← Discover
Discover · GitHub · DeepSeek-Reasonix↑ +333 today

AI coding agent for terminal

DeepSeek-Reasonix is ​​an AI coding agent that runs on the terminal and is based on DeepSeek models. Focusing on prefix-cache stability, this tool ensures developers receive uninterrupted coding support over long sessions.

Updates

  • September 18, 2026: Stars 35,572 → 35,597, latest release desktop-v1.38.10 (September 18, 2026).
  • September 16, 2026: Stars 35,509 → 35,572, latest release desktop-v1.38.3 (September 9, 2026).
  • September 12, 2026: Stars 35,497 → 35,509, latest release desktop-v1.38.7 (September 11, 2026).
  • September 11, 2026: Stars 35,461 → 35,497, latest release desktop-v1.38.6 (September 11, 2026).

What you get

  • Provides long-term uninterrupted coding support with DeepSeek models.
  • It offers low-cost session management with its prefix caching feature.
  • It provides flexible use via the terminal with configurable plug-in support.

Installation

Installation via NPM or Homebrew
npm i -g reasonix                  # any OS; pulls the prebuilt native binary
brew install esengine/reasonix/reasonix   # macOS
Compiling from source code
git clone https://github.com/esengine/DeepSeek-Reasonix.git
cd DeepSeek-Reasonix
make build      # -> bin/reasonix(.exe)
make cross      # -> dist/ (darwin|linux|windows × amd64|arm64)

Running it

Configuration and initialization
reasonix setup                      # configure a provider and model
reasonix                            # start an interactive session
reasonix run "implement the TODOs in main.go"

If you don't write code

🤖 Paste this into your AI agent (Claude Code · Codex · Antigravity)

While working with this artificial intelligence coding agent running on the terminal, develop code suggestions taking into account the current structure and goals of my project. Focus on producing consistent, low-cost responses across our long sessions using prefix cache stability. When writing or debugging code, provide modular and clean solutions that fit the needs of the project.

Related dictionary terms

TerminalArtificial Intelligence
Who it is forIt is for software developers working in a terminal environment who want to automate their coding processes and receive artificial intelligence support in long-term projects.
LicenseMIT

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-08-03: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. This page was machine-translated from the Turkish original · the Turkish version prevails.