Weekly Shaarli

All links of one week in a single page.

Week 25 (June 19, 2023)

GitHub - mps-youtube/yewtube: yewtube, forked from mps-youtube , is a Terminal based YouTube player and downloader

Watch YouTube from the comfort of your terminal. (Well, technically opens an mpv/mplayer instance to display the actual video).

Can also do only audio so you stream audio through your terminal in the background.

Works without any api keys and can search individual content, playlists, create local playlists, downloads videos and more.
Really nice piece of software!

GitHub - npiv/chatblade: A CLI Swiss Army Knife for ChatGPT

Commandline ChatGPT interaction program, using python. Has a few quality of life features like conversation continuing, and token cost estimation.

Requires OpenAI API key to function.

GitHub - go-skynet/LocalAI: :robot: Self-hosted, community-driven, local OpenAI-compatible API. Drop-in replacement for OpenAI running LLMs on consumer-grade hardware. Free Open Source OpenAI alternative. No GPU required. LocalAI is an API to run ggml compatible models: llama, gpt4all, rwkv, whisper, vicuna, koala, gpt4all-j, cerebras, falcon, dolly, starcoder, and many other

Host your own ChatGPT-like AI API. With this you could plug your self-hosted version into any application (that allows plugging custom API URLs) and off you go with whatever model you chose!

I have no idea about the performance with/without GPU.

GitHub - wustho/epy: CLI Ebook (epub2, epub3, fb2, mobi) Reader

A fantastic e-book reader for the terminal.

Supports common ebook formats like epub, mobi, awzs.

Can currently not show images in-line (would be a nice project for e.g. kitty image protocol), but can open them in your external image software.

GitHub - aandrew-me/tgpt: ChatGPT in terminal without needing API keys

Commandline ChatGPT interaction program, using golang. Has few quality of life features (but a pre-determined role to generate and execute shell commands [DANGER DANGER] or to generate code for you).
Has basic interactive mode.

Does NOT require OpenAI API keys, uses API from a different server. (For now, no key required).

GitHub - 0xacx/chatGPT-shell-cli: Simple shell script to use OpenAI's ChatGPT and DALL-E from the terminal.

A shell script to interact with ChatGTP or DALL-E through CLI. Requires openai api key.
Built solely with (bash) shellscript, so no other interpreters required (python, node, ..)

GitHub - wiki-me/open_source_funding_guide: A guide for funding open source - very WIP

A guide for funding open source - very WIP. Contribute to wiki-me/open_source_funding_guide development by creating an account on GitHub.

GitHub - nomic-ai/gpt4all: gpt4all: an ecosystem of open-source chatbots trained on a massive collections of clean assistant data including code, stories and dialogue

Use chatbot models from your own system without having to interact with e.g. the OpenAI API.

Provides a litany of different chat bots, some having almost the same quality of output as ChatGPT3.5 (as of now).

States it does not require a GPU to work well.

GitHub - sigoden/aichat: Using ChatGPT/GPT-3.5/GPT-4 in the terminal.

A rusty commandline program to chat with OpenAI's ChatGPT. Requires OpenAI API key.

Has quite a few quality of life features like pre-determined roles (in yaml format), conversation saving, repl mode and more.

Using Wireguard to Tunnel All Traffic through a VPS to Home

How to set up wireguard in the first place, but then also an example of how to set up routing in your reverse proxy to be able to get to endpoints on a VPS.

audio - From a quality perspective, what is better: turning volume up in the software, in the OS, or on the speakers?

A concise explanation of volume controls (digital and analogue) and where to put which volume to get the best sound quality/usability.