DeepSeek TUI — Your Terminal Becomes a DeepSeek-Powered Coding Agent

DeepSeek TUI is a terminal-native coding agent — a single compiled Rust binary that talks to the DeepSeek API. You type prompts into a terminal interface, and the agent can read and edit files, execute shell commands, manage git branches, search the web, and call out to MCP servers for extra capabilities. It is not a terminal emulator (that's Warp) and not a chat bot (that's the DeepSeek web app). It's a tool-using agent that lives in your terminal.

The project was created by independent developer Hunter Bown and is not affiliated with DeepSeek Inc. It has grown quickly through community contributions — 28 PRs from a single contributor in one release cycle — and supports English, Japanese, Simplified Chinese, and Brazilian Portuguese out of the box.

The easiest route for most developers is npm. The npm package is a thin installer that downloads the matching prebuilt binary — it does not add a Node.js runtime dependency to the tool itself. If you do not have Node.js, use Cargo or download a binary directly from GitHub Releases.

For users in mainland China, prebuilt binaries can use the DEEPSEEK_TUI_RELEASE_BASE_URL environment variable to point at a mirror, and Cargo users can configure the TUNA (Tsinghua) registry mirror for faster crate downloads.

On first launch you will be prompted for a DeepSeek API key. You can also set it explicitly. The key is stored in ~/.deepseek/config.toml — never commit this file. Project-specific overrides go in <workspace>/.deepseek/config.toml (api_key and base_url are denied at the project level for security).

By default the tool targets the official DeepSeek API. It also supports NVIDIA NIM, Fireworks, and self-hosted SGLang deployments as alternative providers.

DeepSeek TUI gives you three escalating levels of autonomy. You cycle between them with Tab in the TUI, or pass them as flags on the command line.

Plan mode is read-only exploration — the agent can search and read files, but cannot modify anything. Use it to understand unfamiliar code or to let the agent survey a repo before you grant it write access.

Agent mode is the default interactive setting. The agent proposes actions (edit a file, run a command, create a branch) and you approve or deny each one. This is the sweet spot for most development work — you stay in control while the agent does the heavy lifting.

YOLO mode auto-approves every tool call. It is fast but risky. Only use it for well-defined, low-stakes tasks where you trust the outcome, like running a linter you have already configured or applying a repetitive find-and-replace across known files.

One of the most interesting features is RLM (rlm_query), which farms out 1–16 cheap deepseek-v4-flash child agents to analyze a problem in parallel. The Pro model orchestrates the overall strategy; Flash workers handle the parallel grunt work. This is the "Pro does the big job, Flash does the small jobs" architecture the tool was designed around.

The practical result: you get the reasoning depth of Pro at a fraction of the cost, because the expensive model only coordinates while the cheap model runs the parallel workstreams. This is ideal for codebase-wide refactors, multi-file bug investigations, and batch code reviews.

DeepSeek V4 Pro supports adjustable reasoning depth. Press Shift+Tab in the TUI to cycle through off → high → max. Recent 0.8.x releases also document an auto mode that picks the reasoning tier based on the prompt content — short factual questions get no extra reasoning, while complex debugging prompts can get deeper reasoning.

This is not a gimmick. Turning reasoning off for simple questions saves tokens and latency. Cranking it to max for hard problems gives the model space to work through multi-step logic before answering.

DeepSeek TUI ships with a typed tool registry covering the full development workflow. Every tool call is logged and auditable.

Skills are directories containing a SKILL.md file with frontmatter (name + description). They are composable, installable from GitHub, and require no backend service. The agent can auto-select skills based on task descriptions via the load_skill tool.

Discovery order: .agents/skills → skills → .opencode/skills → .claude/skills → ~/.deepseek/skills. This means existing Claude Code skills work in DeepSeek TUI without modification — just symlink or copy them into the discovery path.

Every turn is automatically snapshotted via a side-git mechanism — a separate git repository that tracks workspace state without touching your project's .git directory. If the agent makes a mess, /restore rolls back to the previous snapshot. The revert_turn tool can undo a single turn without losing the entire session.

Sessions can be saved and resumed later. Long-running sessions support intelligent context compaction that preserves important state while dropping stale turns to stay within token limits. A durable task queue survives restarts for background work.

DeepSeek TUI displays live per-turn and session-level token usage with cache hit/miss breakdowns. You always know what you are spending. Under the current promotional pricing (through May 31, 2026), DeepSeek V4 Pro costs $0.435/1M input tokens (cache miss) and $0.87/1M output tokens — roughly 1–5% of comparable Claude usage — and cache-hit input drops to just $0.003625/1M tokens.

The RLM feature is designed around this cost structure: Pro coordinates (expensive but brief), Flash workers execute in parallel (cheap and fast). The prefix-cache optimization keeps repeated system prompts and tool definitions in cache, so you only pay the full input rate once per session.

The TUI has a shallow learning curve. These are the shortcuts that matter most. Press F1 anytime for a searchable help overlay.

DeepSeek TUI and Claude Code occupy the same category — terminal coding agents — but make different trade-offs. DeepSeek TUI wins on context window (1M vs ~200K tokens) and cost (1–5% of Claude's per-token price). Claude Code wins on reasoning depth and ecosystem maturity — it ships as a first-party Anthropic product with deeper integration into the Claude model family.

A practical take: if you are doing large-context work (whole-codebase analysis, multi-file refactors, batched reviews), DeepSeek TUI's 1M-token window and parallel Flash workers give you capabilities Claude Code cannot match at any price. For narrower, deeper reasoning tasks, Claude Code's model quality edge still matters.

The two are not mutually exclusive. Several teams run both: DeepSeek TUI for broad, parallel, cost-sensitive work, and Claude Code for tight, reasoning-heavy tasks.