Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/charmbracelet/mods
AI on the command line
https://github.com/charmbracelet/mods
Last synced: 2 days ago
JSON representation
AI on the command line
- Host: GitHub
- URL: https://github.com/charmbracelet/mods
- Owner: charmbracelet
- License: mit
- Created: 2023-03-29T19:41:23.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-12-02T08:23:06.000Z (10 days ago)
- Last Synced: 2024-12-02T09:29:46.914Z (10 days ago)
- Language: Go
- Homepage:
- Size: 683 KB
- Stars: 3,076
- Watchers: 10
- Forks: 120
- Open Issues: 44
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Codeowners: .github/CODEOWNERS
Awesome Lists containing this project
- awesome-cli-apps - Mods! - AI for the command line, built for pipelines. (<a name="ai"></a>AI / ChatGPT)
- project-awesome - charmbracelet/mods - AI on the command line (Go)
- my-awesome-github-stars - charmbracelet/mods - AI on the command line (Go)
- awesome-cli-apps-in-a-csv - Mods! - AI for the command line, built for pipelines. (<a name="ai"></a>AI / ChatGPT)
- awesome-chatgpt-api - mods
- charm-in-the-wild - mods - AI on the CLI, built for pipelines. (_built with Bubble Tea_) (Applications / AI)
- my-awesome - charmbracelet/mods - 12 star:3.1k fork:0.1k AI on the command line (Go)
README
# Mods
AI for the command line, built for pipelines.
Large Language Models (LLM) based AI is useful to ingest command output and
format results in Markdown, JSON, and other text based formats. Mods is a
tool to add a sprinkle of AI in your command line and make your pipelines
artificially intelligent.
It works great with LLMs running locally through [LocalAI]. You can also use
[OpenAI], [Cohere], [Groq], or [Azure OpenAI].
[LocalAI]: https://github.com/go-skynet/LocalAI
[OpenAI]: https://platform.openai.com/account/api-keys
[Cohere]: https://dashboard.cohere.com/api-keys
[Groq]: https://console.groq.com/keys
[Azure OpenAI]: https://azure.microsoft.com/en-us/products/cognitive-services/openai-service
### Installation
Use a package manager:
```bash
# macOS or Linux
brew install charmbracelet/tap/mods
# Windows (with Winget)
winget install charmbracelet.mods
# Arch Linux (btw)
yay -S mods
# Nix
nix-shell -p mods
```
Debian/Ubuntu
```bash
sudo mkdir -p /etc/apt/keyrings
curl -fsSL https://repo.charm.sh/apt/gpg.key | sudo gpg --dearmor -o /etc/apt/keyrings/charm.gpg
echo "deb [signed-by=/etc/apt/keyrings/charm.gpg] https://repo.charm.sh/apt/ * *" | sudo tee /etc/apt/sources.list.d/charm.list
sudo apt update && sudo apt install mods
```
Fedora/RHEL
```bash
echo '[charm]
name=Charm
baseurl=https://repo.charm.sh/yum/
enabled=1
gpgcheck=1
gpgkey=https://repo.charm.sh/yum/gpg.key' | sudo tee /etc/yum.repos.d/charm.repo
sudo yum install mods
```
Or, download it:
- [Packages][releases] are available in Debian and RPM formats
- [Binaries][releases] are available for Linux, macOS, and Windows
[releases]: https://github.com/charmbracelet/mods/releases
Or, just install it with `go`:
```sh
go install github.com/charmbracelet/mods@latest
```
Shell Completions
All the packages and archives come with pre-generated completion files for Bash,
ZSH, Fish, and PowerShell.
If you built it from source, you can generate them with:
```bash
mods completion bash -h
mods completion zsh -h
mods completion fish -h
mods completion powershell -h
```
If you use a package (like Homebrew, Debs, etc), the completions should be set
up automatically, given your shell is configured properly.
## What Can It Do?
Mods works by reading standard in and prefacing it with a prompt supplied in
the `mods` arguments. It sends the input text to an LLM and prints out the
result, optionally asking the LLM to format the response as Markdown. This
gives you a way to "question" the output of a command. Mods will also work on
standard in or an argument supplied prompt individually.
Be sure to check out the [examples](examples.md) and a list of all the
[features](features.md).
Mods works with OpenAI compatible endpoints. By default, Mods is configured to
support OpenAI's official API and a LocalAI installation running on port 8080.
You can configure additional endpoints in your settings file by running
`mods --settings`.
## Saved Conversations
Conversations are saved locally by default. Each conversation has a SHA-1
identifier and a title (like `git`!).
Check the [`./features.md`](./features.md) for more details.
## Usage
- `-m`, `--model`: Specify Large Language Model to use.
- `-f`, `--format`: Ask the LLM to format the response in a given format.
- `--format-as`: Specify the format for the output (used with `--format`).
- `-P`, `--prompt`: Prompt should include stdin and args.
- `-p`, `--prompt-args`: Prompt should only include args.
- `-q`, `--quiet`: Only output errors to standard err.
- `-r`, `--raw`: Print raw response without syntax highlighting.
- `--settings`: Open settings.
- `-x`, `--http-proxy`: Use HTTP proxy to connect to the API endpoints.
- `--max-retries`: Maximum number of retries.
- `--max-tokens`: Specify maximum tokens with which to respond.
- `--no-limit`: Do not limit the response tokens.
- `--role`: Specify the role to use (See [custom roles](#custom-roles)).
- `--word-wrap`: Wrap output at width (defaults to 80)
- `--reset-settings`: Restore settings to default.
#### Conversations
- `-t`, `--title`: Set the title for the conversation.
- `-l`, `--list`: List saved conversations.
- `-c`, `--continue`: Continue from last response or specific title or SHA-1.
- `-C`, `--continue-last`: Continue the last conversation.
- `-s`, `--show`: Show saved conversation for the given title or SHA-1.
- `-S`, `--show-last`: Show previous conversation.
- `--delete-older-than=`: Deletes conversations older than given duration (`10d`, `1mo`).
- `--delete`: Deletes the saved conversation for the given title or SHA-1.
- `--no-cache`: Do not save conversations.
#### Advanced
- `--fanciness`: Level of fanciness.
- `--temp`: Sampling temperature.
- `--topp`: Top P value.
- `--topk`: Top K value.
## Custom Roles
Roles allow you to set system prompts. Here is an example of a `shell` role:
```yaml
roles:
shell:
- you are a shell expert
- you do not explain anything
- you simply output one liners to solve the problems you're asked
- you do not provide any explanation whatsoever, ONLY the command
```
Then, use the custom role in `mods`:
```sh
mods --role shell list files in the current directory
```
## Setup
### Open AI
Mods uses GPT-4 by default. It will fall back to GPT-3.5 Turbo.
Set the `OPENAI_API_KEY` environment variable. If you don't have one yet, you
can grab it the [OpenAI website](https://platform.openai.com/account/api-keys).
Alternatively, set the [`AZURE_OPENAI_KEY`] environment variable to use Azure
OpenAI. Grab a key from [Azure](https://azure.microsoft.com/en-us/products/cognitive-services/openai-service).
### Cohere
Cohere provides enterprise optimized models.
Set the `COHERE_API_KEY` environment variable. If you don't have one yet, you can
get it from the [Cohere dashboard](https://dashboard.cohere.com/api-keys).
### Local AI
Local AI allows you to run models locally. Mods works with the GPT4ALL-J model
as setup in [this tutorial](https://github.com/go-skynet/LocalAI#example-use-gpt4all-j-model).
### Groq
Groq provides models powered by their LPU inference engine.
Set the `GROQ_API_KEY` environment variable. If you don't have one yet, you can
get it from the [Groq console](https://console.groq.com/keys).
## Whatcha Think?
We’d love to hear your thoughts on this project. Feel free to drop us a note.
- [Twitter](https://twitter.com/charmcli)
- [The Fediverse](https://mastodon.social/@charmcli)
- [Discord](https://charm.sh/chat)
## License
[MIT](https://github.com/charmbracelet/mods/raw/main/LICENSE)
---
Part of [Charm](https://charm.sh).
Charm热爱开源 • Charm loves open source