sigoden

AIChat (https://github.com/sigoden/aichat) nearly fulfills all your requirements.

The only difference is that you provide subcommands, while aichat requires users to create various roles.

t2x 'Write a ...' => aichat 'Write a ...'

t2x ask file.md 'What is...' => aichat -f file.md 'What is...'

t2x summary /path/to/file => aichat -r summary -f /path/to/file

t2x summary "This is a..." => aichat -r summary "This is a..."

t2x orc /path/to/image.png => aichat -r orc -f /path/to/image.png

> Note, In AIChat, `-r/--role` specifies the role to use, `-f/--file` indicates the file or URL input.

If you're looking for a tool to simplify the building of big shell programs, I highly recommend using argc (https://github.com/sigoden/argc). It's a powerful Bash CLI framework that significantly simplifies the process of developing feature-rich command-line interfaces.

1. Proxyfor is written in Rust, while mitmproxy is written in Python. 2. Proxyfor supports only capturing and inspecting traffic, so the interface is simple, the operation is direct, and the learning cost is low.

Taskwarrior officially provides bash/zsh/fish completion scripts.

If you're a PowerShell or nushell user and need autocompletion for Taskwarrior, try https://github.com/sigoden/argc-completions.

Argc-completions provides multi-shell completions for over 1000 commands, including Taskwarrior.

A similar coding assistant in less than 100 lines of code.

https://github.com/sigoden/llm-functions/tree/main/agents/co...

Other similar projects:

https://github.com/sigoden/argc-completions

https://github.com/microsoft/inshellisense

There are still many cmake files in the current source code. What are they for? It should be known that rust projects usually do not use cmake.

use LLMs (gpt-4-vision or LLaVA) with aichat

`aichat -f tmp/test.png -- output only text in the image`

https://github.com/sigoden/aichat

Please check out the following projects:

https://github.com/jmorganca/ollama

https://github.com/mudler/LocalAI