org-ai

In addition to the project you mentioned, there is quite an ecosystem for Emacs working with API-based LLM: https://github.com/emacs-openai/chatgpt https://github.com/stuhlmueller/gpt.el https://github.com/rksm/org-ai https://github.com/joshcho/ChatGPT.el https://github.com/rksm/gptel

org-ai does and was recommended here before[1]. The readme mentions the differences: org-assistant.el and org-ai.el org-ai.el is focused more on runtime interaction with AI org-assistant.el is focused more on reproducible sessions via org babel org-assistant.el supports branching conversations org-assistant.el is not meant to be used downstream as a library for AI endpoint interactions. In org-assistant.el, all interaction is async using org-babel, which allows for notebook style prompt development In org-ai.el, interaction is synchronous and inline, which is better for in-editor use cases org-ai.el supports a lot of other AI use cases like text to speech [1] https://github.com/rksm/org-ai

I don't, but you may be interested in something that improves upon that with the history optionally in outline format: https://github.com/rksm/org-ai

Another one specifically for org-mode would be org-ai: https://github.com/rksm/org-ai

org-ai is an Emacs package to integrate with the OpenAI API. It exposes a number of the API parameters (like temperature, system prompt, etc) so that it is easy to experiment with different combinations. The chat text is intentionally made fully modifiable. org-mode is able to embed images so that DALL-E image generation and variation can be used from within an Emacs buffer. Definitely a fun way to create an illustrated story :) Eventually I hope to connect other APIs and maybe local models as well.

Another Emacs integration, using org-mode for ChatGPT and DALL-E: https://github.com/rksm/org-ai