DeepSeek-TUI

Sat, 09 May 2026 16:46:52 +0800

Hmbown/DeepSeek-TUI

DeepSeek TUI

Terminal coding agent for DeepSeek V4. It runs from the deepseek command, streams reasoning blocks, edits local workspaces with approval gates, and includes an auto mode that chooses both model and thinking level per turn.

简体中文 README

Install

deepseek is distributed as Rust binaries: the dispatcher command (deepseek) and the companion TUI runtime (deepseek-tui). Pick whichever install path you already use; they all put the same commands on your PATH. The npm package is an installer/wrapper for the release binaries, not the agent runtime itself.

# 1. npm — easiest if you already use Node. The package downloads the
#    matching prebuilt Rust binaries from GitHub Releases.
npm install -g deepseek-tui

# 2. Cargo — no Node needed.
cargo install deepseek-tui-cli --locked   # `deepseek` (entry point)
cargo install deepseek-tui     --locked   # `deepseek-tui` (TUI binary)

# 3. Homebrew — macOS package manager.
brew tap Hmbown/deepseek-tui
brew install deepseek-tui

# 4. Direct download — no package manager or toolchain.
#    https://github.com/Hmbown/DeepSeek-TUI/releases
#    Prebuilt for Linux x64/ARM64, macOS x64/ARM64, Windows x64.

# 5. Docker — prebuilt release image.
docker run --rm -it \
  -e DEEPSEEK_API_KEY \
  -v "$PWD:/workspace" \
  ghcr.io/hmbown/deepseek-tui:latest

In mainland China, speed up the npm path with --registry=https://registry.npmmirror.com, or use the Cargo mirror below.

DeepWiki project index

What Is It?

DeepSeek TUI is a coding agent that runs in your terminal. It can read and edit files, run shell commands, search the web, manage git, and coordinate sub-agents from a keyboard-driven TUI.

It is built around DeepSeek V4 (deepseek-v4-pro / deepseek-v4-flash), including 1M-token context windows, streaming reasoning blocks, and prefix-cache-aware cost reporting.

Key Features

Auto mode — --model auto / /model auto chooses both the model and thinking level for each turn
Thinking-mode streaming — see DeepSeek reasoning blocks as the model works
Full tool suite — file ops, shell execution, git, web search/browse, apply-patch, sub-agents, MCP servers
1M-token context — context tracking, manual or configured compaction, and prefix-cache telemetry
Three modes — Plan (read-only explore), Agent (interactive with approval), YOLO (auto-approved)
Reasoning-effort tiers — cycle through off → high → max with Shift + Tab
Session save/resume — checkpoint and resume long-running sessions
Workspace rollback — side-git pre/post-turn snapshots with /restore and revert_turn, without touching your repo’s .git
Durable task queue — background tasks can survive restarts
HTTP/SSE runtime API — deepseek serve --http for headless agent workflows
MCP protocol — connect to Model Context Protocol servers for extended tooling; please see docs/MCP.md
Native RLM (rlm_query) — run batched analysis through cheap deepseek-v4-flash children using the same API client
LSP diagnostics — inline error/warning surfacing after every edit via rust-analyzer, pyright, typescript-language-server, gopls, clangd
User memory — optional persistent note file injected into the system prompt for cross-session preferences
Localized UI — en, ja, zh-Hans, pt-BR with auto-detection
Live cost tracking — per-turn and session-level token usage and cost estimates; cache hit/miss breakdown
Skills system — composable, installable instruction packs from GitHub with no backend service required

How It’s Wired

deepseek (dispatcher CLI) → deepseek-tui (companion binary) → ratatui interface ↔ async engine ↔ 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 for the full walkthrough.

Quickstart

1
2
3

npm install -g deepseek-tui
deepseek --version
deepseek --model auto

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 or docs/INSTALL.md.

On first launch you’ll be prompted for your DeepSeek API key. 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:

deepseek auth set --provider deepseek   # saves to ~/.deepseek/config.toml
deepseek auth status                    # shows the active credential source

export DEEPSEEK_API_KEY="YOUR_KEY"      # env var alternative; use ~/.zshenv for non-interactive shells
deepseek

deepseek doctor                         # verify setup

If deepseek doctor says the rejected key came from DEEPSEEK_API_KEY, remove the stale export from your shell startup file, open a fresh shell, or run deepseek auth set --provider deepseek. Use deepseek auth status to see the config, keyring, and env-var source state without printing the key. Saved config keys take precedence over the keyring and environment and are easier to rotate.

To rotate or remove a saved key: deepseek auth clear --provider deepseek.

Auto Mode

Use deepseek --model auto or /model auto when you want DeepSeek TUI to decide how much model and reasoning power a turn needs.

Auto mode controls two settings together:

Model: deepseek-v4-flash or deepseek-v4-pro
Thinking: off, high, or max

Before the real turn is sent, the app makes a small deepseek-v4-flash routing call with thinking off. That router looks at the latest request and recent context, then selects a concrete model and thinking level for the real request. Short/simple turns can stay on Flash with thinking off; coding, debugging, release work, architecture, security review, or ambiguous multi-step tasks can move up to Pro and/or higher thinking.

auto is local to DeepSeek TUI. The upstream API never receives model: "auto"; it receives the concrete model and thinking setting chosen for that turn. The TUI shows the selected route, and cost tracking is charged against the model that actually ran. If the router call fails or returns an invalid answer, the app falls back to a local heuristic. Sub-agents inherit auto mode unless you assign them an explicit model.

Use a fixed model or fixed thinking level when you want repeatable benchmarking, a strict cost ceiling, or a specific provider/model mapping.

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 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:

# ~/.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):

1
2
3

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. Use DEEPSEEK_TUI_RELEASE_BASE_URL for mirrored release assets.

Windows (Scoop)

Scoop is a Windows package manager. DeepSeek TUI is listed in Scoop’s main bucket, but that manifest updates independently and can lag the GitHub/npm/Cargo release. Run scoop update first, then verify the installed version with deepseek --version:

1
2
3

scoop update
scoop install deepseek-tui
deepseek --version

Use npm or direct GitHub release downloads when you need the newest release before Scoop’s manifest catches up.

Install from source

Works on any Tier-1 Rust target — including musl, riscv64, FreeBSD, and older ARM64 distros.

# 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 1.88+; provides `deepseek`
cargo install --path crates/tui --locked   # provides `deepseek-tui`

Both binaries are required. Cross-compilation and platform-specific notes: docs/INSTALL.md.

Other API Providers

# 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

# Generic OpenAI-compatible endpoint
deepseek auth set --provider openai --api-key "YOUR_OPENAI_COMPATIBLE_API_KEY"
OPENAI_BASE_URL="https://openai-compatible.example/v4" deepseek --provider openai --model glm-5

# Self-hosted SGLang
SGLANG_BASE_URL="http://localhost:30000/v1" deepseek --provider sglang --model deepseek-v4-flash

# Self-hosted vLLM
VLLM_BASE_URL="http://localhost:8000/v1" deepseek --provider vllm --model deepseek-v4-flash

# Self-hosted Ollama
ollama pull deepseek-coder:1.3b
deepseek --provider ollama --model deepseek-coder:1.3b

What’s New In v0.8.24

A community-focused bugfix release picking up the backlog after the v0.8.23 security release. Full changelog.

Cache-aware prompt diagnostics + payload optimization (#1196, thanks wplll) — new /cache inspect and /cache warmup commands, layered prompt classification (static / history / dynamic) with per-layer SHA-256 hashes, wire-payload dedup for repeated tool outputs, and a footer cache-hit % chip from the DeepSeek API response. A new Project Context Pack is injected into the stable prefix by default to improve cache hit rates; disable with [context] project_pack = false if you’d rather keep prompts minimal.
Workspace-local slash commands (#1259) — drop a .deepseek/commands/foo.md in any project and /foo works there. Also scans .cursor/commands/ and .claude/commands/. Project-local shadows global by name.
@-mention completion finds AI-tool dot-directories — files inside .deepseek/, .cursor/, .claude/, and .agents/ are now discoverable via @ completion even when those dirs are in .gitignore.
MCP paginated discovery (#1250, thanks Liu-Vince) — MCP servers that paginate tools/list (e.g., gbrain at 5 per page) now have all their tools discovered via nextCursor.
Snapshot disk cap (#1112) — the snapshot side repo enforces a 500 MB hard limit, pruning oldest first when it’s hit. Guards against the reported 1.2 TB blowup. Thanks @Giggitycountless for the PR #1131 proposal.
/clear resets the Todos sidebar (#1258) — was only clearing the Plan panel before.
Mouse-wheel survives focus toggles — re-arms EnableMouseCapture on FocusGained so wheel scroll keeps working after Cmd+Tab or screenshot workflows.
i18n: prompts in English get English replies (#1118) — Chinese filenames in a project tree no longer bias the model toward Chinese responses.
Plus: language-directive strengthening, MCP error-message clarity improvements (PR #1196), and assorted polish.

⚠️ Known issue: v0.8.22+ have a Windows 10 conhost flicker regression (#1260) tracked for v0.8.25. v0.8.20 works correctly if you’re affected.

Usage

deepseek                                         # interactive TUI
deepseek "explain this function"                 # one-shot prompt
deepseek --model deepseek-v4-flash "summarize"   # model override
deepseek --model auto "fix this bug"             # auto-select model + thinking
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 the most recent session in this workspace
deepseek resume <SESSION_ID>                     # resume a specific session by UUID
deepseek fork <SESSION_ID>                       # fork a session at a chosen turn
deepseek serve --http                            # HTTP/SSE API server
deepseek serve --acp                             # ACP stdio adapter for Zed/custom agents
deepseek run pr <N>                              # 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
deepseek update                                  # check for and apply binary updates

Docker images are published to GHCR for release builds:

docker volume create deepseek-tui-home

docker run --rm -it \
  -e DEEPSEEK_API_KEY="$DEEPSEEK_API_KEY" \
  -v deepseek-tui-home:/home/deepseek/.deepseek \
  ghcr.io/hmbown/deepseek-tui:latest

Zed / ACP

DeepSeek can run as a custom Agent Client Protocol server for editors that spawn local ACP agents over stdio. In Zed, add a custom agent server:

{
  "agent_servers": {
    "DeepSeek": {
      "type": "custom",
      "command": "deepseek",
      "args": ["serve", "--acp"],
      "env": {}
    }
  }
}

The first ACP slice supports new sessions and prompt responses through your existing DeepSeek config/API key. Tool-backed editing and checkpoint replay are not exposed through ACP yet.

Keyboard Shortcuts

Key	Action
`Tab`	Complete `/` or `@` entries; while running, queue draft as follow-up; otherwise cycle mode
`Shift+Tab`	Cycle reasoning-effort: off → high → 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
`↑` (at composer start)	Select attachment row for removal

Full shortcut catalog: docs/KEYBINDINGS.md.

Modes

Mode	Behavior
Plan 🔍	Read-only investigation — model explores and proposes a plan (`update_plan` + `checklist_write`) before making changes
Agent 🤖	Default interactive mode — 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: <workspace>/.deepseek/config.toml (denied: api_key, base_url, provider, mcp_config_path). config.example.toml has every option.

Key environment variables:

Variable	Purpose
`DEEPSEEK_API_KEY`	API key
`DEEPSEEK_BASE_URL`	API base URL
`DEEPSEEK_HTTP_HEADERS`	Optional custom model request headers, e.g. `X-Model-Provider-Id=your-model-provider`
`DEEPSEEK_MODEL`	Default model
`DEEPSEEK_STREAM_IDLE_TIMEOUT_SECS`	Stream idle timeout in seconds, default `300`, clamped to `1..=3600`
`DEEPSEEK_PROVIDER`	`deepseek` (default), `nvidia-nim`, `openai`, `openrouter`, `novita`, `fireworks`, `sglang`, `vllm`, `ollama`
`DEEPSEEK_PROFILE`	Config profile name
`DEEPSEEK_MEMORY`	Set to `on` to enable user memory
`NVIDIA_API_KEY` / `OPENAI_API_KEY` / `OPENROUTER_API_KEY` / `NOVITA_API_KEY` / `FIREWORKS_API_KEY` / `SGLANG_API_KEY` / `VLLM_API_KEY` / `OLLAMA_API_KEY`	Provider auth
`OPENAI_BASE_URL` / `OPENAI_MODEL`	Generic OpenAI-compatible endpoint and model ID
`SGLANG_BASE_URL`	Self-hosted SGLang endpoint
`VLLM_BASE_URL`	Self-hosted vLLM endpoint
`OLLAMA_BASE_URL`	Self-hosted Ollama endpoint
`OLLAMA_MODEL`	Self-hosted Ollama model tag
`NO_ANIMATIONS=1`	Force accessibility mode at startup
`SSL_CERT_FILE`	Custom CA bundle for corporate proxies

Set locale in settings.toml, use /config locale zh-Hans, or rely on LC_ALL/LANG to choose UI chrome and the fallback language sent to V4 models. The latest user message still wins for natural-language reasoning and replies, so Chinese user turns stay Chinese even on an English system locale. See docs/CONFIGURATION.md and 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

DeepSeek Platform defaults to https://api.deepseek.com/beta in v0.8.16 so beta-gated API features can be tested without extra setup. Set base_url = "https://api.deepseek.com" to opt out.

Legacy aliases deepseek-chat / deepseek-reasoner map to deepseek-v4-flash and retire after July 24, 2026. 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 31 May 2026. After that time, the TUI cost estimator will revert to the base Pro rates.

[!Note] For the latest DeepSeek-V4-Pro pricing, including the current 75% discount valid until 15:59 UTC on 31 May 2026, please consult the official DeepSeek pricing page. All rates listed in the README correspond to the officially published values.

Publishing Your Own Skill

DeepSeek TUI discovers skills from workspace directories (.agents/skills → skills → .opencode/skills → .claude/skills → .cursor/skills) and global directories (~/.agents/skills → ~/.claude/skills → ~/.deepseek/skills). Each skill is a directory with a SKILL.md file:

1
2

~/.agents/skills/my-skill/
└── SKILL.md

Frontmatter required:

---
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 <name> (activate), /skill new (scaffold), /skill install github:<owner>/<repo> (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	Codebase internals
CONFIGURATION.md	Full config reference
MODES.md	Plan / Agent / YOLO modes
MCP.md	Model Context Protocol integration
RUNTIME_API.md	HTTP/SSE API server
INSTALL.md	Platform-specific install guide
MEMORY.md	User memory feature guide
SUBAGENTS.md	Sub-agent role taxonomy and lifecycle
KEYBINDINGS.md	Full shortcut catalog
RELEASE_RUNBOOK.md	Release process
LOCALIZATION.md	UI locale matrix & switching
OPERATIONS_RUNBOOK.md	Ops & recovery

Full Changelog: CHANGELOG.md.

Thanks

DeepSeek — thank you for the models and support that power every turn. 感谢 DeepSeek 提供模型与支持，让每一次交互成为可能。
DataWhale 🐋 — thank you for your support and for welcoming us into the Whale Brother family. 感谢 DataWhale 的支持，并欢迎我们加入“鲸兄弟”大家庭。

This project ships with help from a growing community of contributors:

merchloubna70-dot — 28 PRs spanning features, fixes, and VS Code extension scaffolding (#645–#681)
WyxBUPT-22 — Markdown rendering for tables, bold/italic, and horizontal rules (#579)
loongmiaow-pixel — Windows + China install documentation (#578)
20bytes — User memory docs and help polish (#569)
staryxchen — glibc compatibility preflight (#556)
Vishnu1837 — glibc compatibility improvements (#565)
shentoumengxin — Shell cwd boundary validation (#524)
toi500 — Windows paste fix report
xsstomy — Terminal startup repaint report
melody0709 — Slash-prefix Enter activation report
lloydzhou and jeoor — Compaction cost reports; lloydzhou also contributed deterministic environment context (#813, #922) and KV prefix-cache stabilisation (#1080)
Agent-Skill-007 — README clarity pass (#685)
woyxiang — Windows install documentation (#696)
wangfeng — Pricing/discount info update (#692)
zichen0116 — CODE_OF_CONDUCT.md (#686)
dfwqdyl-ui — model ID case-sensitivity compatibility report (#729)
Oliver-ZPLiu — stale working... state bug report and Windows clipboard fallback (#738, #850)
reidliu41 — resume hint, workspace trust persistence, Ollama provider support, and thinking-block stream finalization (#863, #870, #921, #1078)
xieshutao — plain Markdown skill fallback (#869)
GK012 — npm wrapper --version fallback (#885)
y0sif — parent turn-loop wakeup after direct child sub-agent completion (#901)
mac119 and leo119 — deepseek update command documentation (#838, #917)
dumbjack / 浩淼的mac — command-safety null-byte hardening (#706, #918)
macworkers — fork confirmation with the new session id (#600, #919)
zero and zerx-lab — notification condition config and richer OSC 9 notification body (#820, #920)
chnjames — cached @mention completions, config recovery polish, and Windows UTF-8 shell output (#849, #927, #982, #1018)
angziii — config safety, async cleanup, Docker hardening, and command-safety fixes (#822, #824, #827, #831, #833, #835, #837)
elowen53 — UTF-8 decoding and deterministic test coverage (#825, #840)
wdw8276 — /rename command for custom session titles (#836)
banqii — .cursor/skills discovery path support (#817)
junskyeed — dynamic max_tokens calculation for API requests (#826)
Hafeez Pizofreude — SSRF protection in fetch_url and Star History chart
Unic (YuniqueUnic) — Schema-driven config UI (TUI + web)
Jason — SSRF security hardening
axobase001 — snapshot orphan cleanup, npm install guards, session telemetry fixes, model-scope cache clear, symlinked skill support, and npm mirror-escape-hatch guidance (#975, #1032, #1047, #1049, #1052, #1019, #1051, #1056)
MengZ-super — /theme command for dark/light toggle and SSE gzip/brotli decompression (#1057, #1061)
DI-HUO-MING-YI — Plan-mode read-only sandbox safety fix (#1077)
bevis-wong — precise paste-Enter auto-submit reproducer (#1073)
Duducoco and AlphaGogoo — skills slash-menu and /skills coverage fix (#1068, #1083)
ArronAI007 — window-resize artifact fix for macOS Terminal.app and ConHost (#993)
THINKER-ONLY — OpenRouter and custom-endpoint model-ID preservation (#1066)
Jefsky — DeepSeek endpoint correction report (#1079, #1084)
wlon — NVIDIA NIM provider API-key preference diagnosis (#1081)

Contributing

See CONTRIBUTING.md. Pull requests welcome — check the open issues for good first contributions.

Support: Buy me a coffee.

[!Note] Not affiliated with DeepSeek Inc.

License

MIT

Rust Binaries on Producthunt daily