cerebrixos-org/tuning-engines-cli

Name: cerebrixos-org/tuning-engines-cli
Author: cerebrixos-org

Plugin插件 Native原生 ⭐ 6 MIT Models & Routing模型与路由 Dev Workflow开发与代码工作流

用于调优引擎的CLI与MCP服务器——在代码库上对大型语言模型进行微调

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

This repository provides the command line interface (CLI) and Model Context Protocol (MCP) server for Tuning Engines, a governed AI runtime for managing model, agent, skill, and MCP workflows across multiple environments. It offers a single OpenAI-compatible API for routing inference requests across different models, and includes built-in support for role-based access control, traffic policies, approval requests for high-risk actions, and usage tracing. It also supports integration with popular orchestration frameworks like LangGraph and Temporal, and enables domain-specific fine-tuning for open-source LLMs using LoRA.

It is built for AI developers and DevOps teams that need to fine-tune custom domain models and govern their AI inference workflows at scale. To get started, users can install the CLI globally via npm or run it directly without installation using the npx command. After completing the browser-based authentication flow, users can add billing credits, estimate training costs, select a fine-tuning agent and base model, specify their target data repository, launch the job, and monitor progress in real time.

The project is distributed under the open-source MIT license, and requires a pre-installed Node.js environment to run. After installation, first-time users run te auth login which opens a browser to complete the device authorization flow, similar to GitHub CLI’s authentication process. Access tokens are saved locally to ~/.tuningengines/config.json with 0600 file permissions to keep credentials secure, and the CLI supports all popular open-source code-focused large language models.

这是面向Tuning Engines平台的命令行界面（CLI）和MCP服务器，Tuning Engines是一个受治理的AI运行时，可管理模型、智能体、技能和MCP工作流。它提供统一的OpenAI兼容API处理推理路由，支持RBAC访问控制、流量策略、高风险操作审批、使用追踪，还可对接LangGraph、Temporal等主流编排框架，同时支持开源大模型的领域特定LoRA微调。

它主要面向AI开发人员和运维团队，可用于从代码仓库生成训练数据、微调适配特定场景的代码大模型。典型工作流是先通过npm全局安装CLI，完成浏览器授权登录后，添加计费额度，预估训练成本，再选择对应领域智能体和基础模型，指定目标仓库，启动微调任务，之后可实时监控进度，管理训练好的模型。

该项目基于Node.js开发，采用MIT许可协议，属于免费开源项目。使用前需要预先安装Node.js环境，既可以通过npm全局安装，也可以用npx直接运行。首次运行需要通过浏览器完成授权登录，令牌会以0600权限保存在本地配置文件中，支持当前主流的多款开源代码大模型。

View on GitHub在 GitHub 查看

Send to your DSH发给你的 DSH 安装

请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：tuning-engines-cli（cerebrixos-org/tuning-engines-cli）
仓库：https://github.com/cerebrixos-org/tuning-engines-cli
本站详情页：https://www.yhbd.top/plugins/cerebrixos-org-tuning-engines-cli/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 6 · 最近提交 2026-08-18 · 主语言 TypeScript

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意

Only 6 stars - very few users, little community feedback星标只有 6，几乎没人在用，遇到问题缺少社区反馈

DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装

dsh plugin --profile default add tuningengines-cli

把 cerebrixos-org/tuning-engines-cli 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

35.7 KB · 缓存于 2026-08-23 03:41:44 · 35.7 KB

Tuning Engines CLI & MCP Server

Govern every AI workflow through one API.

Tuning Engines is a governed AI runtime for model, agent, skill, and MCP workflows. Route inference through one OpenAI-compatible API, apply RBAC and traffic policies, request approvals for high-risk actions, inspect traces and usage, and connect durable orchestration frameworks such as LangGraph and Temporal. The same CLI and MCP server also manage domain-specific fine-tuning of open-source models.

Training Agents

Tuning Engines uses specialized agents that control how your data is analyzed and converted into training data. Each agent produces a different kind of domain-specific fine-tuned model optimized for its use case. Current agents focus on code, with more coming for customer support, data extraction, security review, ops, and other domains.

Cody (`code_repo`) — Code Autocomplete Agent

Cody fine-tunes on your GitHub repo using QLoRA (4-bit quantized LoRA) via the Axolotl framework (HuggingFace Transformers + PEFT). It learns your codebase's patterns, naming conventions, and project structure to produce a fast, lightweight adapter optimized for real-time completions.

Best for: code autocomplete, inline suggestions, tab-complete, code style matching, pattern completion.

te jobs create --agent code_repo \
  --base-model Qwen/Qwen2.5-Coder-7B-Instruct \
  --repo-url https://github.com/your-org/your-repo \
  --output-name my-cody-model

SIERA (`sera_code_repo`) — Bug-Fix Specialist

SIERA (Synthetic Intelligent Error Resolution Agent) uses the Open Coding Agents approach from AllenAI to generate targeted bug-fix training data from your repository. It synthesizes realistic error scenarios and their resolutions, then fine-tunes a model that learns your team's debugging style, error handling conventions, and fix patterns.

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 cerebrixos-org/tuning-engines-cli 的 README.md。在 GitHub 查看原文 →