This repository has been archived on 2024-08-20. You can view files and clone it, but cannot push or open issues or pull requests.
server-personification/README.md

26 lines
1.2 KiB
Markdown
Raw Normal View History

2024-01-20 13:12:58 -07:00
# server-personification
2024-01-20 15:36:47 -07:00
2024-01-20 18:25:09 -07:00
_It would be funny if computers could talk._
2024-01-20 13:12:58 -07:00
2024-01-20 15:36:47 -07:00
This is a project to personify computer systems and give them a voice. OpenAI is used to create an agent you can
converse with and use for server management.
## To Do
- [ ] Cache per-hostname conversation history in a database. Store message timestamps as well. Summarize conversations.
- [ ] Feed the conversation history to the AI and make sure to give it relative dates of the conversations as well
2024-01-20 15:36:47 -07:00
- [ ] Have the agent pull its personality from the database as its hostname as the key.
- [ ] Log all commands and their outputs to the database.
- [ ] Use yaml for config.
- [ ] Add the user's name.
- [ ] Implement context cutoff based on token counts
2024-01-20 17:14:12 -07:00
- [ ] Option to have the bot send the user a welcome message when they connect
2024-01-20 18:23:35 -07:00
- [ ] Streaming
2024-01-20 15:36:47 -07:00
- [ ] Add a Matrix bot.
- [ ] Integrate Icinga2 host and service checks functions.
- [ ] Figure out system permissions and how to run as a special user.
- [ ] Give the agent instructions on how to run the system (pulled from the database).
- [ ] Have the agent run every `n` minutes to check Icinga2 and take action if necessary.
2024-01-20 15:37:45 -07:00
- [ ] Evaluate using langchain.
- [ ] Can langchain use a headless browser to interact with the web?