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

博客园_首页
量子位
D
DataBreaches.Net
博客园 - 司徒正美
J
Java Code Geeks
博客园 - 【当耐特】
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
aimingoo的专栏
aimingoo的专栏
B
Blog
The Cloudflare Blog
D
Docker
I
InfoQ
爱范儿
爱范儿
MongoDB | Blog
MongoDB | Blog
腾讯CDC
月光博客
月光博客
Hugging Face - Blog
Hugging Face - Blog
Microsoft Azure Blog
Microsoft Azure Blog
Vercel News
Vercel News
阮一峰的网络日志
阮一峰的网络日志
小众软件
小众软件
S
SegmentFault 最新的问题
GbyAI
GbyAI
有赞技术团队
有赞技术团队

Hacker News - Newest: "AI"

AI can't read an investor deck AI as an attorney? Student uses ChatGPT, Gemini to sue UW over alleged racial discrimination Hacking MCP Servers in AI Systems – The Rug Pull: Tool Changes After Approval GitHub - MeepCastana/KubeezCut: Free Web based video editor Can AI judge journalism? A Thiel-backed startup says yes, even if it risks chilling whistleblowers Coming soon: 10 Things That Matter in AI Right Now DARPA built an AI to fact-check enemy weapons claims What explains heterogeneity in AI adoption? When AI Meets Muscle: Context-Aware Electrical Stimulation Promises a New Way to Guide Human Movements - Department of Computer Science AI Changed How We Build. It Did Not Change What Matters. Linux rules on using AI-generated code - Copilot is OK, but humans must take 'full responsibility for the… Meta spins up AI version of Mark Zuckerberg to engage with employees Code Mode: Let Your AI Write Programs, Not Just Call Tools | TanStack Blog GitHub - Delavalom/graft: Go framework for building AI agents. Type-safe tools, multi-provider (OpenAI, Anthropic, Gemini, Bedrock), zero vendor SDKs. India's TCS tops estimates, says new AI models did not dent services demand Gen Z's fading AI hype Strong feeling: we are in a folded AI reality GitHub - machinarii/total-recall-catalog: A reference catalog of latest knowledge retrieval, memory & RAG systems GitHub - mensfeld/code-on-incus: Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.. Quantization, LoRA, and the 8% Problem: Benchmarking Local LLMs for Production AI Iran war: We spoke to the man making Lego-style AI videos that experts say are powerful propaganda Powell, Bessent discussed Anthropic's Mythos AI cyber threat with major U.S. banks GitHub - immartian/bellamem: Persistent belief-graph memory for AI agents. Retrieves decisive context by importance — not recency, not RAG, not /compact. recursive-mode: The Repo-Native Operating System for AI Engineering After the attack on Sam Altman's home, will AI CEO's go on the offensive? The biggest advance in AI since the LLM Opus 4.6 vs GPT 5.4 One Prompt Unity World Generation Test “AI polls” are fake polls Client Challenge Can AI be a 'child of God'? Inside Anthropic's meeting with Christian leaders
GitHub - deltaxmodules/tuxaide
jorgeataide · 2026-05-05 · via Hacker News - Newest: "AI"

Stop searching. Just ask your terminal. Local AI assistant that runs entirely on your machine — no cloud, no API, no setup friction.

License: MIT Ollama Shell: bash/zsh Privacy: 100% local


⚡ Example

$ how do I list hidden files sorted by size

→ instantly returns:

ls -laSh

No browser. No copy/paste. No remembering flags.


🚀 Install

curl -fsSL https://raw.githubusercontent.com/deltaxmodules/tuxaide/main/setup.sh | bash

Then:

# Linux (bash)
source ~/.bashrc

# macOS (zsh)
source ~/.zshrc

Start typing questions directly in your terminal.


How it works

Write your Linux question directly in the terminal, as if it were a command:

$ how do I list hidden files sorted by size

TuxAide intercepts it silently and answers inline:

╭──────────────────────────────────────────────────────────────╮
╞═ 🐧 TuxAide (Ollama · qwen2.5-coder:7b · Smart RAG) ═╡

  To list hidden files sorted by size:

  ┄ shell ┄
  ls -laSh
  ┄┄┄┄┄┄┄

  -a shows hidden files, -S sorts by size (largest first),
  -h shows human-readable sizes (KB, MB, GB).
  To reverse: ls -laShr

  Source: man ls(1)

╰──────────────────────────────────────────────────────────────╯

Normal commands (ls -la, git commit, sudo apt update) pass through untouched. Zero interference.


Why TuxAide

1. No trigger word needed. You don’t type ask, hey or anything else. Just write your question — TuxAide hooks into the shell and responds.

2. It only explains. Never executes. Safer by design. You stay in control of what runs on your system.

3. 100% local by default. No API key. No account. No cloud. Nothing leaves your machine — ever.

4. Built for people learning Linux. No remembering flags. No searching docs. Just ask.

5. One command installs everything. Ollama, model, shell hook — all in one command.

6. Smart RAG — fast when simple, precise when needed. Simple questions → fast LLM answers Command-specific → local documentation (man pages)


Response speed (v2.1)

Question type Example Speed
Repeated question any question asked before < 1s (cache)
Simple / general "how do I create a folder" 3–5s
Command-specific "rsync options to exclude files" 8–15s
Deep documentation tuxaide mode deep 15–25s

Any language

how do I check open ports
como listar ficheiros ocultos
comment lister les fichiers cachés
cómo ver el espacio en disco
wie zeige ich offene Ports

TuxAide automatically replies in your language.


Examples

how do I backup with rsync
why is my process consuming so much RAM
what is the difference between chmod and chown
how to configure cron to run at 3am
how to see who is connected via SSH
how to create a sudo user on Ubuntu
what does the -z flag do in grep

Destructive command warnings

⚠ WARNING: This command is destructive and irreversible. Verify carefully before running.

rm -rf /old-data/

Controls

tuxaide on
tuxaide off
tuxaide status
tuxaide model llama3.2

tuxaide mode smart
tuxaide mode deep
tuxaide mode llm

tuxaide --timing
tuxaide reindex
tuxaide index nginx

tuxaide-uninstall

🔒 Data Sovereignty

  • Fully local processing via Ollama
  • No external calls
  • No tracking
  • Works offline after install
  • GDPR / NIS2 / Swiss nDSG friendly

Compatibility

Platform Support
Ubuntu / Debian
Fedora / RHEL
Arch Linux
macOS
ARM / Raspberry Pi

Shells: bash, zsh RAM: 5GB minimum (8GB recommended)


Contributing

Open source project — contributions welcome.

👉 https://github.com/deltaxmodules/tuxaide