DeepSeek-TUI
SHA-256DeepSeek TUI is a terminal-based coding agent that brings DeepSeek V4's reasoning power to your command line, with auto mode, tool suite, and session persistence.
Smart Download
Download Download Version
v0.8.31 · 43.1 MB
A keyboard-driven terminal agent for DeepSeek models with auto mode and streaming reasoning.
Core Features
- Auto mode: dynamically selects model (Flash/Pro) and thinking level per turn
- Streaming reasoning: see DeepSeek's thought process in real-time
- Full tool suite: file ops, shell, git, web, sub-agents, MCP servers
- 1M-token context: long context with cost-aware compaction
- Three modes: Plan (read-only), Agent (interactive approval), YOLO (auto-approved)
What It Can't Do
- •Requires a valid DeepSeek API key. Auto mode may select the more expensive Pro model. YOLO mode executes actions without approval. Building from source requires Rust 1.88+ and system dependencies (dbus, pkg-config).
Use Cases
- Edit and manage code files interactively with AI assistance in terminal
- Debug and refactor large projects with full context understanding
Detailed Introduction
DeepSeek TUI is a keyboard-driven terminal agent that integrates DeepSeek V4 models (Pro/Flash) with 1M-token context, streaming reasoning, and a complete toolset: file editing, shell commands, git, web search, sub-agents, MCP servers, and more. It features auto mode that dynamically selects model and thinking level per turn, session save/resume, workspace rollback, LSP diagnostics, and localized UI. Install via npm, Cargo, Homebrew, Docker, or direct binary download.
Tags
Getting Started
Download installer
Click the button above to download the installer for your system
Install the software
Install the appropriate package for your distro (dpkg / rpm / AppImage)
Install globally via npm: npm install -g deepseek-tui
Run deepseek, enter your DeepSeek API key on first launch
Start chatting, use /model auto to enable automatic model selection
- Install globally via npm: npm install -g deepseek-tui
- Run deepseek, enter your DeepSeek API key on first launch
- Start chatting, use /model auto to enable automatic model selection
SHA-256 checksum verified
Checksum extracted from GitHub official Release page
SHA256 Checksum
cbe7a54314a501d294f48834ca809aabe86d58d34c02ae8412848e717a5e3c63This checksum is extracted from the GitHub Release page. Verify file integrity after download.
All SHA-256 checksums on this platform are extracted from the project's official GitHub Release page, without any modification. You can independently verify them on the GitHub Releases page.
Open Source Transparency
View GitHub SourceUninstall Info
If installed via npm: npm uninstall -g deepseek-tui. Via Cargo: cargo uninstall deepseek-tui-cli && cargo uninstall deepseek-tui. Via Homebrew: brew uninstall deepseek-tui.
No Extra Dependencies
Ready to use after download. No additional runtime required.
Similar Projects
Chatbox
Chatbox Community Edition is an open-source desktop client for interacting with multiple large language models. It supports OpenAI (ChatGPT), Azure OpenAI, Claude, Google Gemini Pro, Ollama (local models like Llama 2, Mistral), and ChatGLM-6B. All your chat data is stored locally on your device, ensuring privacy and preventing data loss. The app features a clean, ergonomic UI with dark mode, keyboard shortcuts, streaming replies, and full Markdown/LaTeX rendering with code highlighting. It also includes a prompt library, message quoting, and team collaboration for sharing API resources. Available on Windows, macOS, Linux, Web, iOS, and Android. The community edition is fully functional but may lack some advanced features from the pro version.
ollama
Ollama lets you download, run, and manage large language models locally. One command, multiple platforms, endless possibilities.
llama.cpp
High-performance LLM inference engine in C/C++ with minimal dependencies, supporting quantized models (1.5–8 bit) and diverse hardware (Apple Silicon, CUDA, Vulkan, etc.).