DeepSeek Reasonix in action: Build an AI programming agent at zero cost (30-minute tutorial)

Tutorial Objectives

Complete the installation, configuration and practice of DeepSeek Reasonix in 30 minutes. You will learn to use this open source AI programming agent to automatically fix bugs, write functions, and run tests - and because of DeepSeek's prefix-cache mechanism, the cost of long-session input tokens is reduced to 1/5 of the original.

What will you build?

• AI Programming Agent Environment: Terminal native TUI, start anytime, anywhere npx reasonix code
• Cache-first long sessions: 94% cache hit, append-only loops keep costs extremely low
• Skills Automation Script: Use Markdown to write reusable Agent scripts

Preparation list

• DeepSeek API Key (platform.deepseek.com registered to obtain, billed by volume)
• Node.js ≥ 22 (macOS/Linux/Windows are acceptable)
• An existing code project (or create a new demo project to practice)

Overall architecture

Reasonix's loop is append-only: messages and tool results are always appended to the end, and the history is never modified. This keeps DeepSeek's prefix-cache hit after every tool invocation.

Step 1: Install Reasonix and configure API Key

Reasonix does not require global installation. In Node.js ≥ 22 environment, one line of commands can start:

#
cd /path/to/your-project

# （ API Key）
npx reasonix code

， DeepSeek API Key 。 Key ~/.reasonix/config.json ，。

****DeepSeek API —— $0.07/Mtok， $0.014/Mtok。Reasonix append-only 90% ，。

，

#
cat ~/.reasonix/config.json

#
npx reasonix --help

Reasonix （Tauri ）， Node runtime、 tab cost/cache/token ，。——、 CI/CD 。

2 AI

Reasonix ， TUI 。 IDE ——diff git diff， ls，。

，。Reasonix DeepSeek V4-Flash（）， /pro V4-Pro

# Flash（）
> Python

# Pro
/pro
> ，，

Reasonix 、 shell 、。，。

Reasonix bug

utils.py ， parse_config

Reasonix

1. utils.py， parse_config
3. （ try/except os.path.exists ）

，Reasonix ， git diff 。

3 Skills

Skills Reasonix —— Markdown Agent ， .reasonix/skills/ 。

Code Review Skill

.reasonix/skills/code-review.md

---
name: code-review
description: 、
runAs: subagent
allowed-tools: [read, grep, glob]
---

##

。

##

1. **** SQL 、XSS、
2. **** N+1 、、
3. ****（>30 ）、

##

 markdown ，。

Reasonix

/skill code-review
``__TOK28 __read`, `grep`, `glob` Three read-only tools - will not modify any code, ensuring the independence of the review.

### More Skill Examples

You can create various Skills:

- **Generate CHANGELOG**: Read git log and automatically generate version update log
- **Run Test + Fix**: Run the test first and automatically fix the code for failed use cases
- **API document generation**: scan routing files and generate OpenAPI documents

Skills are plain text Markdown that can be submitted to the git repository, and team members share the same set of Agent scripts.

## Step 4: Access the MCP extension tool chain

Reasonix provides first-class citizen support for MCP (Model Context Protocol) and supports three transmission protocols: stdio, SSE, and Streamable HTTP.

### Mount an MCP Server

```bash

# GitHub MCP Server
npx reasonix code --mcp "github=npx @anthropic/mcp-server-github"

# MCP Server
npx reasonix code --mcp "fs=npx @anthropic/mcp-server-filesystem /path/to/allowed/dir"

~/.reasonix/config.json

{
  "mcp": {
    "github": {
      "command": "npx",
      "args": ["@anthropic/mcp-server-github"]
    },
    "filesystem": {
      "command": "npx",
      "args": ["@anthropic/mcp-server-filesystem", "/home/user/projects"]
    }
  }
}

MCP server Reasonix registry，。 GitHub MCP ，" PR"——Reasonix GitHub 。

（FAQ）

Q1npx reasonix code "Node version too old"？

Node.js ≥ 22。 node -v ， nvm

nvm install 22
nvm use 22

Q2API Key ？

~/.reasonix/config.json apiKey 。

export DEEPSEEK_API_KEY="sk-xxxxxxxxxxxxxxxx"

Q3 token 1/5？

。Reasonix append-only DeepSeek prefix-cache 、 marker ，。（50+ ） 90%+， token 1/5～1/4。

Q4Reasonix Claude Code ？

Claude Code Anthropic Agent， Claude API。Reasonix DeepSeek ，（DeepSeek + Reasonix Cache-First ）。—— Reasonix（）， Claude Code（）。

（）

， tools hover-card DeepSeek、Reasonix、Claude Code、Node.js

Reference video/material

• Reasonix
• GitHub: esengine/DeepSeek-Reasonix
• DeepSeek API

Internal link guidance

• Someone has successfully practiced it: He used Claude Code + AWS to build AI SaaS, and his monthly income was $12,000 for 3 months
• Someone has successfully practiced it: Claude Code 48 hours to start a business: one person + US$29 monthly fee, monthly income in 3 months $9,000

DeepSeek topic related tutorials

• DeepSeek R2 Review: 1.7T Params vs GPT-5 Benchmarks
• DeepSeek V4 vs Claude Code: 90% Cheaper, Same Quality
• Claude Code + DeepSeek V4 Building Tutorial: API Fees Dropped by 90% (15 Minutes)
• Running a 70B large model locally is not a dream: Intel AutoRound quantitative practical tutorial