登录 注册
开发者工具AI 应用与 AI Agent网站与 SaaS 工具 aicodegencoding-assistantcoding-languagedeveloper-experiencedeveloper-tools
33,937
Stars
1,796
Forks
182
Watchers
348
Open Issues
NOASSERTION
许可证
Rust
语言
2023-03-16
创建时间
2026-06-30
最近更新

项目能做什么

支持自托管的 AI 代码辅助工具。
来源:基于仓库元数据 · 内容以仓库实际 README 为准

使用说明 查看原始 README 原仓库文档

中文使用说明暂未生成。下面保留原仓库 README 摘录,命令与配置均以原文为准。
原始 README 摘录(英文原文,节选前 3000 字符)
<div align="center">
  
# 🐾 Tabby

[📚 Docs](https://tabby.tabbyml.com/docs/welcome/) • [💬 Slack](https://links.tabbyml.com/join-slack) • [🗺️ Roadmap](https://tabby.tabbyml.com/docs/roadmap/)

[![latest release](https://shields.io/github/v/release/TabbyML/tabby)](https://github.com/TabbyML/tabby/releases/latest)
[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](https://makeapullrequest.com)
[![Docker pulls](https://img.shields.io/docker/pulls/tabbyml/tabby)](https://hub.docker.com/r/tabbyml/tabby)
[![codecov](https://codecov.io/gh/TabbyML/tabby/graph/badge.svg?token=WYVVH8MKK3)](https://codecov.io/gh/TabbyML/tabby)

[English](/README.md) |
[简体中文](/README-zh.md) |
[日本語](/README-ja.md)

</div>

Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features:
* Self-contained, with no need for a DBMS or cloud service.
* OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE).
* Supports consumer-grade GPUs.

<p align="center">
  <a target="_blank" href="https://tabby.tabbyml.com"><img alt="Open Live Demo" src="https://img.shields.io/badge/OPEN_LIVE_DEMO-blue?logo=xcode&style=for-the-badge&logoColor=green"></a>
</p>

<p align="center">
  <img alt="Demo" src="https://user-images.githubusercontent.com/388154/230440226-9bc01d05-9f57-478b-b04d-81184eba14ca.gif">
</p>

## 🔥 What's New
* **12/12/2025** Get your GitHub issues implemented by connecting them to [Pochi](https://github.com/TabbyML/pochi) tasks and create PRs directly from the sidebar with a breakdown of CI/Lint/Test results [vscode@0.20.0](https://github.com/TabbyML/pochi/releases/tag/vscode%400.20.0).
* **07/02/2025** [v0.30](https://github.com/TabbyML/tabby/releases/tag/v0.30.0) supports indexing GitLab Merge Request as Context! 
* **05/25/2025** 💡Interested in joining [Agent](https://links.tabbyml.com/pochi-github-readme) private preview? DM in [X](https://x.com/getpochi) for early waitlist approval!🎫
* **05/20/2025** Enhance Tabby with your own documentation📃 through REST APIs in [v0.29](https://github.com/TabbyML/tabby/releases/tag/v0.29.0)! 🎉
* **05/01/2025** [v0.28](https://github.com/TabbyML/tabby/releases/tag/v0.28.0) transforming Answer Engine messages into persistent, shareable Pages
* **03/31/2025** [v0.27](https://github.com/TabbyML/tabby/releases/tag/v0.27.0) released with a richer `@` menu in the chat side panel.


<details>
  <summary>Archived</summary>

* **02/05/2025** LDAP Authentication and better notification for background jobs coming in Tabby [v0.24.0](https://github.com/TabbyML/tabby/releases/tag/v0.24.0)!✨
* **02/04/2025** [VSCode 1.20.0](https://marketplace.visualstudio.com/items/TabbyML.vscode-tabby/changelog) upgrade! @-mention files to add them as chat context, and edit inline with a new right-click option are available!
* **01/10/2025** Tabby [v0.23.0](https://github.com/TabbyML/tabby/releases/tag/v0.23.0) featuring e
阅读完整原文

项目深度分析 规则生成(AI 未配置)

综合评分 63.7 分。该项目在“个人可实施性”维度得 35 分,“付费可能性”维度得 64.0 分,差异化空间 100.0 分(评分依据见评分卡)。

将 tabby 改造为垂直场景 SaaS

产品构想保留核心能力,针对某一类用户(如某行业团队)做托管版,收取月费。
目标用户有该需求的中小团队 / 独立站长
难度/周期较高 · 2~4 周(MVP)
收费模式订阅制(如 ¥29~99/月)
竞争风险需验证付费意愿;注意许可证合规
依据 数据支持的判断:许可证与关键词显示存在商用与付费场景

面向细分需求的二次开发产品

产品构想基于 tabby 的核心能力,聚焦一个更窄的场景(如某平台、某行业)做差异化。
目标用户该细分场景用户
难度/周期中 · 2~6 周
收费模式买断制 / 订阅制 / 广告
竞争风险细分需求规模需验证
依据 AI 推测:基于项目主题标签的判断
以上为规则引擎基于仓库公开数据生成的参考结论,包含推测成分,不构成投资或创业承诺;配置 AI 后可获得更深入的分析。
报告会保存到 个人中心

竞品与相似项目 GitHub Search 真实检索

相似项目数据正在完善中,暂不展示(避免误导)

项目优势与风险

技术成熟度创建于 2023-03-16,最近推送 2026-06-30,发布过 100 个 Release
社区活跃Star 33,937 / Fork 1,796 / Issue 348(数据支持,可自行核实)
许可证NOASSERTION
主要风险上游项目方向可能变化;同赛道竞争者较多(见竞品表);热度与需求不完全等价

安装与使用

此项目未提供 Docker 镜像,安装步骤以原仓库 README 为准(涉及依赖安装与环境配置,对新手门槛较高)。