惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

V
V2EX
P
Proofpoint News Feed
D
DataBreaches.Net
C
Check Point Blog
L
LangChain Blog
量子位
美团技术团队
Vercel News
Vercel News
人人都是产品经理
人人都是产品经理
N
Netflix TechBlog - Medium
V
Visual Studio Blog
Microsoft Security Blog
Microsoft Security Blog
博客园 - 【当耐特】
MongoDB | Blog
MongoDB | Blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
Last Week in AI
Last Week in AI
The GitHub Blog
The GitHub Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
U
Unit 42
腾讯CDC
M
MIT News - Artificial intelligence
Microsoft Azure Blog
Microsoft Azure Blog
Blog — PlanetScale
Blog — PlanetScale

Hacker News: Show HN

PurrrrrFocus: Pomodoro Timer App - App Store Workflow Engine — Multi-Step Orchestration for Bun RapidPhoto: Pro Photo Editor App - App Store GitHub - DheerG/swarms: Achieve extraordinary results with claude code across a variety of tasks SPICE simulation → oscilloscope → verification with Claude Code — Lucas Gerads Show HN: VCoding – A 5 MB native Windows IDE with no dynamic dependencies Show HN: LLMs don't hallucinate because they're bad at math, it's the format GitHub - Agent-FM/agentfm-core: AgentFM is a peer-to-peer network that turns everyday computers into a decentralized AI supercomputer. AgentFM lets you run massive AI workloads directly across a global mesh of idle CPUs and GPUs. Show HN: Tracking Top US Science Olympiad Alumni over Last 25 Years GitHub - Potarix/agent-hub: One place to talk to all your agents Show HN: Runtime security for AI agents(injection,tool abuse, data exfiltration) GitHub - dubeyKartikay/lazyspotify: Terminal Spotify client for macOS and Linux GitHub - the-banana-tool/king-louie: Easy to use GUI Personal AI Assistant. Win/Linux/Mac. Show HN I made my vacation rental bookable by AI agents–no Airbnb, 0% commission GitHub - basteez/jsf-autoreload: maven plugin to enable hot reload on jsf projects uvm32/hosts/host-gdbstub at main · ringtailsoftware/uvm32 GitHub - labsai/EDDI: Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus. GitHub - glitchnsec/fortyone-oss: AI Executive Assistant Platform Quickstart | Alien GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. GitHub - ocrbase-hq/ocrbase: 📄 PDF/IMG ->.MD/JSON Document OCR API for PaddleOCR and GLMOCR. Self-hostable. GitHub - impactjo/home-memory: MCP server that lets your AI assistant remember everything about your home. GitHub - Sets88/dbcls: DbCls is a powerful terminal database client that supports various databases GitHub - neptun2000/heor-agent-mcp GitHub - SeanFDZ/macmind: Single-layer transformer in HyperTalk for the classic Macintosh RollQuation: Math Puzzles - Apps on Google Play GitHub - dropbox/witchcraft Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis GitHub - opentalon/opentalon: OpenTalon is an open-source platform built from the ground up in Go as a robust alternative to OpenClaw LinkedIn™ 职位抓取工具 - Chrome 应用商店
GitHub - longyijdos/hi-shell: AI-powered zsh command gene...
longyijdos · 2026-06-20 · via Hacker News: Show HN

hi-shell logo

AI-powered zsh command generation with reviewable, risk-scored shell suggestions.

hi-shell demo

hi-shell turns natural language into shell commands and shows the result as ghost text in your current zsh line. Press Tab to accept the suggestion, edit it if needed, then press Enter yourself.

It is not an autonomous shell agent, terminal emulator, or chat UI. It keeps command generation inside your normal terminal workflow while leaving execution under your control.

✨ Why hi-shell

Shell commands are often easy to describe and annoying to spell out. hi-shell handles the translation without taking over the terminal.

  • Stay in zsh instead of switching to a chat window.
  • Review every generated command before it can run.
  • Accept suggestions into the real command line, not a separate UI.
  • Revise a suggestion or ask what it does before running it.
  • Block clearly catastrophic commands by default.

⚡ Features

  • Natural-language command generation from your shell.
  • Ghost-text suggestions powered by zsh ZLE widgets.
  • Tab-to-accept flow; Enter only runs after you accept.
  • safe, warn, and blocked risk scoring.
  • Built-in support for OpenAI and DeepSeek APIs.
  • OpenAI-compatible provider configuration.
  • Optional shell context and filtered history.
  • Clean install and uninstall with one managed .zshrc block.

🚀 Install

curl -fsSL https://raw.githubusercontent.com/longyijdos/hi-shell/main/scripts/install.sh | sh
exec zsh

Make sure ~/.local/bin is in your PATH.

From source:

git clone https://github.com/longyijdos/hi-shell.git
cd hi-shell
./scripts/install.sh
exec zsh

Prerequisites for source installs: Go 1.22+, git, and zsh.

⚙️ Configure

OpenAI is the default provider:

export OPENAI_API_KEY="sk-..."

hi-shell config set provider openai
hi-shell config set openai.api_key_env OPENAI_API_KEY
hi-shell config set openai.model gpt-4.1-mini

DeepSeek is also supported:

export DEEPSEEK_API_KEY="sk-..."

hi-shell config set provider deepseek
hi-shell config set deepseek.api_key_env DEEPSEEK_API_KEY
hi-shell config set deepseek.model deepseek-v4-flash

Secrets stay in environment variables. The config file stores environment variable names, not API keys.

See Configuration for the full config reference.

🧭 Use

Type a natural-language request with the hi prefix:

Press Enter to generate a suggestion. If the command looks right, press Tab to accept it into your shell input line. Press Enter again to run it.

Use the prefix key, Ctrl-] by default, to revise, ask about, edit, or dismiss the current suggestion. See Usage and Keybindings for details.

🛡️ Safety

hi-shell never runs generated commands automatically.

The shell plugin only inserts a suggestion after you accept it. You still review the final command and press Enter yourself. Local risk scoring classifies suggestions as safe, warn, or blocked; clearly catastrophic commands such as rm -rf / are blocked by default.

See Risk Scoring for the detailed model.

📚 Documentation

🧹 Uninstall

hi-shell uninstall
exec zsh

To remove all hi-shell files, including config:

hi-shell uninstall --purge
exec zsh

📄 License

MIT