Alternatives
Products that do what Supacrawler does
Simple API for extracting structured content from the Web
- 1
- 2
- 3
- 4YO
2023 · github.com
- 5IS
Yeah, there's AI, but I added it because I found it easier to find answers I'm looking for. For the data scientists, you can download the CSV and go crazy. Would love to know what discoveries or learnings can be found from it. To download the raw scraped data you need to become a paid member but you don't really need it unless you're wanting to finesse a table of data for a particular need. The cost is mostly just an incentive to help me pay the bills for running the website. The bunch of available CSV files contain large amounts of data which has everything from tags, genres, pricing,…
2025 · gginsights.io
- 6
- 7IM
Hey HN, I'm Adithya, a 20-year-old dev from India. I have been working with GenAI for the past year, and I've found it really painful to deal with the many different forms of data out there and get the best representation of it for my AI applications. That's why I built OmniParse—an open-source platform designed to handle any unstructured data and transform it into optimized, structured representations. Key Features: - Completely local processing—no external APIs - Supports ~20 file types - Converts documents, multimedia, and web pages to high-quality structured markdown - Table extraction,…
2024 · github.com
- 8
- 9BA
It works on top of the open-source workflow engine windmill [1] that you can easily self-host on a tiny server or a large k8s cluster. You will also need pgvector (here hosted on supabase) and of course a GPT4 api key. It showcases an approval step so that you only provide answers you are confident giving to your users, which feels less robotic. All the building blocks are scripts that you can reuse outside of windmill and you could build this in any other workflow engines (although less conveniently). We use it for our own needs on discord [2] and thoughts this was a common need for any…
2023 · windmill.dev
- 10
- 11
- 12OS
Hey HN! I'm open-sourcing a little weekend side project. It's a terminal UI that generates parsers for webpages using AI, and a library that runs these parsers while you browse (it connects to Chrome over CDP). You can parse Twitter, LinkedIn, and HN posts and they get saved to a DuckDB database, so you can query them later. Contributions welcome! I wrote a bit more about it here: https://0thernet.substack.com/p/memo-2-selectron
2025 · github.com
- 13SO
Henry, Matt and James here – we’re building an open source toolkit that makes it easy to integrate an LLM-powered copilot that talks to your API into software products. It works by calling API endpoints which you choose to expose to it. This lets the chatbot complete tasks within your software in response to natural language queries. It’s also open source, so you don’t have to send user data to another 3rd party. We support Llama 2, but we haven’t fine-tuned Llama 2 yet (coming soon) so highest accuracy is seen with GPT-4 or fine-tuned GPT-3.5 (much faster). We started working together 2…
2023 · github.com
- 14OC
Hi HN, I'm excited to finally launch this project. While existing tools like Postman excel at API discovery and testing, they often require us to navigate complex interfaces, manually construct requests, etc. That's why I created OpenAstra. The core idea is to combine the visual richness of traditional API tools with the simplicity of a chat interface. Think of it as "Postman meets ChatGPT" - allowing us to interact with APIs through natural conversation while retaining core essential features of traditional API tools. If you want to test an endpoint or understand what it does? Just ask. The…
2025 · github.com
- 15TW
Hello HN Community! I've transformed the "Ask HN: Who's hiring? (November 2023)" post into a Google Sheet. Here's a quick rundown of the method: I utilized the Hacker News Algolia Search API to extract data. You can find the specific thread URL here: https://hn.algolia.com/api/v1/search_by_date?tags=comment,st... Using a GET request, I fetched comments from the thread and processed them via the ChatGPT API. Employing the ChatGPT API for each comment, I parsed crucial job details such as company, position, location, and more. This information was structured and…
2023 · docs.google.com
- 16
- 17SO
Last month, we open-sourced Supaglue (https://github.com/supaglue-labs/supaglue) as a developer toolkit for building customer-facing Salesforce integrations. Since then, we've been iterating on our approach with users and are re-launching Supaglue as an open source unified API, starting with CRMs. With our re-launched public alpha you can: - Interact with HubSpot and Salesforce through a unified REST API - Sync data from HubSpot and Salesforce into a local Postgres cache and make reads against a normalized CRM schema - Make writes (POST and PATCH) to HubSpot and…
2023
- 18WB
2023 · github.com
- 19GA
Our team just published Geppetto. Geppetto is an open source Slack App to use ChatGPT inside your workspace. It is written in Python and super easy to tinker and fork: - GitHub: https://github.com/Deeptechia/geppetto - Our first public release: https://deeptechia.io/blog/geppetto-ai-companion-for-slack/
2024 · github.com
- 20
- 21LW
Hey HN! We are happy to share with you our latest project: Llama Workspace (https://llamaworkspace.ai). It's an open-source ChatGPT Teams alternative made with the needs of businesses and organizations in mind. It has everything you can expect from ChatGPT, plus first class support for users and roles management, as well as advanced collaboration features. We've made it very easy to self-host anywhere you like, and we also provide a cloud version. So no excuse for trying it out! Why using Llama Workspace instead of ChatGPT Teams? - You have access to all the major Large Language…
2024 · llamaworkspace.ai
- 22IM
I vibe-coded a small project that turns the “Ask HN: Who is hiring?” thread into searchable job data using OpenAI, PostgreSQL, and Metabase. It pulls the thread using the Hacker News API, uses GPT to extract fields like company, role, location, salary, and contact, stores everything in PostgreSQL, and spins up Metabase so you can explore and search the results. Right now it runs locally, but would anyone be interested if I built this out a bit more and made a public dashboard?
2025 · github.com
- 23CA
Hey folks, we created a ChatGPT alternative for anyone to try out LLaMA models and benchmark responses across OpenAI's models and other open source models. Would love some feedback! No data is being used for retraining models.
2023 · chat.nbox.ai
- 24UC
During my winter holiday I played with ChatGPT and built an integration with the OpenAI Completion APIs and Excel. (And yes technically not ChatGPT but as close that we can get with the APIs that are available.) I found this incredible useful for my work on Filestar. I wrote some instructions here on how to try this yourself: https://www.linkedin.com/pulse/use-chatgpt-excel-get-superpo... Please let me know if you figure out any useful prompts.
2023 · linkedin.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →