TNAC.ai
Hey HN, I’m Julia, my team and I are building Rag-in-a-Box (https://www.joinable.ai/rag-in-a-box), hosted RAG service that let’s builders of any skill level launch their own RAG app loaded with their own data in minutes. [ What can you do ] 1. Load your documents (PDFs, CSV, PPTs, Word Docs, etc) and make them searchable instantly. All your data stays private and encrypted. 2. Choose latest open source LLM (Llama 4, Deepseek, GPT-oss, etc) to interact with your docs 3. Access your hosted RAG via API - build your own custom front end or integrate with your existing product…
TNAC.ai launched on October 20, 2023 with 5 votes, #1,683 of 4,393 launches that month. The site was still online in September 2026, 3 years on.
What it does
TNAC.ai (Totally not a cheat!) is designed to be the easiest way to load your data into ChatGPT for you to converse with your information. TNAC was originally for students to keep on top of research projects and homework but it does so much more!
Your company knows more than your AI can use. Joinable turns raw, scattered data into governed, agent-ready knowledge and gives your team the framework to build and own the agents that act on it.
Joinable gives your AI agents the governed, trusted knowledge they need, grounded in what your business already knows. AI that doesn't have to sort through knowledge benefits everyone. Joinable does that work up front, so your agents act on knowledge they can trust. Critical institutional knowledge is scattered across PDFs, emails, spreadsheets, manuals, support tickets, chat threads, and more. It was created for people, not machines. Propagator refines it into clean, governed, agent-ready knowledge, kept continuously in sync with the source, and governed by the same permissions, so your agents act on knowledge they can trust. Sev-1 routes to the on-call security lead within 15 minutes.…from joinable.ai
In the maker’s words, at launch
Hey HN, I’m Julia, my team and I are building Rag-in-a-Box (https://www.joinable.ai/rag-in-a-box), hosted RAG service that let’s builders of any skill level launch their own RAG app loaded with their own data in minutes. [ What can you do ] 1. Load your documents (PDFs, CSV, PPTs, Word Docs, etc) and…
Does a similar job
all alternatives →
Turn any website into a knowledge base for LLMs2024 · embedding.io · ▲305I built this tool because I wanted a way to just take a bunch of URLs or domains, and query their content in RAG applications. It takes away the pain of crawling, extracting content, chunking, vectorizing, and updating periodically. I'm curious to see if it can be useful to others. I meant to launch this six months ago but life got in the way...
How we leapfrogged traditional vector based RAG with a 'language map'2024 · twitter.com · ▲162TL;DR: Vector-based RAG performs poorly for many real-world applications like codebase chats, and you should consider 'language maps'. Part of our mission at Mutable.ai is to make it much easier for developers to build and understand software. One of the natural ways to do this is to create a codebase chat, that answer questions about your repo and help you build features. It might seem simple to plug in your codebase into a state-of-the-art LLM, but LLMs have two limitations that make human-level assistance with code difficult: 1. They currently have context windows that are too small to…
LiquidIndex 2.02025 · liquidindex.dev · ▲134I'm building LiquidIndex, an RAG API service that makes it easy to add personalized context to AI apps. Instead of building a whole system to upload, process, and search through a user’s files or notes, you just call a few APIs. It handles the hard parts - like connecting to Notion or Google Drive, breaking the data into usable pieces, and making it searchable. Then, when you want to answer a question using that data, you just query it, and it gives you the most relevant results - optionally with an LLM-generated answer. No pipelines, no infrastructure, no headaches. Here are the core APIs:…
ragobble2025 · ragobble.com · ▲124Hey HN! I recently created and launched ragobble! I made this out of a personal need to just dump links, videos, and files as I browse the web to be able to quickly summarize or pull certain information from long podcasts , articles, or books. I also wanted to be able to reference these collections of material later on after leaving the application. - Users can create Knowledge-Bases and upload various data types such as links to articles, YouTube videos, files, etc. - You can create multiple Knowledge-Bases and compartmentalize your data. - Users can then asks questions with AI utilizing…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Product Hunt launch ↗ · launch text quoted in part
Launched alongside, October 2023
the whole month →
Nudge 2.0▲1,051In-app experiences to activate, retain, & understand users
Growth · 2023 · nudgenow.com
Unlock AI magic for elevated customer engagement, fast
AI · 2023 · tiledesk.com
Effortlessly discover API behaviour with a Chrome extension that automatically generates OpenAPI specifications in real time for any app or website.
Dev tools · 2023 · github.com