@mmmbuto/deepseek-tui-termux

Install and run the Termux/Android ARM64 deepseek and deepseek-tui binaries.

Install

npm install -g @mmmbuto/deepseek-tui-termux@latest
deepseek --version

Set your API key:

export DEEPSEEK_API_KEY="YOUR_KEY"
deepseek --model auto

The package bundles Forge-built Android ARM64 binaries in bin/downloads/ and exposes deepseek and deepseek-tui commands.

First run

The deepseek facade and deepseek-tui binary share ~/.deepseek/config.toml for DeepSeek auth and default model settings. Common TUI commands are available directly through the facade, including deepseek doctor, deepseek models, deepseek sessions, and deepseek resume --last.

The app talks to DeepSeek's documented OpenAI-compatible Chat Completions API. Set DEEPSEEK_BASE_URL only if you need the China endpoint or DeepSeek beta features such as strict tool mode, chat prefix completion, or FIM completion.

NVIDIA NIM-hosted DeepSeek V4 Pro is also supported:

deepseek auth set --provider nvidia-nim --api-key "YOUR_NVIDIA_API_KEY"
deepseek --provider nvidia-nim

For a single process, set DEEPSEEK_PROVIDER=nvidia-nim and NVIDIA_API_KEY or NVIDIA_NIM_API_KEY (with DEEPSEEK_API_KEY as a compatibility fallback). The NIM default model is deepseek-ai/deepseek-v4-pro and the default base URL is https://integrate.api.nvidia.com/v1. With --provider nvidia-nim, --model deepseek-v4-flash maps to deepseek-ai/deepseek-v4-flash.

Supported platform

• Android ARM64 through Termux
• Node.js >= 18

Desktop Linux, macOS, and Windows users should use upstream Hmbown/DeepSeek-TUI.

Configuration

• Default bundled binary version comes from deepseekBinaryVersion in package.json.
• Set DEEPSEEK_TUI_DISABLE_INSTALL=1 to skip install-time download.
• Set DEEPSEEK_TUI_FORCE_DOWNLOAD=1 only when testing external release assets.

Release integrity

npm publish verifies that the Android ARM64 binaries and version markers are bundled before the tarball is created.