@huangjinbo: Reasonix is truly excellent. Don't be misled by its project name (DeepSeek-Reasonix). As long as the relay supports OpenAI-compatible, it can be supported... Recommending again. Mainly its skills, memory, Hooks, MCP and other features are all very useful... It was used to…
Summary
Reasonix (formerly named DeepSeek-Reasonix) is an AI coding agent CLI tool developed in Go, supporting features like skills, memory, Hooks, MCP, etc., and can replace OpenCode.
View Cached Full Text
Cached at: 06/16/26, 07:41 PM
English · Simplified Chinese · Guide · Spec · Website · 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.
MIT — see LICENSE Built by the community at esengine/DeepSeek-Reasonix
Similar Articles
@GithubProjects: Reasonix is a terminal-based AI coding agent built specifically for DeepSeek, designed to keep token costs low through …
Reasonix is a terminal-based AI coding agent optimized for DeepSeek models, achieving 99.82% cache hit rate and reducing token costs from ~$61 to ~$12 per workload through stable prefix caching.
@NFTCPS: Holy cow! DeepSeek is trying to sweep all the Agents off the market, giving you the whole family bucket! Even Reasonix didn't escape, directly acquired. To put it in plain English: This is the native terminal that can save you the most on your DeepSeek bill. Tool calls are rock solid, no glitches. Relying on cache hits, it slashes API costs down to your ankles—broken bones don't even describe it.
DeepSeek-Reasonix is a native terminal AI coding agent based on DeepSeek, drastically reducing API costs through cache hits, with stable and reliable tool calls.
@QingQ77: A terminal AI coding agent designed specifically for DeepSeek API prefix caching mechanism, maintaining ultra-low token costs in long sessions through a cache-first architecture. https://github.com/esengine/DeepSeek-Reasonix… Reaso…
Reasonix is a terminal AI coding agent designed specifically for DeepSeek API prefix caching mechanism, achieving ultra-low token costs in long sessions through a cache-first architecture. In testing, 435 million input tokens cost only about $12, with a cache hit rate of 99.82%.
@Xudong07452910: Open source project recommendation: loop-engineering — a practical framework that gives your AI coding agent self-looping and intelligent orchestration capabilities. loop-engineering is a very popular concept right now, offering practical patterns, starters, and CLI tools to help developers design systems…
loop-engineering is an open-source framework that provides self-looping and intelligent orchestration capabilities for AI coding agents (such as Claude Code, Codex, Cursor). It includes 7 production-grade loop patterns, practical CLI tools, and a five-data-block design, helping developers transition from manual prompting to systematic automation.
@AYi_AInotes: https://x.com/AYi_AInotes/status/2066865618104586525
This is a panoramic analysis of OpenAI Codex, detailing its architecture (five entry points), three layers of extensibility (MCP, Skills, Plugins), a horizontal comparison with Claude Code, Cursor, and Devin, and seven best practices that can be directly adopted.