隐私与广告选择
Git-Stars 会使用必要存储来保障网站运行。可选分析和广告测量脚本默认不加载，只有在你同意后，Google 等合作伙伴才可能按要求使用 Cookie 或类似标识符。 隐私政策
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
这个仓库详情页已经具备足够的原创分析、来源证据和同类对比，可以作为 Git-Stars 的可索引评测页。
100
评测分
解决的问题
It addresses the high token cost and latency of long-running AI coding sessions by optimizing for prefix-cache stability, which reduces repeated computation and cost. It also solves the rigidity of many AI agents by being fully config-driven and plugin-driven, allowing users to define providers, tools, and models in a TOML file without writing new code.
部署现实
当前可用的安装信号是：npm i -g reasonix。这只能作为起点，正式使用前建议让 Codex 或 Claude 检查 README、环境变量、运行时版本和部署目标。
商业可用性
当前记录的许可证是 MIT。这是重要的商业使用信号，但仍应核验许可证全文、依赖许可证、模型/API 条款和商标限制。
能力上限
Developers can build a versatile AI coding assistant that integrates with any OpenAI-compatible API, run dual-model setups (executor + planner) for complex tasks, and extend functionality via MCP-compatible plugins. Real-world uses include automated code generation, refactoring, debugging, and repository-level analysis directly in the terminal. The ceiling is high: it can be tailored to any workflow, from simple autocomplete to multi-step autonomous coding tasks, with cost-efficient long sessions.
Git-Stars 是独立产品，不隶属于 GitHub 或该项目。 分析可能由 AI 辅助生成，依据公开仓库元数据和 README 的短摘要。 我们不镜像完整 README、文档、Issue 或社媒评论。
esengine/DeepSeek-Reasonix 被追踪为 Go 项目，主要属于 LLM Tool, AI Agent, Developer Tool, UI Framework 方向。这个评估结合公开 GitHub 元数据、分类信号、短来源摘要和 Git-Stars 编辑规则，而不是复制项目文档。
增长检查：该仓库目前有 34k Star，今日 +0，本周 +2.4k，本月 +0。这些窗口用于区分持续采用信号和短期曝光峰值。
维护检查：当前活跃度为 一般；最近一次推送距今 61 天，未关闭 Issue 为 1.4k，约占总 Star 的 4.00%。这只是采用信号，不替代工程尽调。
采用检查：2.3k Fork 和 34k Watcher 反映项目被复用和关注的程度。许可证信号：MIT。商业或内部使用前请核验许可证兼容性。
适用判断：当你需要「AI 原型、LLM 工作流和 Agent 类应用」时，这个项目更值得评估；如果「无法接受较大的未解决 Issue 队列」，则需要谨慎。
来源检查：Git-Stars 当前为这份报告保留了 2 个明确来源引用，近期增长信号为 2.4k。最终安装、安全和版本信息仍应以原始 GitHub 仓库为准。
原创分析
充分已经具备问题、能力和结论层面的原创判断。
来源
充分已附带仓库元数据和 README/来源引用。
许可证
充分已记录 MIT，可作为评估依据。
维护
充分仓库元数据中可以看到近期活跃信号。
同类对比
充分已有足够相近项目用于对比。
热度
34k 星标
复用
2.3k 复刻
关注
34k 关注者
维护
moderate
许可证
MIT
未解决 Issue
1.4k
Reasonix is a DeepSeek-native AI coding agent for the terminal, built as a config- and plugin-driven harness in a single static Go binary. It is tuned around DeepSeek's prefix cache to keep token costs low across long sessions, and supports multiple models, plugins, and editor integrations.
核心特性
- Config-driven: providers, agent, tools, and plugins declared in reasonix.toml. - Multi-model & composable: supports DeepSeek preset and any OpenAI-compatible endpoint, with optional executor+planner dual-model sessions. - Plugin-driven: external tools via stdio JSON-RPC (MCP-compatible), built-in tools self-register. - Cache-aware context maintenance: stable environment summary, stale tool output pruning, and documented tool schema. - Zero-friction distribution: single static binary, cross-compiles to six targets, only dependency is a TOML parser.
LLM Tool
Libraries and tools for LLM apps, RAG, prompts, and evals
AI Agent
Agent frameworks, autonomous workflows, and tool-use systems
Developer Tool
Tools that improve coding, testing, build, and local workflow
UI Framework
Frontend frameworks, design systems, and interface libraries
npm i -g reasonix70
健康评分
一般
提交活跃度
Apr 21, 2026
创建于
Aug 14, 2026
最近提交
每日同步积累数据后，Star 历史将在此显示。
复刻
未解决
关注者
esengine
GitHub 主页codecrafters-io/build-your-own-x
Master programming by recreating your favorite technologies from scratch.
sindresorhus/awesome
😎 Awesome lists about all kinds of interesting topics
freeCodeCamp/freeCodeCamp
freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.
EbookFoundation/free-programming-books
:books: Freely available programming books
nilbuild/developer-roadmap
Interactive roadmaps, guides and other educational content to help developers grow in their careers.
✓
许可证
✓
Fork 情况
~ 一般
维护情况
解决的问题
It addresses the high token cost and latency of long-running AI coding sessions by optimizing for prefix-cache stability, which reduces repeated computation and cost. It also solves the rigidity of many AI agents by being fully config-driven and plugin-driven, allowing users to define providers, tools, and models in a TOML file without writing new code.
能力范围
Developers can build a versatile AI coding assistant that integrates with any OpenAI-compatible API, run dual-model setups (executor + planner) for complex tasks, and extend functionality via MCP-compatible plugins. Real-world uses include automated code generation, refactoring, debugging, and repository-level analysis directly in the terminal. The ceiling is high: it can be tailored to any workflow, from simple autocomplete to multi-step autonomous coding tasks, with cost-efficient long sessions.
结论
Reasonix is ideal for developers who want a cost-effective, configurable AI coding agent that integrates deeply with DeepSeek or any OpenAI-compatible API, especially for long, continuous sessions. It may not suit those who prefer a fully managed, out-of-the-box solution or who are not comfortable with TOML configuration and plugin management. The key trade-off is its DeepSeek-centric optimization versus broader provider flexibility.