OpenAdapt
url2epub
OpenAdapt | url2epub | |
---|---|---|
28 | 8 | |
681 | 66 | |
30.5% | - | |
9.3 | 7.3 | |
3 days ago | 12 days ago | |
Python | Go | |
MIT License | BSD 3-clause "New" or "Revised" License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
OpenAdapt
-
Llama 3-V: Matching GPT4-V with a 100x smaller model and 500 dollars
Our initial testing suggests MiniCPM outperforms InternVL for GUI understanding: https://github.com/OpenAdaptAI/OpenAdapt/issues/637#issuecom...
(InternVL appears to hallucinate more.)
-
Why MSFT Copilot+ and AI PCs are the final nail in the coffin of open computing
We have Linux support on the roadmap in https://github.com/OpenAdaptAI/OpenAdapt.
OpenAdapt has similar functionality, except:
- it's open source
- it only records when you explicitly tell it to
- it has multiple PII/PHI scrubbing providers built in (see https://github.com/OpenAdaptAI/OpenAdapt?tab=readme-ov-file#...)
- the purpose for recording is to automate tasks in desktop apps
- it's cross platform (Mac and Windows now, Linux coming soon)
Full disclosure: I'm the primary author. Feedback welcome!
-
PaliGemma: Open-Source Multimodal Model by Google
Excited to test how this performs compared to MiniCPMv2, especially when analyzing GUI images: https://github.com/OpenAdaptAI/OpenAdapt/issues/637
-
Show HN: Tarsier – vision for text-only LLM web agents that beats GPT-4o
Congratulations on shipping!
In https://github.com/OpenAdaptAI/OpenAdapt/blob/main/openadapt... we use FastSAM to first segment the UI elements, then have the LLM describe each segment individually. This seems to work quite well; see https://twitter.com/OpenAdaptAI/status/1789430587314336212 for a demo.
More coming soon!
- GPT-4o
- Rabbit R1 can be run on a Android device
- OpenAdapt: AI-First Process Automation with Large Multimodal Models
- Adapter between LMMs and traditional desktop and web GUI
-
I Witnessed the Future of AI, and It's a Broken Toy
> Rabbit has said the device will be able to learn any app, if you teach it.
We're building this over at https://github.com/OpenAdaptAI/OpenAdapt. OpenAdapt learns to automate tasks in desktop apps by observing human demonstrations.
Early demo: https://twitter.com/abrichr/status/1784307190062342237 (more coming soon!)
The demo is overly simplistic to keep it short -- it also works with arbitrary applications and operations.
Also, we're open source. Contributions and feedback are welcome and encouraged :)
-
Memary is a cutting-edge long-term memory system based on a knowledge graph
Very interesting, thank you for making this available!
At OpenAdapt (https://github.com/OpenAdaptAI/OpenAdapt) we are looking into using pm4py (https://github.com/pm4py) to extract a process graph from a recording of user actions.
I will look into this more closely. In the meantime, could the authors share their perspective on whether Memary could be useful here?
url2epub
-
Show HN: CLI for generating beautiful PDF for offline reading
Somewhat similarly, I wrote a web app to generate epub (instead of pdf) out of urls and send to eink reader(s) directly (via a telegram bot) so I can read them. Currently it supports sending epub by email (for kindle) or uploading epub to dropbox (for kobo, etc.). It originally also supports reMarkable cloud but we can no longer make reMarkable cloud actually work. There's also a REST api to generate epub to be downloaded directly: https://github.com/fishy/url2epub/blob/main/REST.md
For e-ink readers epubs are generally better than PDFs for urls anyways, as epubs are basically packed htmls, and also the flow text works better on smaller screens.
- Omnivore – free, open source, read-it-later App
-
Ask HN: Tell us about your project that's not done yet but you want feedback on
I wrote a service (Google Cloud Run as the backend, with Telegram bot as the frontend) to generate readable ePub from URLs and send directly to e-ink readers. It was originally wrote for reMarkable 2 (using reMarkable cloud), I recently added support for Kindle (by using the send-to-kindle emails). The code is at https://github.com/fishy/url2epub and I blogged about the recently added kindle support at https://b.yuxuan.org/url2epub-kindle.
I'm open to suggestions on what other e-ink platforms to add, as long as they have a reasonable cloud API. I'm also looking for a good e-ink platform to move to personally, as it becomes apparent that reMarkable really doesn't want third parties to use their proprietary cloud "API".
-
ReMarkable 2
2. It's a relatively open system (compared to other e-ink readers), so it's pretty fun in terms of hackability.
I did get the forever free subscription which helps, but I also totally understand why they would want to charge for that, and I think the new $3/month is a pretty reasonable price for it.
Regarding instapaper use case and also hackability, shameless plug: I wrote https://github.com/fishy/url2epub for my own use case, so instead of relying on a third party service and manually sync stuff to reMarkable 2, I just send the link to the telegram bot (I picked telegram bot so that I can easily send links from my phone, not only desktops), and the epub will be auto synced to my reMarkable cloud account (they did made some changes to the cloud api causing I have to manually open their official mobile or desktop app to sync once before the reMarkable 2 itself would accept the new epub I uploaded through url2epub, haven't figured out how to avoid that yet, but it's still mostly automated).
- Instructions on how to send articles from your iPhone to reMarkable
-
Zenreader: A 4.7 Inches E-Ink RSS Reader Powered by ESP32
For reMarkable, I also wrote a Telegram bot to convert http url into ePub and send to reMarkable directly: https://github.com/fishy/url2epub
(if you don't like telegram or don't use reMarkable, it also comes with a public rest API to generate epub out of urls)
-
Show HN: Epub.to – ePub to pdf, ePub to mobi, ePub to kindle, and an ePub API
Shameless plug and this is only loosely related: Over the last holiday season I wrote a backend (written in Go and running on App Engine) to convert http url into epub. The frontend is a telegram bot that sends the epub to your reMarkable account directly, but it also has rest api to download the epub file: https://github.com/fishy/url2epub/blob/main/REST.md
-
Show HN: Create ePub Out of URL
With the purchase of reMarkable 2, I have this need to easily send web articles to my reMarkable 2 from my phone, while officially they only provided a Chrome extension, which can only be used on desktops.
As a result I wrote some go code (https://github.com/fishy/url2epub) for the past 2 days, to generate ePub from URL. I also implemented reMarkable API to send them to reMarkable tablets directly.
The current UI for it is implemented as a Telegram bot (https://t.me/url2rM_bot?start=1), running on AppEngine (code: https://github.com/fishy/url2epub/tree/main/appengine). I initially considered making an Android app for the UI, but decided that Telegram bot is less work for me, and works good enough for this use case (sorry for people who don't use Telegram, but this also means that people on iOS, desktop, etc. will be able to use it).
For the future, I might do:
- Expand the URLs supported (currently it only supports URLs with an AMP version provided, and the AMP version does have article tag inside)
What are some alternatives?
ios-mail - Secure email that protects your privacy
M5Paper_FactoryTest
CogVLM - a state-of-the-art-level open visual language model | 多模态预训练模型
lines-are-beautiful - C++ File API for the reMarkable tablet
LLaVA - [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
KindleUnpack - python based software to unpack Amazon / Kindlegen generated ebooks
adept-inference - Inference code for Persimmon-8B
seleneCMSBundle - Add CMS functionality to your Symfony Apps
IfcOpenShell - Open source IFC library and geometry engine
is - an inspector for your environment
strawberry - A GraphQL library for Python that leverages type annotations 🍓
golang-samples - Sample apps and code written for Google Cloud in the Go programming language.