Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Emacs as your personal AI assistant. Use LLMs such as ChatGPT or LLaMA for text generation or DALL-E and Stable Diffusion for image generation. Also supports speech input / output.
| Date | Stars |
|---|---|
| 2026-07-31 | 820 |
| 2026-08-06 | 821 |
Today
+1 stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# org-ai [](https://melpa.org/#/org-ai)
[](https://www.youtube.com/watch?v=fvBDxiFPG6I)
Minor mode for Emacs org-mode that provides access to generative AI models. Currently supported are
- OpenAI API (ChatGPT, DALL-E, other text models), optionally run against Azure API instead of OpenAI
- Stable Diffusion through [stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui)
Inside an org-mode buffer you can
- use ChatGPT to generate text, having full control over system and user prompts ([demo](#chatgpt-in-org-mode))
- Speech input and output! Talk with your AI!
- generate images and image variations with a text prompt using Stable Diffusion or DALL-E ([demo 1](#dall-e-in-org-mode), [demo 2](#image-variations))
- org-ai everywhere: Various commands usable outside org-mode for prompting using the selected text or multiple files.
_Note: In order to use the OpenAI API you'll need an [OpenAI account](https://platform.openai.com/) and you need to get an API token. As far as I can tell, the current usage limits for the free tier get you pretty far._
------------------------------
## Table of Contents
- [Demos](#demos)
- [ChatGPT in org-mode](#chatgpt-in-org-mode)
- [DALL-E in org-mode](#dall-e-in-org-mode)
- [Image variations](#image-variations)
- [Features and Usage](#features-and-usage)
- [`#+begin_ai...#+end_ai` special blocks](#begin_aiend_ai-special-blocks)
- [Syntax highlighting in ai blocks](#syntax-highlighting-in-ai-blocks)
- [Jump to the end of the block after completion](#jump-to-the-end-of-the-block-after-completion)
- [Auto-fill paragraphs on insertion](#auto-fill-paragraphs-on-insertion)
- [Block Options](#block-options)
- [For ChatGPT](#for-chatgpt)
- [For DALL-E](#for-dall-e)
- [Other text models](#other-text-models)
- [Image variation](#image-variation)
- [Global Commands](#global-commands)
- [org-ai-on-project](#org-ai-on-project)
- [Noweb Support](#noweb-support)
- [Installation](#installation)
- [Melpa](#melpa)
- [Straight.el](#straightel)
- [Manual](#manual)
- [OpenAI API key](#openai-api-key)
- [Using other services than OpenAI](#using-other-services-than-openai)
- [Azure](#azure)
- [perplexity.ai](#perplexityai)
- [Anthropic / Claude](#anthropic--claude)
- [Setting up speech input / output](#setting-up-speech-input--output)
- [Whisper](#whisper)
- [macOS specific steps](#macos-specific-steps)
- [macOS alternative: Siri dictation](#macos-alternative-siri-dictation)
- [Windows specific steps](#windows-specific-steps)
- [espeak / greader](#espeak--greader)
- [Setting up Stable Diffusion](#setting-up-stable-diffusion)
- [Using local LLMs with oobabooga/text-generation-webui](#using-local-llms-with-oobaboogatext-generation-webui)
- [FAQ](#faq)
- [Sponsoring](#sponsoring)
## Demos
### ChatGPT in org-mode
```org
#+begin_ai
Is Emacs the greatest editor?
#+end_ai
```
You can continue to type and press `C-c C-c` to create a conversation. `C-g` will interrupt a running request.
### DALL-E in org-mode
Use the `:image` keyword to generate an image. This uses DALL·E-3 by default.
```org
#+begin_ai :image :size 1024x1024
Hyper realistic sci-fi rendering of super complicated technical machine.
#+end_ai
```
You can use the following keywords to control the image generation:
- `:size <width>x<height>` - the size of the image to generate (default: 1024x1024)
- `:model <model>` - the model to use (default: `"dall-e-3"`)
- `:quality <quality>` - the quality of the image (choices: `hd`, `standard`)
- `:style <style>` - the style to use (choices: `vivid`, `natural`)
- `:n Excerpt of 33,521 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:4dab015ceb0ac302, topic:gpt
matched fp:4dab015ceb0ac302, desc:image generation, desc:stable diffusion
matched fp:4dab015ceb0ac302, desc:ai assistant, desc:personal ai
matched fp:4dab015ceb0ac302, topic:chatgpt
