khoj

khoj-aiAGPL-3.0活跃维护 有专家点评

可自托管的个人 AI 第二大脑,能从网页和本地文档中检索答案,支持自定义智能体、定时自动化和深度研究,兼容多种在线或本地大模型。

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.

2.0.0-beta.28发布于 2026-03-26 03:36 UTC38,102star +69 / 7 天2,543fork同步于 2026-11-10 23:22 UTC

专家点评

上手难度:进阶更新于 2026-11-11

自托管的个人知识库 RAG 层,把散在 PDF、Notion、org-mode 里的笔记变成可对话的检索入口

适用场景

  • 个人笔记检索:Obsidian、Logseq、org-mode 里积累了几千条笔记,想用自然语言问「上次那个方案写在哪」,而不是靠关键词搜索;换纯向量库方案就得自己搭 UI 和 LLM 编排。
  • 离线或内网环境:数据不能出机器,用 llama.cpp 接本地模型跑完整检索问答链路;换 SaaS 类第二大脑产品直接出局。
  • 定时简报:让它在固定时间扫一遍指定知识源,生成摘要推到邮箱,替代自己写 cron 加脚本拼 LLM 调用。
  • 多模型对比:同一份知识库挂不同后端(本地 qwen 和在线 API 各一套),比较检索问答质量,不用为每个模型重搭一套 RAG。

踩坑

  • 自托管部署门槛:README 没给安装命令,只指向 docs,实际要按官方文档走一遍配置;想 clone 完直接跑的人会卡在这里。
  • 在线模型接入的配置限制:issue 里「Allow Custom URL for OpenAI API」被反复提出,说明想接自建 OpenAI 兼容端点(vLLM、one-api 之类)时,默认配置未必直接支持,需要确认当前版本是否已放开。
  • 多用户和认证:issue 里有自定义 OAuth2 多用户认证的诉求,说明默认部署形态偏单人自用;要给团队共享实例,认证层得自己补。
  • 硬件要求没写清:issue 里专门有人要求「Document recommend system requirements」,本地模型跑多大参数、要多少内存,README 层面拿不到答案,得自己去文档或实测。

同类对比

同类可看 AnythingLLM、Open WebUI 的 RAG 功能,或纯检索层用 LlamaIndex、Haystack 自己拼。分流点在于:只要文档问答不想要 agent 和定时任务,轻量方案更省事;反过来要跨多个笔记源加定时自动化,Khoj 的整合度更高。

怎么上手

由 README 提炼,执行前请确认
README 未给出具体安装命令,仅指向 https://docs.khoj.dev/get-started/setup
硬件要求按 README 说明

README 未说明

下载:源码 zip·GitHub Releases(安装包)本站不镜像安装包

项目说明

由 README 自动翻译提炼

自托管的个人 AI 第二大脑,从网页和文档中检索答案并构建自定义智能体

可自托管的个人 AI 第二大脑,能从网页和本地文档中检索答案,支持自定义智能体、定时自动化和深度研究,兼容多种在线或本地大模型。

核心能力

  • 接入本地或在线 LLM,如 llama3、qwen、gpt、claude、gemini
  • 从 PDF、Markdown、Word、Notion、org-mode 等文档中检索答案
  • 创建带自定义知识、人设、模型和工具的智能体
  • 用语义搜索快速定位相关文档
  • 定时生成个人简报和智能通知并发送到邮箱

容易踩的坑

自托管步骤需查阅官方文档,README 未直接给出命令;使用在线 LLM 需自备对应 API 密钥

内容由模型根据 README 生成,可能不完整或不准确,以官方文档为准。看原文 README

最近发版

5 个版本2.0.0-beta.28
  1. 2.0.0-beta.28最新正式版2026-03-26 · 2026-03-26 03:36 UTC

    🛠️ Fix

    • Fix using web app after disabling memories for users who never set chat model by @majiayu000 in https://github.com/khoj-ai/khoj/pull/1296
    • Fix showing deprecation banner on Khoj cloud by @debanjum in fdd5fd8f7

    Full Changelog: https://github.com/khoj-ai/khoj/compare/2.0.0-beta.27...2.0.0-beta.28

  2. 2.0.0-beta.272026-03-25 · 2026-03-25 20:12 UTC
    查看更新说明

    🛠️ Fix

    • Fix Khoj web app page templates to be compatible with Starlette 1.0.0 by @debanjum in a19e7acd5

    Full Changelog: https://github.com/khoj-ai/khoj/compare/2.0.0-beta.26...2.0.0-beta.27

  3. 2.0.0-beta.262026-03-25 · 2026-03-25 15:09 UTC
    查看更新说明

    🧪 Improve

    • Faster, more reliable web app experience with Next.js 15 upgrade in a9749c718
    • Add Banner to notify Khoj cloud users about the upcoming cloud deprecation by @debanjum in f7bce4893
    • Disable subscribing to Khoj cloud from web app settings page by @sabaimran in b864cb1f3

    🛠️ Fix

    • Fix memories not loading on the web app Settings page in 0b8cf5112
    • Fix research agent occasionally stopping earlier than it should by @jnMetaCode in #1271
    • Fix Khoj sometimes ignoring content it already fetched from web pages by @jnMetaCode in #1269
    • Fix PDF files failing to process in some cases in by @BillionClaw in #1292
    • Make loading ChatModel name more robust by @yang1002378395-cmyk in #1277
    • Fix memory leaks when reading org-mode files by @buley in #1284

    New Contributors

    Full Changelog: https://github.com/khoj-ai/khoj/compare/2.0.0-beta.25...2.0.0-beta.26

  4. 2.0.0-beta.252026-02-22 · 2026-02-22 20:00 UTC
    查看更新说明

    What's Changed

    New Contributors

    Full Changelog: https://github.com/khoj-ai/khoj/compare/2.0.0-beta.24...2.0.0-beta.25

  5. 2.0.0-beta.242026-01-02 · 2026-01-02 04:01 UTC
    查看更新说明

    🧪 Improve

    • Render mermaid diagram wrapped in markdown codeblocks on web app

    🛠️ Fix

    • Fix subscriptions failures
    • Fix AI interacting with user files in code sandbox

    Full Changelog: https://github.com/khoj-ai/khoj/compare/2.0.0-beta.23...2.0.0-beta.24

用户点评

登录用户的真实使用记录,可按版本和硬件筛选
共 0 条

    还没有人点评。第一个说出真实体验的人最有价值。

    README 原文

    未翻译

    test docker pypi discord

    📑 Docs   •   🌐 Web   •   🔥 App   •   💬 Discord   •   ✍🏽 Blog


    🎁 New

    • Meet 🌶️ Pipali - our open-source AI coworker that runs on your computer.
    • Read about Khoj's excellent performance on modern retrieval and reasoning benchmarks.

    Overview

    Khoj is a personal AI app to extend your capabilities. It smoothly scales up from an on-device personal AI to a cloud-scale enterprise AI.

    • Chat with any local or online LLM (e.g llama3, qwen, gemma, mistral, gpt, claude, gemini, deepseek).
    • Get answers from the internet and your docs (including image, pdf, markdown, org-mode, word, notion files).
    • Access it from your Browser, Obsidian, Emacs, Desktop, Phone or Whatsapp.
    • Create agents with custom knowledge, persona, chat model and tools to take on any role.
    • Automate away repetitive research. Get personal newsletters and smart notifications delivered to your inbox.
    • Find relevant docs quickly and easily using our advanced semantic search.
    • Generate images, talk out loud, play your messages.
    • Khoj is open-source, self-hostable. Always.
    • Run it privately on your computer or try it on our cloud app.

    See it in action

    demo_chat

    Go to https://app.khoj.dev to see Khoj live.

    Full feature list

    You can see the full feature list here.

    Self-Host

    To get started with self-hosting Khoj, read the docs.

    Enterprise

    Khoj is available as a cloud service, on-premises, or as a hybrid solution. To learn more about Khoj Enterprise, visit our website.

    Frequently Asked Questions (FAQ)

    Q: Can I use Khoj without self-hosting?

    Yes! You can use Khoj right away at https://app.khoj.dev — no setup required.

    Q: What kinds of documents can Khoj read?

    Khoj supports a wide variety: PDFs, Markdown, Notion, Word docs, org-mode files, and more.

    Q: How can I make my own agent?

    Check out this blog post for a step-by-step guide to custom agents. For more questions, head over to our Discord!

    Contributors

    Cheers to our awesome contributors! 🎉

    Made with contrib.rocks.

    Interested in Contributing?

    Khoj is open source. It is sustained by the community and we’d love for you to join it! Whether you’re a coder, designer, writer, or enthusiast, there’s a place for you.

    Why Contribute?

    • Make an Impact: Help build, test and improve a tool used by thousands to boost productivity.
    • Learn & Grow: Work on cutting-edge AI, LLMs, and semantic search technologies.

    You can help us build new features, improve the project documentation, report issues and fix bugs. If you're a developer, please see our Contributing Guidelines and check out good first issues to work on.