Tsung-Jung Tsai (TJ_Tsai)
    • Create new note
    • Create a note from template
      • Sharing URL Link copied
      • /edit
      • View mode
        • Edit mode
        • View mode
        • Book mode
        • Slide mode
        Edit mode View mode Book mode Slide mode
      • Customize slides
      • Note Permission
      • Read
        • Only me
        • Signed-in users
        • Everyone
        Only me Signed-in users Everyone
      • Write
        • Only me
        • Signed-in users
        • Everyone
        Only me Signed-in users Everyone
    • Invite by email
      Invitee

      This note has no invitees

    • Publish Note

      Share your work with the world Congratulations! 🎉 Your note is out in the world Publish Note No publishing access yet

      Your note will be visible on your profile and discoverable by anyone.
      Your note is now live.
      This note is visible on your profile and discoverable online.
      Everyone on the web can find and read all notes of this public team.

      Your account was recently created. Publishing will be available soon, allowing you to share notes on your public page and in search results.

      Your team account was recently created. Publishing will be available soon, allowing you to share notes on your public page and in search results.

      Explore these features while you wait
      Complete general settings
      Bookmark and like published notes
      Write a few more notes
      Complete general settings
      Write a few more notes
      See published notes
      Unpublish note
      Please check the box to agree to the Community Guidelines.
      View profile
    • Commenting
      Permission
      Disabled Forbidden Owners Signed-in users Everyone
    • Enable
    • Permission
      • Forbidden
      • Owners
      • Signed-in users
      • Everyone
    • Suggest edit
      Permission
      Disabled Forbidden Owners Signed-in users Everyone
    • Enable
    • Permission
      • Forbidden
      • Owners
      • Signed-in users
    • Emoji Reply
    • Enable
    • Versions and GitHub Sync
    • Note settings
    • Note Insights New
    • Make a copy
    • Transfer ownership
    • Delete this note
    • Save as template
    • Insert from template
    • Import from
      • Dropbox
      • Google Drive
      • Gist
      • Clipboard
    • Export to
      • Dropbox
      • Google Drive
      • Gist
    • Download
      • Markdown
      • HTML
      • Raw HTML
Menu Note settings Note Insights Versions and GitHub Sync Sharing URL Create Help
Create Create new note Create a note from template
Menu
Options
Make a copy Transfer ownership Delete this note
Import from
Dropbox Google Drive Gist Clipboard
Export to
Dropbox Google Drive Gist
Download
Markdown HTML Raw HTML
Back
Sharing URL Link copied
/edit
View mode
  • Edit mode
  • View mode
  • Book mode
  • Slide mode
Edit mode View mode Book mode Slide mode
Customize slides
Note Permission
Read
Only me
  • Only me
  • Signed-in users
  • Everyone
Only me Signed-in users Everyone
Write
Only me
  • Only me
  • Signed-in users
  • Everyone
Only me Signed-in users Everyone
  • Invite by email
    Invitee

    This note has no invitees

  • Publish Note

    Share your work with the world Congratulations! 🎉 Your note is out in the world Publish Note No publishing access yet

    Your note will be visible on your profile and discoverable by anyone.
    Your note is now live.
    This note is visible on your profile and discoverable online.
    Everyone on the web can find and read all notes of this public team.

    Your account was recently created. Publishing will be available soon, allowing you to share notes on your public page and in search results.

    Your team account was recently created. Publishing will be available soon, allowing you to share notes on your public page and in search results.

    Explore these features while you wait
    Complete general settings
    Bookmark and like published notes
    Write a few more notes
    Complete general settings
    Write a few more notes
    See published notes
    Unpublish note
    Please check the box to agree to the Community Guidelines.
    View profile
    Engagement control
    Commenting
    Permission
    Disabled Forbidden Owners Signed-in users Everyone
    Enable
    Permission
    • Forbidden
    • Owners
    • Signed-in users
    • Everyone
    Suggest edit
    Permission
    Disabled Forbidden Owners Signed-in users Everyone
    Enable
    Permission
    • Forbidden
    • Owners
    • Signed-in users
    Emoji Reply
    Enable
    Import from Dropbox Google Drive Gist Clipboard
       Owned this note    Owned this note      
    Published Linked with GitHub
    • Any changes
      Be notified of any changes
    • Mention me
      Be notified of mention me
    • Unsubscribe
    [AI] Agents / Hermes Agent - 安裝與設定步驟(A版) === ###### tags: `AI / Tools / Agents / Hermes Agent /` ###### tags: `AI`, `tools`, `agents`, `Hermes Agent`, `Hermes`, `愛馬仕` <br> > [!Note] > - 整理自 **Hermes Agent 官方文件 / GitHub README 文件** > - **解說**:**自架 OpenAI-compatible model server** 放進實作流程。 <br> **目錄** - [\[AI\] Agent / Hermes Agent - 安裝詳解](#AI-Agent--Hermes-Agent---安裝詳解) - [Hermes 快速安裝與設定流程](#Hermes-快速安裝與設定流程) - [1. 官方推薦安裝方式](#1-官方推薦安裝方式) - [2. 先檢查安裝狀態](#2-先檢查安裝狀態) - [3. 設定模型供應商:你的情境選 Custom endpoint](#3-設定模型供應商:你的情境選-Custom-endpoint) - [4. 先用 curl 驗證你的 OpenAI-compatible endpoint](#4-先用-curl-驗證你的-OpenAI-compatible-endpoint) - [4.1 查模型列表](#41-查模型列表) - [4.2 測 chat completions](#42-測-chat-completions) - [5. 官方設定檔位置與優先順序](#5-官方設定檔位置與優先順序) - [6. 手動設定 `~/.hermes/config.yaml`](#6-手動設定-hermesconfigyaml) - [單一自架 endpoint](#單一自架-endpoint) - [多個自架 endpoint](#多個自架-endpoint) - [7. 很重要:`hermes model` vs `/model`](#7-很重要:hermes-model-vs-model) - [8. 關於 context length:官方文件有一點需要注意](#8-關於-context-length:官方文件有一點需要注意) - [9. vLLM 自架模型建議設定](#9-vLLM-自架模型建議設定) - [10. 設定完成後測試](#10-設定完成後測試) - [11. 常見錯誤對照](#11-常見錯誤對照) - [12. 最推薦給你的完整流程](#12-最推薦給你的完整流程) > Date: 2026-04-29 12:34:40 GMT+8 <br> > [!Note] > **官方文件**:https://hermes-agent.nousresearch.com/docs/ <br> ## Hermes 快速安裝與設定流程 - ### 1. 安裝 Hermes ```bash curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash ``` 重新載入 shell: ```bash source ~/.bashrc # 或 source ~/.zshrc ``` 檢查: ```bash hermes doctor ``` --- - ### 2. 先確認你的自架 OpenAI-compatible endpoint 查模型名稱: ```bash curl -s http://YOUR_HOST:8000/v1/models | jq ``` 測試 chat completions: ```bash curl -s http://YOUR_HOST:8000/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{ "model": "YOUR_MODEL_NAME", "messages": [ {"role": "user", "content": "hi"} ] }' | jq ``` 如果有 API key: ```bash -H "Authorization: Bearer YOUR_API_KEY" ``` --- - ### 3. 設定 Hermes 使用自架模型 執行: ```bash hermes model ``` 選: ```text Custom endpoint (enter URL manually) ``` 依序輸入: ```text Base URL: http://YOUR_HOST:8000/v1 API Key: 沒有就留空 Model Name: YOUR_MODEL_NAME Context Length: 65536 ``` --- - ### 4. 確認設定檔 ```bash cat ~/.hermes/config.yaml ``` 大致會像這樣: ```yaml model: provider: custom default: "YOUR_MODEL_NAME" base_url: "http://YOUR_HOST:8000/v1" api_key: "" context_length: 65536 ``` --- - ### 5. 啟動 Hermes ```bash hermes ``` 或: ```bash hermes --tui ``` --- - ### 6. 常見錯誤 | 問題 | 解法 | | --- | --- | | `No inference provider configured` | 離開 Hermes chat,回 shell 執行 `hermes model` | | 在 Hermes 裡打 `hermes model` 沒用 | Hermes 裡要用 `/model`;設定 provider 要在外層 shell 跑 `hermes model` | | endpoint 連不上 | 確認 URL 有 `/v1`,例如 `http://host:8000/v1` | | model name 錯 | 用 `/v1/models` 回傳的 `id` | | tool calling 不正常 | vLLM 啟動時加 `--enable-auto-tool-choice --tool-call-parser ...` | --- - ### 快速版本 ```bash # 安裝 curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash source ~/.bashrc # 檢查 hermes doctor # 查自架模型名稱 curl -s http://YOUR_HOST:8000/v1/models | jq # 設定模型 hermes model # 選 Custom endpoint # URL: http://YOUR_HOST:8000/v1 # Model: /v1/models 回傳的 id # 啟動 hermes ``` <br> --- <br> ## 1. 官方推薦安裝方式 官方 Quickstart / Installation / GitHub README 都指向同一個一行安裝指令: ```bash id="zf6pmb" curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash ``` 官方說明支援 **Linux / macOS / WSL2 / Android Termux**;Windows 原生不支援,Windows 使用者需要先安裝 WSL2,再在 WSL2 terminal 裡執行安裝。([Hermes Agent][20260429-A-1]) 官方也說安裝器會自動處理 Python、Node.js、ripgrep、ffmpeg、virtualenv、全域 `hermes` 指令與 LLM provider 設定;唯一明確前置需求是 `git`。([Hermes Agent][20260429-A-1]) 安裝完成後: ```bash id="ec6efq" source ~/.bashrc # 或 source ~/.zshrc hermes ``` 官方安裝頁也列出後續常用設定指令:`hermes model` 設定模型、`hermes tools` 設定工具、`hermes gateway setup` 設定訊息平台、`hermes setup` 重新跑完整設定精靈。([Hermes Agent][20260429-A-1]) --- ## 2. 先檢查安裝狀態 安裝後建議先跑: ```bash id="ebkuqb" hermes doctor ``` 官方 troubleshooting 建議遇到問題時使用 `hermes doctor`,它會檢查缺少什麼並提示修正方式。([Hermes Agent][20260429-A-1]) 常見檢查: ```bash id="ugeuft" which hermes hermes --help hermes doctor ``` 若出現: ```text id="i1ckzq" hermes: command not found ``` 通常是 shell 還沒重新載入: ```bash id="vtwqm2" source ~/.bashrc # 或 source ~/.zshrc ``` --- ## 3. 設定模型供應商:你的情境選 Custom endpoint 官方 AI Providers 頁面說,Hermes 需要至少一個 inference provider;可以用 `hermes model` 互動式切換 provider/model。對於自架模型,只要 server 實作 OpenAI-compatible `/v1/chat/completions`,Hermes 就能指向它。([Hermes Agent][20260429-A-2]) 執行: ```bash id="egbqk9" hermes model ``` 選: ```text id="rl3ya2" Custom endpoint (enter URL manually) ``` 或官方文件中的名稱: ```text id="8a4zql" Custom endpoint (self-hosted / VLLM / etc.) ``` 然後填: ```text id="r14f0i" API base URL: http://你的-model-server:8000/v1 API key: 有就填,沒有就留空 Model name: 你的模型 ID Context length: 建議填 65536 或你的 server 實際支援值 ``` 官方 Custom endpoint 一般設定流程就是:`hermes model` → 選 Custom endpoint → 輸入 API base URL、API key、Model name。([Hermes Agent][20260429-A-2]) --- ## 4. 先用 curl 驗證你的 OpenAI-compatible endpoint 在設定 Hermes 前,先確認你的 server 真的有 OpenAI-compatible API。 ### 4.1 查模型列表 ```bash id="eqfwqv" curl -s http://YOUR_HOST:8000/v1/models | jq ``` 如果有 API key: ```bash id="fim8ma" curl -s http://YOUR_HOST:8000/v1/models \ -H "Authorization: Bearer YOUR_API_KEY" | jq ``` 看回傳的 `id`,例如: ```json id="fi3cnb" { "data": [ { "id": "Qwen/Qwen2.5-Coder-32B-Instruct" } ] } ``` 這個 `id` 就是 Hermes 裡要填的 `Model name`。 ### 4.2 測 chat completions ```bash id="52f7rd" curl -s http://YOUR_HOST:8000/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{ "model": "Qwen/Qwen2.5-Coder-32B-Instruct", "messages": [ {"role": "user", "content": "hi"} ] }' | jq ``` 有 API key 則加: ```bash id="tp4312" -H "Authorization: Bearer YOUR_API_KEY" ``` 只要這個能回應,Hermes 才比較可能正常接上。 --- ## 5. 官方設定檔位置與優先順序 官方 Configuration 說設定解析順序是: | 優先順序 | 來源 | 用途 | | ---: | ----------------------- | ------------------------- | | 1 | CLI arguments | 單次執行覆蓋 | | 2 | `~/.hermes/config.yaml` | 主要非機密設定 | | 3 | `~/.hermes/.env` | API keys、tokens、passwords | | 4 | 內建預設值 | fallback | 官方原則是:**secrets 放 `.env`,其他模型/provider/terminal/tool 設定放 `config.yaml`**。([Hermes Agent][20260429-A-3]) 所以你的自架模型,核心應該落在: ```bash id="x15bnx" ~/.hermes/config.yaml ``` API key 這類秘密值才放: ```bash id="7r4a6w" ~/.hermes/.env ``` --- ## 6. 手動設定 `~/.hermes/config.yaml` 互動式設定失敗時,可以直接手動改。 ### 單一自架 endpoint ```yaml id="o30uhf" model: default: "Qwen/Qwen2.5-Coder-32B-Instruct" provider: "custom" base_url: "http://YOUR_HOST:8000/v1" api_key: "" context_length: 65536 ``` 官方 Custom endpoint 手動設定範例就是在 `~/.hermes/config.yaml` 設 `model.default`、`provider: custom`、`base_url`、`api_key`。([Hermes Agent][20260429-A-2]) ### 多個自架 endpoint 如果你有本機、GPU server、公司內部 proxy,可以用 named custom providers: ```yaml id="sgylu7" custom_providers: - name: local base_url: "http://localhost:8000/v1" models: Qwen/Qwen2.5-Coder-32B-Instruct: context_length: 65536 - name: work base_url: "http://gpu-server.internal:8000/v1" key_env: CORP_API_KEY models: deepseek-ai/DeepSeek-V3: context_length: 65536 ``` 官方文件也支援 `custom_providers`,可設定多個 named custom endpoints,並用 `/model custom:local:qwen-2.5` 這種三段式語法切換。([Hermes Agent][20260429-A-2]) --- ## 7. 很重要:`hermes model` vs `/model` 你前面遇到的狀況就是這個差異。 | 指令 | 在哪裡執行 | 用途 | | -------------- | ------------------- | ----------------------------------------- | | `hermes model` | 外層 shell / terminal | 新增 provider、輸入 API key、設定 custom endpoint | | `/model` | Hermes chat 裡面 | 只切換已經設定好的 provider/model | 官方明確說:`hermes model` 要在 chat session 外執行,是完整 provider setup wizard;`/model` 只能在已啟動的 Hermes chat 裡切換已設定好的模型,不能新增 provider、不能跑 OAuth、不能要求輸入 API key。([Hermes Agent][20260429-A-2]) 所以正確流程是: ```bash id="7ez7ys" # 在 Hermes chat 裡 /quit # 回到 shell hermes model # 設定完後再進入 hermes ``` --- ## 8. 關於 context length:官方文件有一點需要注意 官方 Quickstart 目前寫:Hermes Agent 需要至少 **64,000 tokens context**,小於這個視窗的模型可能無法維持多步驟 tool-calling 工作,甚至啟動時被拒絕。([Hermes Agent][20260429-A-4]) 但 FAQ / Local model 範例中仍出現 `32768` 的範例值。([Hermes Agent][20260429-A-5]) 我的建議是: **以目前 Quickstart 的 64K 要求為準**,你的自架模型盡量設定: ```yaml id="j2q1mc" context_length: 65536 ``` vLLM server 端也對應: ```bash id="f1ikrb" --max-model-len 65536 ``` --- ## 9. vLLM 自架模型建議設定 官方 vLLM 範例: ```bash id="z9jvtq" pip install vllm vllm serve meta-llama/Llama-3.1-70B-Instruct \ --port 8000 \ --max-model-len 65536 \ --tensor-parallel-size 2 \ --enable-auto-tool-choice \ --tool-call-parser hermes ``` 官方說 vLLM 適合 production GPU inference;tool calling 需要 `--enable-auto-tool-choice`,並依模型格式指定 `--tool-call-parser`,否則工具呼叫可能只會被模型輸出成普通文字。([Hermes Agent][20260429-A-2]) 常見 parser 對照: | 模型類型 | 建議 parser | | --------------------- | ------------------------------ | | Qwen 2.5 / Hermes 2/3 | `hermes` | | Llama 3.x | `llama3_json` | | Mistral | `mistral` | | DeepSeek V3 | `deepseek_v3` 或 `deepseek_v31` | 官方列出的 supported parsers 包含 `hermes`、`llama3_json`、`mistral`、`deepseek_v3`、`deepseek_v31`、`xlam`、`pythonic`。([Hermes Agent][20260429-A-2]) --- ## 10. 設定完成後測試 ```bash id="v9i4bd" hermes ``` 或: ```bash id="h9zw95" hermes --tui ``` 官方說 `hermes` 是 classic CLI,`hermes --tui` 是較新的 TUI;兩者共用 sessions、slash commands 與 config。([Hermes Agent][20260429-A-4]) 進入後測: ```text id="akf8uv" hi ``` 或更實用: ```text id="24tg5e" Check my current directory and tell me what looks like the main project file. ``` 官方 Quickstart 說成功狀態應該包含:banner 顯示選定的 model/provider、Hermes 能正常回應、必要時能使用 tool、對話能持續多輪。([Hermes Agent][20260429-A-4]) --- ## 11. 常見錯誤對照 | 錯誤 | 原因 | 解法 | | ---------------------------------- | ------------------------------- | --------------------------------------------------------- | | `No inference provider configured` | 沒有設定 provider/model | 在外層 shell 執行 `hermes model` | | 在 Hermes 裡打 `hermes model` 無效 | 你在 chat session 內,不是在 shell | `/quit` 後再跑 `hermes model` | | `/model` 找不到 custom endpoint | `/model` 只能切換已設定項目 | 先用 `hermes model` 新增 | | `hermes: command not found` | PATH 尚未更新 | `source ~/.bashrc` 或 `source ~/.zshrc` | | endpoint 連不上 | base URL 錯、少 `/v1`、防火牆、port 不通 | 先用 `curl /v1/models` 測 | | model name 不對 | Hermes 填的 model id 跟 server 不一致 | 用 `/v1/models` 回傳的 `id` | | tool calling 失效 | vLLM/SGLang 沒開 tool parser | vLLM 加 `--enable-auto-tool-choice --tool-call-parser ...` | | context 不足 | local model context 太小 | server 端設 64K,Hermes `context_length: 65536` | --- ## 12. 最推薦給你的完整流程 ```bash id="zh4rxq" # 1. 安裝 curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash # 2. 重新載入 shell source ~/.bashrc # 3. 檢查 hermes doctor # 4. 先確認自架 endpoint curl -s http://YOUR_HOST:8000/v1/models | jq # 5. 設定 Hermes model hermes model # 選 Custom endpoint # URL: http://YOUR_HOST:8000/v1 # API key: 沒有就留空 # Model name: 用 /v1/models 回傳的 id # Context length: 65536 # 6. 確認設定 cat ~/.hermes/config.yaml # 7. 啟動 hermes ``` 以你現在的需求,**不要選 OpenAI Codex、Nous Portal、OpenRouter**。 你要選的是: ```text id="visbgg" Custom endpoint (enter URL manually) ``` 然後填你的 OpenAI-compatible URL,例如: ```text id="p3mmfc" http://10.78.26.123:8000/v1 ``` [20260429-A-1]: https://hermes-agent.nousresearch.com/docs/getting-started/installation "Installation | Hermes Agent" [20260429-A-2]: https://hermes-agent.nousresearch.com/docs/integrations/providers "AI Providers | Hermes Agent" [20260429-A-3]: https://hermes-agent.nousresearch.com/docs/user-guide/configuration "Configuration | Hermes Agent" [20260429-A-4]: https://hermes-agent.nousresearch.com/docs/getting-started/quickstart "Quickstart | Hermes Agent" [20260429-A-5]: https://hermes-agent.nousresearch.com/docs/reference/faq "FAQ & Troubleshooting | Hermes Agent" <br> {%hackmd vaaMgNRPS4KGJDSFG0ZE0w %}

    Import from clipboard

    Paste your markdown or webpage here...

    Advanced permission required

    Your current role can only read. Ask the system administrator to acquire write and comment permission.

    This team is disabled

    Sorry, this team is disabled. You can't edit this note.

    This note is locked

    Sorry, only owner can edit this note.

    Reach the limit

    Sorry, you've reached the max length this note can be.
    Please reduce the content or divide it to more notes, thank you!

    Import from Gist

    Import from Snippet

    or

    Export to Snippet

    Are you sure?

    Do you really want to delete this note?
    All users will lose their connection.

    Create a note from template

    Create a note from template

    Oops...
    This template has been removed or transferred.
    Upgrade
    All
    • All
    • Team
    No template.

    Create a template

    Upgrade

    Delete template

    Do you really want to delete this template?
    Turn this template into a regular note and keep its content, versions, and comments.

    This page need refresh

    You have an incompatible client version.
    Refresh to update.
    New version available!
    See releases notes here
    Refresh to enjoy new features.
    Your user state has changed.
    Refresh to load new user state.

    Sign in

    Forgot password
    or
    Sign in via Google Sign in via Facebook Sign in via X(Twitter) Sign in via GitHub Sign in via Dropbox Sign in with Wallet
    Wallet ( )
    Connect another wallet

    New to HackMD? Sign up

    By signing in, you agree to our terms of service.

    Help

    • English
    • 中文
    • Français
    • Deutsch
    • 日本語
    • Español
    • Català
    • Ελληνικά
    • Português
    • italiano
    • Türkçe
    • Русский
    • Nederlands
    • hrvatski jezik
    • język polski
    • Українська
    • हिन्दी
    • svenska
    • Esperanto
    • dansk

    Documents

    Help & Tutorial

    How to use Book mode

    Slide Example

    API Docs

    Edit in VSCode

    Install browser extension

    Contacts

    Feedback

    Discord

    Send us email

    Resources

    Releases

    Pricing

    Blog

    Policy

    Terms

    Privacy

    Cheatsheet

    Syntax Example Reference
    # Header Header 基本排版
    - Unordered List
    • Unordered List
    1. Ordered List
    1. Ordered List
    - [ ] Todo List
    • Todo List
    > Blockquote
    Blockquote
    **Bold font** Bold font
    *Italics font* Italics font
    ~~Strikethrough~~ Strikethrough
    19^th^ 19th
    H~2~O H2O
    ++Inserted text++ Inserted text
    ==Marked text== Marked text
    [link text](https:// "title") Link
    ![image alt](https:// "title") Image
    `Code` Code 在筆記中貼入程式碼
    ```javascript
    var i = 0;
    ```
    var i = 0;
    :smile: :smile: Emoji list
    {%youtube youtube_id %} Externals
    $L^aT_eX$ LaTeX
    :::info
    This is a alert area.
    :::

    This is a alert area.

    Versions and GitHub Sync
    Get Full History Access

    • Edit version name
    • Delete

    revision author avatar     named on  

    More Less

    Note content is identical to the latest version.
    Compare
      Choose a version
      No search result
      Version not found
    Sign in to link this note to GitHub
    Learn more
    This note is not linked with GitHub
     

    Feedback

    Submission failed, please try again

    Thanks for your support.

    On a scale of 0-10, how likely is it that you would recommend HackMD to your friends, family or business associates?

    Please give us some advice and help us improve HackMD.

     

    Thanks for your feedback

    Remove version name

    Do you want to remove this version name and description?

    Transfer ownership

    Transfer to
      Warning: is a public team. If you transfer note to this team, everyone on the web can find and read this note.

        Link with GitHub

        Please authorize HackMD on GitHub
        • Please sign in to GitHub and install the HackMD app on your GitHub repo.
        • HackMD links with GitHub through a GitHub App. You can choose which repo to install our App.
        Learn more  Sign in to GitHub

        Push the note to GitHub Push to GitHub Pull a file from GitHub

          Authorize again
         

        Choose which file to push to

        Select repo
        Refresh Authorize more repos
        Select branch
        Select file
        Select branch
        Choose version(s) to push
        • Save a new version and push
        • Choose from existing versions
        Include title and tags
        Available push count

        Pull from GitHub

         
        File from GitHub
        File from HackMD

        GitHub Link Settings

        File linked

        Linked by
        File path
        Last synced branch
        Available push count

        Danger Zone

        Unlink
        You will no longer receive notification when GitHub file changes after unlink.

        Syncing

        Push failed

        Push successfully