This repository has been archived by the owner on Jan 7, 2025. It is now read-only.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The Mentat Daemon is an experiment not meant to necessarily replace Mentat, but is an alternate way to interface with Mentat that may provide a better, Copilot-like DX.
The idea is that there is a background process (the Mentat Daemon) that watches a directory for file changes. When a user changes a file, the daemon calls an LLM and inserts the code into the file where the comment was.
The daemon can be started in the command line like this:
>> mentat-daemon
Once started, a simple TUI showing file changes and LLM progress/edits is displayed. To invoke the Mentat Daemon, the user can write comments prefixed with
@mentat
to insert LLM-generated code. For a python file, the syntax would look like this:# @mentat create a function for getting market quote data from yahoo finance by ticker
After the user saves the file, the Mentat Daemon will check if the current file contents contain
@mentat
and will generate a response that will be inserted into the line the comment is on.