt-in language server support for diagnostics, navigation, completion, and formatting, plus Vim mode.
BYOK AI providers covering OpenAI, Anthropic, Google (Gemini), Groq, xAI (Grok), Cerebras, OpenRouter, DeepSeek, and Mistral, any OpenAI-compatible endpoint, and local or offline models through LM Studio, MLX, and Ollama.
Agentic workflow with plans, sub-agents, project memory via TERAX.md, file read, write, edit, multi-edit, grep, and glob tools, bash with approval gating, and background processes.
Composer prompt input that references files with @path and snippets with #handle, supports voice input, and accepts attachments from the explorer or the current selection.
Source control with hunk-level stage and unstage, commit on Cmd+Enter or Ctrl+Enter, push with upstream awareness, and a git history pane rendering a real commit graph with lanes for merges and branches.

Who uses it and how

Windows developers who treat WSL as a first-class workspace environment, assigning Local or a chosen WSL distro per terminal tab instead of wrapping a subprocess.
Developers orchestrating coding agents, spawning Claude Code in a terminal, inspecting its output, and sending follow-up work through approval-gated tools.
Teams and individuals working offline or on private code, running LM Studio, MLX, or Ollama locally so prompts never leave the machine.
Privacy-conscious users who want no telemetry and no account, including Linux users installing from the Arch AUR or the Nix flake.
Polyglot developers editing TypeScript, Rust, Python, Go, C/C++, Java, HTML/CSS, JSON, and Markdown in one workspace with rendered Markdown, image, video, audio, and PDF viewing.

Getting started

Installers for the latest release are published on the GitHub Releases page, and Terax auto-updates from there. Arch and AUR users can run yay -S terax-bin, and NixOS or Nix users can install the official flake with nix profile install github:crynta/terax-ai.

How it compares

No comparable or paid products are named in the facts provided for this entry. On the available record, Terax stands alone in this registry as a terminal-first AI-native development environment.

When to use it — and when not to

Terax is a desktop binary rather than a hosted service, so a self-hoster operates nothing extra: there is no server, database, or SMTP dependency mentioned, and the only external touchpoint is the auto-update feed on GitHub Releases. It is a poor fit for teams that need a browser-based IDE, shared remote sessions, or vendor support with a service-level agreement, because none of those are offered. The open issue count of 449 against 9,221 stars and 1,007 forks is a real signal that the project carries a substantial unresolved backlog, so anyone depending on it for critical daily work should check recent release cadence first.

project readme (upstream, from github) — read inline

Terax

Lightweight Terminal-first AI-native dev workspace.

Website · Docs · Website's source code

version downloads

Terax is a lightweight open-source terminal-first AI-native development environment (ADE) built on Tauri 2 + Rust and React 19. A native PTY backend with a WebGL renderer, an agentic AI side-panel that runs against your own keys or fully local models, plus a code editor, file explorer, source control with a git graph, and a web preview pane built in. About 7-8 MB on disk. No telemetry. No account.

Screenshots

_{Web preview of local dev servers}	_{Agentic AI workflow with edit diffs in the code editor}
_{Custom themes, presets, and background images}	_{Source control panel with git graph in history}
_{Block-based WebGL terminal with editor-like input panel}

Features

Terminal

xterm.js with WebGL renderer, multi-tab with background streaming
GPU-accelerated block-based terminal with editor-like command input
Native PTY backend via portable-pty (zsh, bash, pwsh, fish, cmd)
Split panels (horizontal and vertical)
Inline search, link detection, true-color
Drag files from the explorer or desktop into a terminal as shell-safe quoted paths
Per-tab workspace environments on Windows (Local, or any installed WSL distro)
Spaces restore tabs, working directories, and split layouts across launches

Code editor

CodeMirror 6 (supports all popular languages - TS/JS, Rust, Python, Go, C/C++, Java, HTML/CSS, JSON, Markdown, etc.)
Inline AI autocomplete with local model support
AI edit diffs, accept or reject hunk by hunk
Opt-in language server support with diagnostics, navigation, completion, formatting, and custom servers
Rendered Markdown plus image, video, audio, and PDF viewing
Vim mode
Built-in editor themes including Kanagawa, Catppuccin, Rosé Pine, Everforest, Dracula, Solarized, Nord, Tokyo Night, GitHub, and Xcode

Source control

Stage / unstage hunks, commit (Cmd+Enter / Ctrl+Enter), push with upstream awareness
Branch display including detached HEAD state
Git history pane with a real commit graph (lane rendering for merges and branches)
Commit search and filter, click through to the remote commit page

File explorer

Catppuccin icon theme
Fuzzy search, keyboard navigation, inline rename, context actions
Live updates when files change on disk
Attach files and selections directly to the AI side-panel

Web preview

Auto-detects local dev servers and opens them in a preview tab
External URL preview via a native child webview

Themes and customization

Custom themes built in-app, switch between bundled presets and your own
Create your own themes, share them or import from the community
Background images with adjustable opacity and blur
Editor theme is independent from the app theme

AI

BYOK providers: OpenAI, Anthropic, Google (Gemini), Groq, xAI (Grok), Cerebras, OpenRouter, DeepSeek, Mistral, plus any OpenAI-compatible endpoint
Local / offline: LM Studio, MLX, Ollama
Agentic workflow: plans, sub-agents, project memory via TERAX.md, file read / write / edit / multi-edit / grep / glob, bash with approval gating, background processes
Coding-agent orchestration: spawn Claude Code in a terminal, inspect its output, and send follow-up work through approval-gated tools
Composer: prompt snippets via #handle, files via @path, voice input, attach-to-agent from explorer or selection
Custom agents with their own system prompt and tool subset
Plan mode for multi-step work, generates and confirms before doing

Install

Latest installers are on the Releases page. Terax auto-updates from there.

Windows notes

Default shell detection: pwsh.exe (PowerShell 7+) -> powershell.exe (Windows PowerShell 5.1) -> cmd.exe.
WSL is a first-class workspace environment, not a wrapped subprocess.

Linux notes

Arch / AUR: yay -S terax-bin (or paru, etc.). Tracks the latest release.
NixOS / Nix: use the official flake - nix profile install github:crynta/terax-ai (non-NixOS), or import the flake and add inputs.terax.packages.${pkgs.system}.terax to environment.systemPackages (NixOS). The nixosModules.terax output is also available for a simpler setup.
AppImage: needs FUSE. Without it: ./Terax_*.AppImage --appimage-extract-and-run. On Wayland with rendering glitches, try WEBKIT_DISABLE_DMABUF_RENDERER=1. Otherwise the .deb / .rpm packages link against the system GTK stack and tend to be smoother.

Configure AI

Open Settings -> AI.
Pick a provider and paste your API key. For local inference, point Terax at your LM Studio / MLX / Ollama endpoint.
Keys are written to the OS keychain via keyring. They never touch disk or localStorage.

Build from source

Prerequisites

Rust (stable), https://rustup.rs
Node 22+ and pnpm
Tauri prerequisites for your platform, https://tauri.app/start/prerequisites/

Run

pnpm install
pnpm tauri dev          # development
pnpm tauri build        # production bundle

Checks

pnpm lint
pnpm check-types
pnpm test
cd src-tauri && cargo clippy --all-targets --locked -- -D warnings   # Rust lint (matches CI)
cd src-tauri && cargo nextest run --locked                           # or: cargo test --locked

Tech stack

Tauri 2, Rust, portable-pty, React 19, TypeScript, Vite, xterm.js, CodeMirror 6, Vercel AI SDK v6, Tailwind v4, shadcn/ui, Zustand.

Contributing

Issues and PRs are welcome! Feel free to open issues, suggest features, or submit pull requests. See CONTRIBUTING.md and the architecture docs for more details.

Code signing

Windows builds are signed with a free code signing certificate provided by SignPath.io, certificate by the SignPath Foundation.

License

Terax is licensed under the Apache-2.0 License. For more information on our dependencies, see Apache License 2.0.

Frequently asked questions

Is terax-ai free to use?

terax-ai is open source under the Apache-2.0 licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does terax-ai do?

Lightweight (7MB) Terminal-first AI-native dev workspace

What is terax-ai written in?

terax-ai is primarily written in TypeScript. Its source is publicly available at https://github.com/crynta/terax-ai, and it has 9,221 GitHub stars.