GraphCanon

DeepSeek-Reasonix

esengine/DeepSeek-Reasonix

DeepSeek-native AI coding agent for your terminal.

GitHub Website
26k
Stars
1.6k
Forks
1.0k
Open issues
74
Watchers
Go MITLast pushed Jul 7, 2026

Overview

DeepSeek-Reasonix is an advanced AI agent implemented in Go, designed to provide coding assistance via a command-line interface. It features prompt caching and stability optimizations focused on a prefix cache strategy.

Categories

Developer ToolsAI Agents

Tags

terminaltuideepseekagentdeveloper-toolscliai-agent

Similar tools

ECC

affaan-m/ECC

The agent harness performance optimization system

227k 35kJavaScript

hermes-agent

NousResearch/hermes-agent

The self-improving AI agent built by Nous Research

211k 39kPython

AutoGPT

Significant-Gravitas/AutoGPT

AutoGPT: Build, Deploy, and Run AI Agents

185k 46kPython

ollama

ollama/ollama

Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

176k 17kGo

prompts.chat

f/prompts.chat

The world's largest open-source prompt library for AI

165k 21kHTML

JavaGuide

Snailclimb/JavaGuide

Snailclimb/JavaGuide: 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发

157k 46kJavaScript

Install

go get github.com/esengine/DeepSeek-Reasonix
pkg.go.dev Docs / website

README

English  ·  简体中文  ·  Guide  ·  Spec  ·  Website  ·  Discord

[!IMPORTANT] Reasonix 1.0 is a ground-up rewrite in Go — this branch (main-v2) is the new default and where development happens now. The earlier 0.x TypeScript releases are legacy, living on the v1 branch (maintenance only). See the migration guide. npm i -g reasonix stays the install command — 1.0.0+ delivers the Go binary, 0.x is the legacy TS build.

npm version CI license downloads GitHub stars AtomGit stars contributors Discussions Discord


A DeepSeek-native AI coding agent for your terminal.

A config- and plugin-driven harness — a single static Go binary, tuned around DeepSeek's prefix cache so token costs stay low across long sessions.


[!IMPORTANT] Community · 加入社区 — bilingual Discord for setup help (#help / #求助), workflow showcases, and feature ideas. → https://discord.gg/XF78rEME2D


Features

  • Config-driven. Providers, the agent, enabled tools, and plugins are all declared in reasonix.toml. No hardcoded models.
  • Multi-model & composable. DeepSeek ships as a preset; any OpenAI-compatible endpoint is a config entry, not new code. Optionally run two models together (executor + planner) in separate, cache-stable sessions.
  • Plugin-driven. External tools run as subprocesses over stdio JSON-RPC (MCP-compatible). Built-in tools self-register at compile time.
  • Cache-aware context maintenance. Startup injects a small stable environment summary, stale tool output is snipped/pruned before summary compaction, and the