Show HN: Agentmux – iOS terminal and workspace built for CLI AI agents
Agentmux is an iOS terminal and workspace built for command‑line AI agents. It enables one‑tap launching of agents such as Shell, Claude, Codex, Gemini, OpenCode, and custom Pro agents from a single project menu. The tool was announced as a Show HN post targeting developers who need a portable CLI environment for AI models.
- ▪Agentmux provides a unified interface for launching multiple AI agents on iOS devices.
- ▪Supported agents include Shell, Claude, Codex, Gemini, OpenCode, and user‑defined Pro agents.
- ▪The launch menu is multilingual, showing instructions in English, Chinese, and Japanese.
- ▪The project was introduced on Hacker News as a Show HN submission for developers interested in AI‑driven CLI tools.
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,266 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Saxcave |
| Canonical URL | https://agentmux.saxcave.cc/ |
| Publication time | Thu, 23 Jul 2026 06:41:49 +0000 |
| Retrieval time | 2026-07-23T08:18:15.554Z |
| Last seen | 2026-07-23T08:18:15.554Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | gB5h1qzxeFnC |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
01 One-tap agent launch Agent 一鍵啟動 Agent 一键启动 Agent をすぐ起動 Start Shell, Claude, Codex, Gemini, OpenCode, and Pro custom agents from one project menu. Shell、Claude、Codex、Gemini、OpenCode，加上 Pro 自訂 Agent，全都從同一個專案選單啟動。 Shell、Claude、Codex、Gemini、OpenCode，加上 Pro 自定义 Agent，全都从同一个项目菜单启动。 Shell、Claude、Codex、Gemini、OpenCode、Pro のカスタムエージェントをプロジェクトメニューからすぐ起動。
Excerpt limited to ~120 words for fair-use compliance. The full article is at Saxcave.
Discussion
0 commentsMore from Saxcave
