by vlinx-io
VelaTerm = iTerm2 + Codex, The Best ADE for AI Coding
# Add to your Claude Code skills
git clone https://github.com/vlinx-io/VelaTermLast scanned: 8/13/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-08-13T05:41:33.833Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how VelaTerm compares with popular alternatives.
VelaTerm is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by vlinx-io. VelaTerm = iTerm2 + Codex, The Best ADE for AI Coding. It has 138 GitHub stars.
Yes. VelaTerm passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/vlinx-io/VelaTerm" and add it to your Claude Code skills directory (see the Installation section above).
VelaTerm is primarily written in TypeScript. It is open-source under vlinx-io on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh VelaTerm against similar tools.
No comments yet. Be the first to share your thoughts!
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
English | 简体中文
The best ADE. Not just a terminal. Not just an IDE.
Manage agent sessions like Codex. Split terminals like iTerm2. VelaTerm keeps both in one native app, and brings them to your browser and your phone.
Watch the intro video (2:55) · Download · User manual
Claude Code, Codex, OpenCode, Copilot, Cursor, Antigravity, Cline, Pi and more. Each one runs as a managed session, with live status, resume and custom launch arguments.
Follow an agent's plan, edits, commands and test results as a conversation, or switch the same session to the terminal view and work in its TUI.
Projects → groups → nested sub-groups → sessions. However many sessions you run, they stay in order. Every session is a real pseudo-terminal that keeps running in the background, and sessions can be split side by side.
Command and path suggestions appear as you type. Choose with the arrow keys, then press Tab to accept.
Session states follow the conversation live, in the session tree and the status bar, with a desktop notification when an agent finishes and waits for you.
While the agent works, the right panel keeps plan quota, context, tokens and system load in view.
An agent can hand a side task to a child session with vspawn: pick the agent, model and effort,
and give it its own worktree when needed. The child appears under its parent in the tree.
Sessions running Claude, Codex, OpenCode or Pi can search each other's conversations, ask about them, and send each other messages.
| Command | What it does |
|---|---|
vsearch |
Search every session |
vrefer |
Read a conversation, or ask about it |
vtell |
Message another session; with --steer the message joins the turn that is already running |
Plan / Execute mode splits a large task across several agent sessions, each with one job. The planner writes the plan, splits the work and reviews every result; the executors each build one part in its own worktree and report back.
Organize a session into the Session Knowledge Base, keep Markdown notes in local knowledge bases, and
search both at once. With vkb, an agent looks things up before it acts:
| Command | Looks up |
|---|---|
vkb memories |
Session knowledge |
vkb notes |
Local notes |
vkb explore |
The code graph, queried locally without calling a model |
See the notebook guide.
A WYSIWYG Markdown editor, a code editor and an image viewer, plus a built-in browser on desktop. All of them work on remote machines too.
Open Game Center from your workspace and play Pixel Wing with a keyboard, touch controls or a controller.
Remote access is built in: connect over SSH, or serve the app over HTTPS with end-to-end encryption.
Connect over SSH, open a pairing link, or sign in to your account and pick one of your devices.
Scan a QR code to connect. Browse the tree, read agent replies as they stream and answer them, and get a push notification when an agent needs you.
One native app on every desktop. On Windows, Git Bash comes bundled with the full installer. Built on Tauri 2: a small install that stays smooth under heavy terminal load.
| Platform | Architectures | Shells |
|---|---|---|
| macOS | Apple Silicon, Intel | zsh |
| Windows | x64, arm64 | PowerShell, Git Bash, WSL |
| Linux | x86_64, aarch64 | bash |
From the first command to the final review. Get the installer for your platform at velaterm.com/download, then start with the getting started guide.
| Layer | Choice |
|---|---|
| Desktop shel |