Skip to content

ai-cli-tools.mdx

Latest commit

 

History

History
137 lines (97 loc) · 3.36 KB

ai-cli-tools.mdx

File metadata and controls

137 lines (97 loc) · 3.36 KB
Raw
title AI CLI Tools
description Claude Code, Qwen Code, Gemini CLI, Codex, and Local LLM — set up on your Android device.

Overview

OCA installs AI CLI tools via npm install -g during Step 7. All run through the glibc Node.js environment.

AI CLIs need **API keys** from their respective providers. OCA installs the binaries — you configure the keys after install.

🟢 Using Free AI Models (Quick Reference)

You can run advanced LLMs—like GPT-4.1, GPT-5 mini, MiniMax, Kimi, GLM—absolutely free via Copilot CLI, OpenCode app, or Zen! Here’s how:

Step 1: Pick a Free Model

  • Run /models or open model picker; look for:
    • GPT-4.1, GPT-5 mini (FREE via GitHub integration)
    • MiniMax, Kimi, Big Pickle, GLM, Nemotron (Free via Zen/OpenCode!)
    • Green tick/0x = no cost!

Step 2: Provide Your API Key

  • Even free models need an API key (from Zen, OpenCode, etc).
  • Register here and paste key at prompt.

Step 3: Respect Free Quota

Model/Platform Cost Free Limit Notes
GPT-4.1, 5-mini ₹0 200 req / 5 hr GitHub, Copilot
MiniMax, Kimi ₹0 200 req / 5 hr Zen, OpenCode
Big Pickle ₹0 Shared pool, capped OpenCode
GLM/Nemotron ₹0 Shared pool, capped Zen, Kilo Code

Pro Tip: Main (Jarvis RTX⚡) bhi GPT-4.1 hoon—bilkul free tier ki tarah!

Caveats

  • Free plan pe data provider ko model training ke liye jaa sakta hai—so avoid super private code.
  • Models rotate/expire; /models or Zen dashboard for latest free list!

For in-depth details and advanced tips, see full README “Getting Free AI Models” or OpenCode Zen Docs.

Qwen Code

Best choice for Android — lightweight and uses --ignore-scripts which skips native builds that fail on Android.

Install:

npm install -g @qwen-code/qwen-code@latest --ignore-scripts

Setup:

qwen config set api-key YOUR_DASHSCOPE_KEY
qwen config set model qwen-coder-turbo

Start:

qwen
`--ignore-scripts` skips `node-pty` and `@lvce-editor/ripgrep` native builds, which both fail on Android. Core CLI functionality is unaffected.

Claude Code

npm install -g @anthropic-ai/claude-code
claude config set apiKey YOUR_ANTHROPIC_KEY
claude

Get your key at console.anthropic.com.

Gemini CLI

npm install -g @google/gemini-cli
gemini  # prompts for Google account login on first run

Or with API key:

export GEMINI_API_KEY=your_key
gemini

Get your key at aistudio.google.com.

Codex (OpenAI)

npm install -g @openai/codex
export OPENAI_API_KEY=your_key
codex

Using inside tmux

Always run AI CLIs inside tmux for long sessions:

tmux new -s ai
qwen
# Detach: Ctrl+B, then D
# Reattach: tmux attach -t ai

Managing CLIs

# Check installed
npm list -g --depth=0

# Update all
npm update -g @qwen-code/qwen-code @anthropic-ai/claude-code @google/gemini-cli @openai/codex

# Or via OCA
oca --update