← 开源
lmg-anon

mikupad

LLM Frontend in a single html file

ApplicationsWrappersHTML
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
754
Star
73
Fork
+3
本周
17
贡献者
创建于 2023-10-04 · 更新于 2026-10-11 · 今日第 14186 名
主要开发者

lmg-anon/mikupad 排名第 14,186,有 754 个星标。

同类别比较

lmg-anon/mikupad 排名第 14,186,此处有 8 个同类条目;john-mnz/ComfyUI-Inspyrenet-Rembg 排名第 14,185。

同类别比较
名称排名指标
mantoni/beads-ui14,174
语言:
JavaScript
星标数:
755
分叉数:
108
eduardolat/kokoro-web14,182
语言:
TypeScript
星标数:
754
分叉数:
108
简介:
🔊 Kokoro Web: Free AI text-to-speech, online or self-hosted, OpenAI compatible!
jina-ai/auto-gpt-web14,184
语言:
TypeScript
星标数:
754
分叉数:
137
简介:
Set Your Goals, AI Achieves Them.
john-mnz/ComfyUI-Inspyrenet-Rembg14,185
语言:
Python
星标数:
754
分叉数:
45
简介:
ComfyUI node for background removal, implementing InSPyreNet the best method up to date
polyrabbit/hacker-news-digest14,190
语言:
Python
星标数:
754
分叉数:
94
简介:
:newspaper: Let LLM Summarize Hacker News for You
ClawRunr/JavaClaw14,195
语言:
Java
星标数:
753
分叉数:
167
简介:
JavaClaw, a Java version of OpenClaw built on Spring Boot, Spring AI and JobRunr
clmnin/summarize.site14,198
语言:
JavaScript
星标数:
753
分叉数:
82
简介:
Summarize web pages using OpenAI ChatGPT
r1n7aro/Locus14,203
语言:
Rust
星标数:
753
分叉数:
79
简介:
The open source Unity Dev Agent
关键参数与规格
关键参数与规格
参数值
语言HTML
类别Applications
子类别Wrappers
星标数754
分叉数73
贡献者17
创建日期2023-10-04
更新日期2026-10-11
1 天星标数0
7 天星标数3
排名14,186
上次排名14,052
排名变化-134
7 天星标排名7,247
上次 7 天星标排名7,277
7 天星标排名变化30
总星标排名14,017
上次总星标排名13,991
总星标排名变化-26
README 摘录

mikupad **mikupad** is a user-friendly, browser-based interface for interacting with language models. It's built with ReactJS and supports various text generation backends, all within a single HTML file. Features **Multiple Backends**: Supports **llama. cpp**, **koboldcpp**, **AI Horde**, and any **OpenAI Compatible** API. **Session Persistence**: Your prompt is automatically saved and restored, allowing you to continue seamlessly across multiple sessions. Import and export sessions for sharing or maintaining backups. **Optional Server**: Can be hosted on a local Node. js

server, enabling database access remotely or across your local network. **Persistent Context**: **Memory**: Seamlessly inject a text of your choice at the beginning of the context. **Author's Note**: Seamlessly inject a text of your choice at the end of the context, with adjustable depth. **World Info**: Dynamically include extra information in the context, triggered by specific keywords. **Prediction Undo/Redo**: Easily experiment and refine your generated text with the ability to undo and redo predictions. **Token Probability**: Hover over any

token to reveal the top 10 most probable tokens at that point. Click on a probability to regenerate the text from that specific token. If you're using oobabooga, make sure to use an \_HF sampler for this feature to function properly. If you're using koboldcpp, token probabilities are only available with Token Streaming disabled. **Logit Bias**: Fine-tune the generation process by adjusting the likelihood bias of specific tokens on-the-fly. **Completion/Chat Modes**: **Completion**: Have the language model

directly continue your prompt. **Chat**: Mikupad simplifies using instruct models. It automatically adds the right delimiters when you start or stop generating, based on your selected template. This also structures your prompt into messages, making it compatible with the Chat Completions API (for OpenAI-compatible backends). **Themes**: Customize your environment by choosing from a variety of themes. Getting Started You can easily run **mikupad** by opening the file in your web browser. Choose your preferred backend and start generating text

! To use **mikupad** fully offline, run the provided script or download the pre-compiled file from Releases. Contributing Contributions from the open-source community are welcome. Whether it's fixing a bug, adding a feature, or improving the documentation, your contributions are greatly appreciated. To contribute to **mikupad**, follow these steps: 1. Create a new branch for your changes: 3. Push your changes to your forked repository: 5. Open a pull request on the main repository, explaining your changes. License This

project is licensed under the GNU Affero General Public License v3.

常见问题

记录了多少星标和分叉?

lmg-anon/mikupad 有 754 个星标和 73 个分叉。

仓库排名是多少?

lmg-anon/mikupad 排名第 14,186。

记录的语言和类别是什么?

lmg-anon/mikupad 有 754 个星标,语言为 HTML,类别为 Applications。

哪个仓库排名最接近?

lmg-anon/mikupad 与 john-mnz/ComfyUI-Inspyrenet-Rembg 比较,后者排名第 14,185,有 754 个星标。

README

mikupad

mikupad is a user-friendly, browser-based interface for interacting with language models. It's built with ReactJS and supports various text generation backends, all within a single HTML file.

Features

  • Multiple Backends: Supports llama.cpp, koboldcpp, AI Horde, and any OpenAI Compatible API.
  • Session Persistence: Your prompt is automatically saved and restored, allowing you to continue seamlessly across multiple sessions. Import and export sessions for sharing or maintaining backups.
  • Optional Server: Can be hosted on a local Node.js server, enabling database access remotely or across your local network.
  • Persistent Context:
    • Memory: Seamlessly inject a text of your choice at the beginning of the context.
    • Author's Note: Seamlessly inject a text of your choice at the end of the context, with adjustable depth.
    • World Info: Dynamically include extra information in the context, triggered by specific keywords.
  • Prediction Undo/Redo: Easily experiment and refine your generated text with the ability to undo and redo predictions.
  • Token Probability: Hover over any token to reveal the top 10 most probable tokens at that point. Click on a probability to regenerate the text from that specific token.
    • If you're using oobabooga, make sure to use an _HF sampler for this feature to function properly.
    • If you're using koboldcpp, token probabilities are only available with Token Streaming disabled.
  • Logit Bias: Fine-tune the generation process by adjusting the likelihood bias of specific tokens on-the-fly.
  • Completion/Chat Modes:
    • Completion: Have the language model directly continue your prompt.
    • Chat: Mikupad simplifies using instruct models. It automatically adds the right delimiters when you start or stop generating, based on your selected template. This also structures your prompt into messages, making it compatible with the Chat Completions API (for OpenAI-compatible backends).
  • Themes: Customize your environment by choosing from a variety of themes.

Getting Started

You can easily run mikupad by opening the mikupad.html file in your web browser. No additional installation is required. Choose your preferred backend and start generating text!

git clone https://github.com/lmg-anon/mikupad.git
cd mikupad
open mikupad.html

To use mikupad fully offline, run the provided compile script or download the pre-compiled mikupad_compiled.html file from Releases.

You can also try it on GitHub Pages.

Contributing

Contributions from the open-source community are welcome. Whether it's fixing a bug, adding a feature, or improving the documentation, your contributions are greatly appreciated. To contribute to mikupad, follow these steps:

  1. Fork the repository.
  2. Create a new branch for your changes: git checkout -b feature/your-feature-name
  3. Make your changes and commit them: git commit -m 'Add your feature'
  4. Push your changes to your forked repository: git push origin feature/your-feature-name
  5. Open a pull request on the main repository, explaining your changes.

License

This project is licensed under the GNU Affero General Public License v3.0 - see the LICENSE file for details.

排名相邻
同类项目