1 unstable release
0.1.0 | Sep 27, 2023 |
---|
#20 in #review
30KB
688 lines
augre
An LLM-powered (CodeLlama or OpenAI) local diff code review tool.
Binary Usage
Install
Windows:
$ iwr https://github.com/twitchax/augre/releases/latest/download/augre_x86_64-pc-windows-gnu.zip
$ Expand-Archive augre_x86_64-pc-windows-gnu.zip -DestinationPath C:\Users\%USERNAME%\AppData\Local\Programs\augre
Mac OS (Apple Silicon):
$ curl -LO https://github.com/twitchax/augre/releases/latest/download/augre_aarch64-apple-darwin.zip
$ unzip augre_aarch64-apple-darwin.zip -d /usr/local/bin
$ chmod a+x /usr/local/bin/augre
Linux:
$ curl -LO https://github.com/twitchax/augre/releases/latest/download/augre_x86_64-unknown-linux-gnu.zip
$ unzip augre_x86_64-unknown-linux-gnu.zip -d /usr/local/bin
$ chmod a+x /usr/local/bin/augre
Cargo:
$ cargo install augre
Help Docs
$ augre -h
Usage: augre [OPTIONS] [COMMAND]
Commands:
review Performs a code review of the current `git diff HEAD^`
ask Gives a response to the specified prompt
stop Stop all of the background services
help Print this message or the help of the given subcommand(s)
Options:
-d, --data-path <DATA_PATH> The path to the data directory [default: .augre]
-m, --mode <MODE> The default operation mode [default: openai]
-y, --yes Whether to skip the confirmation prompt
-h, --help Print help
-V, --version Print version
Example Config
mode = "LocalGpu"
model_url = "https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-GGML/resolve/main/codellama-13b-instruct.ggmlv3.Q3_K_M.bin"
cria_port = 3000
License
MIT
Dependencies
~13–31MB
~440K SLoC