LiteEditorAI — DevOps skill for Claude Code
Terminal-first workspace for supervising AI coding agents (Claude Code, Codex, Gemini): live agent status per project, code viewer + Git, 20+ tool modules (databases, Docker/Podman, Kafka, S3, SSH), p.
How to install LiteEditorAI
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open DanielLetto2020/LiteEditorAI and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What LiteEditorAI does
Terminal-first workspace for supervising AI coding agents (Claude Code, Codex, Gemini): live agent status per project, code viewer + Git, 20+ tool modules (databases, Docker/Podman, Kafka, S3, SSH), plugins your own agent writes, and an Android remote. Linux · Windows · macOS.
Alternatives in DevOps
- Appwrite — Appwrite® - complete cloud infrastructure for your web, mobile and AI apps 57.5k ★
- Render Deploy — Deploy applications to Render's cloud platform using Git-backed services 14.6k ★
- Ship Release — Systematic release workflow for RTK: build verification, version bump, changelog update, git tag, and push to 11.9k ★
README
▍ LiteEditorAI
Your agents write the code. This is where you watch them.
A terminal-first desktop workspace for developers who **supervise AI coding agents** (Claude Code, Codex, Gemini CLI, Qwen…) instead of typing every line themselves.
[](LICENSE) [](https://github.com/DanielLetto2020/LiteEditorAI/releases) [](#install) [](https://www.electronjs.org/) [](#status)
**English** · [Русский](README.ru.md) · [简体中文](README.zh.md) · [lite-editor-ai.ru](https://lite-editor-ai.ru)
*Three agents running in three projects. The tab renamed itself after the task the agent is on; the amber dots mark the two agents waiting for an answer, and the badge in the title bar counts them.*
[!NOTE] **Interface language: English, Russian or 简体中文** — switch it in *Settings → Interface language*, applied live without a restart. Languages are **pluggable files** (`locales/
.json`), so adding your own is one file and no build — see [Languages](#languages).
Why
Your editor was built around a person typing code. That person now spends most of the day **reading, steering and reviewing an agent** instead. The shape no longer fits:
- The center of the work is not a file — it's a conversation in a terminal.
- A full IDE is overkill for that. A bare terminal is blind: which agent finished? which one is stuck waiting for your answer? what did it just change in your files?
- Run agents in three projects at once and you lose track by lu
Related Skills
Relay Dev
Native macOS workspace manager for developers: projects, terminal sessions, AI CLI agents, dev services, Docke
Agentbox Client
Self-hosted browser workspace for Claude Code and Codex CLI, with Docker sessions, terminal, files, Git, and u
TerminalOs
macOS terminal that runs your servers — SSH, Docker, live metrics, SFTP and keys over one connection per host,
Ohmyharness
Run any coding agent in a Docker sandbox with your rules, skills and MCP servers already inside. Git worktree
Repo Control
One local dashboard for many Git repos — status, Docker, and your Codex/Claude/Gemini CLI sessions.
Deploy Status
SSH to 2anki.net, show pm2 status and recent server log tail
Related Agents
Ade
Agent sessions routinely outlast the machine that started them, and checking a Claude Code or Codex run from a
Agent Of Empires
Claude Code, OpenCode, Mistral Vibe, Codex CLI, Gemini CLI Coding Agent Terminal Session manager via tmux and
Developer Overview
code-container (container) creates isolated Docker environments for AI coding harnesses (Claude Code, OpenCode
