# đŗ DeepSeek TUI
> **This terminal-native coding agent is built around DeepSeek V4's 1M-token context window and prefix cache capability. It is distributed as a single binary and requires no Node.js or Python runtime. It also includes an MCP client, a sandbox, and a durable task queue out of the box.**
[įŽäŊ䏿 README](README.zh-CN.md)
Before proceeding, ensure that `Node.js` and `npm` are installed.
```bash
node --version
npm --version
```
If `Node.js` and `npm` are not installed in your environment, refer to the installation guides provided below:
* English version: [https://nodejs.org/en/download](https://nodejs.org/en/download)
* Chinese version: [https://nodejs.org/zh-cn/download](https://nodejs.org/zh-cn/download)
Select the version that best matches your device specifications and operating system.
Install the `deepseek-tui` now:
```bash
npm install -g deepseek-tui
# When installing deepseek-tui in China's internet environment, you can use an npm mirror to speed up the installation process.
# npm install -g deepseek-tui@latest --registry=https://registry.npmmirror.com
```
[](https://github.com/Hmbown/DeepSeek-TUI/actions/workflows/ci.yml)
[](https://www.npmjs.com/package/deepseek-tui)
[](https://crates.io/crates/deepseek-tui-cli)
[](https://deepwiki.com/Hmbown/DeepSeek-TUI)

---
## What Is It?
DeepSeek TUI is a coding agent that runs entirely in your terminal. It gives DeepSeek's frontier models direct access to your workspace â reading and editing files, running shell commands, searching the web, managing git, and orchestrating sub-agents â all through a fast, keyboard-driven TUI.
**Built for DeepSeek V4** (`deepseek-v4-pro` / `deepseek-v4-flash`) with 1M-token context window and native thinking-mode (chain-of-thought) streaming.
### Key Features
- **Native RLM** (`rlm_query`) â fans out 1â16 cheap `deepseek-v4-flash` children in parallel for batched analysis and parallel reasoning, all against the existing API client
- **Thinking-mode streaming** â watch the model's chain-of-thought unfold in real time as it works through your tasks
- **Full tool suite** â file ops, shell execution, git, web search/browse, apply-patch, sub-agents, MCP servers
- **1M-token context** â automatic intelligent compaction when context fills up; prefix-cache aware for cost efficiency
- **Three modes** â Plan (read-only explore), Agent (interactive with approval), YOLO (auto-approved)
- **Reasoning-effort tiers** â cycle through `off â high â max` with `Shift + Tab`
- **Session save/resume** â checkpoint and resume long-running sessions
- **Workspace rollback** â side-git pre/post-turn snapshots with `/restore` and `revert_turn`, without touching your repo's `.git`
- **Durable task queue** â background tasks survive restarts; think scheduled automation, long-running reviews
- **HTTP/SSE runtime API** â `deepseek serve --http` for headless agent workflows
- **MCP protocol** â connect to Model Context Protocol servers for extended tooling; please see [docs/MCP.md](docs/MCP.md)
- **LSP diagnostics** â inline error/warning surfacing after every edit via rust-analyzer, pyright, typescript-language-server, gopls, clangd
- **User memory** â optional persistent note file injected into the system prompt for cross-session preferences
- **Localized UI** â `en`, `ja`, `zh-Hans`, `pt-BR` with auto-detection
- **Live cost tracking** â per-turn and session-level token usage and cost estimates; cache hit/miss breakdown
- **Skills system** â composable, installable instruction packs from GitHub with no backend service required
---
## How It's Wired
`deepseek` (dispatcher CLI) â `deepseek-tui` (companion binary) â ratatui interface â async engine â OpenAI-compatible streaming client. Tool calls route through a typed registry (shell, file ops, git, web, sub-agents, MCP, RLM) and results stream back into the transcript. The engine manages session state, turn tracking, the durable task queue, and an LSP subsystem that feeds post-edit diagnostics into the model's context before the next reasoning step.
See [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) for the full walkthrough.
---
## Quickstart
```bash
npm install -g deepseek-tui
deepseek --version
deepseek
```
Prebuilt binaries are published for **Linux x64**, **Linux ARM64** (v0.8.8+), **macOS x64**, **macOS ARM64**, and **Windows x64**. For other targets (musl, riscv64, FreeBSD, etc.), see [Install from source](#install-from-source) or [docs/INSTALL.md](docs/INSTALL.md).
On first launch you'll be prompted for your [DeepSeek API key](https://platform.deepseek.com/api_keys). The key is saved to `~/.deepseek/config.toml` so it works from any directory without OS credential prompts.
You can also set it ahead of time:
```bash
deepseek auth set --provider deepseek # saves to ~/.deepseek/config.toml
export DEEPSEEK_API_KEY="YOUR_KEY" # env var alternative; use ~/.zshenv for non-interactive shells
deepseek
deepseek doctor # verify setup
```
> To rotate or remove a saved key: `deepseek auth clear --provider deepseek`.
### Linux ARM64 (Raspberry Pi, Asahi, Graviton, HarmonyOS PC)
`npm i -g deepseek-tui` works on glibc-based ARM64 Linux from v0.8.8 onward. You can also download prebuilt binaries from the [Releases page](https://github.com/Hmbown/DeepSeek-TUI/releases) and place them side by side on your `PATH`.
### China / Mirror-friendly Installation
If GitHub or npm downloads are slow from mainland China, use a Cargo registry mirror:
```toml
# ~/.cargo/config.toml
[source.crates-io]
replace-with = "tuna"
[source.tuna]
registry = "sparse+https://mirrors.tuna.tsinghua.edu.cn/crates.io-index/"
```
Then install both binaries (the dispatcher delegates to the TUI at runtime):
```bash
cargo install deepseek-tui-cli --locked # provides `deepseek`
cargo install deepseek-tui --locked # provides `deepseek-tui`
deepseek --version
```
Prebuilt binaries can also be downloaded from [GitHub Releases](https://github.com/Hmbown/DeepSeek-TUI/releases). Use `DEEPSEEK_TUI_RELEASE_BASE_URL` for mirrored release assets.
Install from source
Works on any Tier-1 Rust target â including musl, riscv64, FreeBSD, and older ARM64 distros.
```bash
# Linux build deps (Debian/Ubuntu/RHEL):
# sudo apt-get install -y build-essential pkg-config libdbus-1-dev
# sudo dnf install -y gcc make pkgconf-pkg-config dbus-devel
git clone https://github.com/Hmbown/DeepSeek-TUI.git
cd DeepSeek-TUI
cargo install --path crates/cli --locked # requires Rust 1.85+; provides `deepseek`
cargo install --path crates/tui --locked # provides `deepseek-tui`
```
Both binaries are required. Cross-compilation and platform-specific notes: [docs/INSTALL.md](docs/INSTALL.md).
### Other API Providers
```bash
# NVIDIA NIM
deepseek auth set --provider nvidia-nim --api-key "YOUR_NVIDIA_API_KEY"
deepseek --provider nvidia-nim
# Fireworks
deepseek auth set --provider fireworks --api-key "YOUR_FIREWORKS_API_KEY"
deepseek --provider fireworks --model deepseek-v4-pro
# Self-hosted SGLang
SGLANG_BASE_URL="http://localhost:30000/v1" deepseek --provider sglang --model deepseek-v4-flash
```
---
## What's New In v0.8.11
A targeted patch for the V4 cache-maxing overhaul plus three runtime fixes discovered in YOLO long-session dogfooding. [Full changelog](CHANGELOG.md).
- **Cache-maxing prompt path for DeepSeek V4** â the engine skips system-prompt reassembly when the stable prefix is unchanged, moves the working-set summary out of the system prompt into per-turn metadata, and anchors the tool array with `cache_control: ephemeral`. Net effect: fewer prefix rewrites, higher cache-hit rates, lower cost per turn.
- **500K token compaction floor** â automatic compaction refuses below 500K tokens; manual `/compact` still bypasses. The message-count trigger (a 128K-era heuristic) is removed â token budget is the sole auto-trigger.
- **`npm install` resilience** â retry with exponential backoff, per-attempt timeout + stall detector, `HTTPS_PROXY`/`HTTP_PROXY`/`NO_PROXY` support (pure Node, no new deps), and download progress to stderr. Driven by a community report from China where `npm install` took 18 minutes through a CN mirror.
- **YOLO sandbox dropped** â YOLO now uses DangerFullAccess (no sandbox), consistent with its auto-approval + trust mode posture. Previously, the WorkspaceWrite sandbox was intercepting legitimate outside-workspace writes.
- **Scroll lock preserved during live streaming** â scrolling up mid-stream no longer gets yanked back to the tail on the next chunk. The `user_scrolled_during_stream` lock now survives render-time clamping.
- **Capacity controller off by default** â the controller was silently clearing transcripts independent of token usage or `auto_compact` settings. Now defaults to disabled; opt-in via `capacity.enabled = true`.
- **README clarity pass** (#685) â title-cased headings, explicit prerequisites, China-friendly install variant. *Thanks to [@Agent-Skill-007](https://github.com/Agent-Skill-007) for this PR.*
---
## Usage
```bash
deepseek # interactive TUI
deepseek "explain this function" # one-shot prompt
deepseek --model deepseek-v4-flash "summarize" # model override
deepseek --yolo # auto-approve tools
deepseek auth set --provider deepseek # save API key
deepseek doctor # check setup & connectivity
deepseek doctor --json # machine-readable diagnostics
deepseek setup --status # read-only setup status
deepseek setup --tools --plugins # scaffold tool/plugin dirs
deepseek models # list live API models
deepseek sessions # list saved sessions
deepseek resume --last # resume latest session
deepseek serve --http # HTTP/SSE API server
deepseek pr # fetch PR and pre-seed review prompt
deepseek mcp list # list configured MCP servers
deepseek mcp validate # validate MCP config/connectivity
deepseek mcp-server # run dispatcher MCP stdio server
```
### Keyboard Shortcuts
| Key | Action |
|---|---|
| `Tab` | Complete `/` or `@` entries; while running, queue draft as follow-up; otherwise cycle mode |
| `Shift+Tab` | Cycle reasoning-effort: off â high â max |
| `F1` | Searchable help overlay |
| `Esc` | Back / dismiss |
| `Ctrl+K` | Command palette |
| `Ctrl+R` | Resume an earlier session |
| `Alt+R` | Search prompt history and recover cleared drafts |
| `Ctrl+S` | Stash current draft (`/stash list`, `/stash pop` to recover) |
| `@path` | Attach file/directory context in composer |
| `â` (at composer start) | Select attachment row for removal |
| `Alt+â` | Edit last queued message |
Full shortcut catalog: [docs/KEYBINDINGS.md](docs/KEYBINDINGS.md).
---
## Modes
| Mode | Behavior |
| --- | --- |
| **Plan** đ | Read-only investigation â model explores and proposes a plan (`update_plan` + `checklist_write`) before making changes |
| **Agent** đ¤ | Default interactive mode â multi-step tool use with approval gates; model outlines work via `checklist_write` |
| **YOLO** ⥠| Auto-approve all tools in a trusted workspace; still maintains plan and checklist for visibility |
---
## Configuration
User config: `~/.deepseek/config.toml`. Project overlay: `/.deepseek/config.toml` (denied: `api_key`, `base_url`, `provider`, `mcp_config_path`). [config.example.toml](config.example.toml) has every option.
Key environment variables:
| Variable | Purpose |
|---|---|
| `DEEPSEEK_API_KEY` | API key |
| `DEEPSEEK_BASE_URL` | API base URL |
| `DEEPSEEK_MODEL` | Default model |
| `DEEPSEEK_PROVIDER` | `deepseek` (default), `nvidia-nim`, `fireworks`, `sglang` |
| `DEEPSEEK_PROFILE` | Config profile name |
| `DEEPSEEK_MEMORY` | Set to `on` to enable user memory |
| `NVIDIA_API_KEY` / `FIREWORKS_API_KEY` / `SGLANG_API_KEY` | Provider auth |
| `SGLANG_BASE_URL` | Self-hosted SGLang endpoint |
| `NO_ANIMATIONS=1` | Force accessibility mode at startup |
| `SSL_CERT_FILE` | Custom CA bundle for corporate proxies |
UI locale is separate from model language â set `locale` in `settings.toml`, use `/config locale zh-Hans`, or rely on `LC_ALL`/`LANG`. See [docs/CONFIGURATION.md](docs/CONFIGURATION.md) and [docs/MCP.md](docs/MCP.md).
---
## Models & Pricing
| Model | Context | Input (cache hit) | Input (cache miss) | Output |
|---|---|---|---|---|
| `deepseek-v4-pro` | 1M | $0.003625 / 1M* | $0.435 / 1M* | $0.87 / 1M* |
| `deepseek-v4-flash` | 1M | $0.0028 / 1M | $0.14 / 1M | $0.28 / 1M |
Legacy aliases `deepseek-chat` / `deepseek-reasoner` map to `deepseek-v4-flash`. NVIDIA NIM variants use your NVIDIA account terms.
*DeepSeek Pro rates currently reflect a limited-time 75% discount, which remains valid until 15:59 UTC on 5 May 2026. After that time, the TUI cost estimator will revert to the base Pro rates.*
---
## Publishing Your Own Skill
DeepSeek TUI discovers skills from workspace directories (`.agents/skills` â `skills` â `.opencode/skills` â `.claude/skills`) and the global `~/.deepseek/skills`. Each skill is a directory with a `SKILL.md` file:
```text
~/.deepseek/skills/my-skill/
âââ SKILL.md
```
Frontmatter required:
```markdown
---
name: my-skill
description: Use this when DeepSeek should follow my custom workflow.
---
# My Skill
Instructions for the agent go here.
```
Commands: `/skills` (list), `/skill ` (activate), `/skill new` (scaffold), `/skill install github:/` (community), `/skill update` / `uninstall` / `trust`. Community installs from GitHub require no backend service. Installed skills appear in the model-visible session context; the agent can auto-select relevant skills via the `load_skill` tool when your task matches their descriptions.
---
## Documentation
| Doc | Topic |
|---|---|
| [ARCHITECTURE.md](docs/ARCHITECTURE.md) | Codebase internals |
| [CONFIGURATION.md](docs/CONFIGURATION.md) | Full config reference |
| [MODES.md](docs/MODES.md) | Plan / Agent / YOLO modes |
| [MCP.md](docs/MCP.md) | Model Context Protocol integration |
| [RUNTIME_API.md](docs/RUNTIME_API.md) | HTTP/SSE API server |
| [INSTALL.md](docs/INSTALL.md) | Platform-specific install guide |
| [MEMORY.md](docs/MEMORY.md) | User memory feature guide |
| [SUBAGENTS.md](docs/SUBAGENTS.md) | Sub-agent role taxonomy and lifecycle |
| [KEYBINDINGS.md](docs/KEYBINDINGS.md) | Full shortcut catalog |
| [RELEASE_RUNBOOK.md](docs/RELEASE_RUNBOOK.md) | Release process |
| [OPERATIONS_RUNBOOK.md](docs/OPERATIONS_RUNBOOK.md) | Ops & recovery |
Full Changelog: [CHANGELOG.md](CHANGELOG.md).
---
## Thanks
Earlier releases shipped with help from these contributors:
- **Hafeez Pizofreude** â SSRF protection in `fetch_url` and Star History chart
- **Unic (YuniqueUnic)** â Schema-driven config UI (TUI + web)
- **Jason** â SSRF security hardening
---
## Contributing
See [CONTRIBUTING.md](CONTRIBUTING.md). Pull requests welcome â check the [open issues](https://github.com/Hmbown/DeepSeek-TUI/issues) for good first contributions.
> [!Note]
> *Not affiliated with DeepSeek Inc.*
## License
[MIT](LICENSE)
## Star History
[](https://www.star-history.com/?repos=Hmbown%2FDeepSeek-TUI&type=date&logscale=&legend=top-left)