Open-source Perplexity clone one file back end, streaming answers
I built an open-source research agent. You ask a question, it searches the web via Tavily, synthesizes an answer with an LLM, and shows the sources it used. Answers stream in real-time. The interesting part is the backend. It's a single JS file (~100 lines) that handles web search, LLM streaming, and per-user conversation history. No vector database, no Redis, no separate storage service. It runs inside a cell — an isolated environment with a built-in database, search index, and filesystem. The cell handles persistence and streaming natively, so the agent code only has to deal with the…
What it does
In the maker’s words, at launch
I built an open-source research agent. You ask a question, it searches the web via Tavily, synthesizes an answer with an LLM, and shows the sources it used. Answers stream in real-time. The interesting part is the backend. It's a single JS file (~100 lines) that handles web search, LLM streaming, and per-user conversation history. No vector database, no Redis, no separate storage service. It runs inside a cell — an isolated environment with a built-in database, search index, and filesystem. The cell handles persistence and streaming natively, so the agent code only has to deal with the actual logic. Tech: Next.js frontend, Tavily for search, OpenRouter for LLM (Gemini 2.5 Flash default). Demo: https://youtu.be/jvTVA7J925Y
Does the same job
all alternatives →
- IBI built an open-source answer engine that runs local LLMs2024 · github.com · ▲5
hey hn, I built an open-source Perplexity clone that can run local LLMs and cloud LLMs. It's fully self-hostable through Docker and uses ollama to support local LLMs. The demo video in the repository shows me running it locally with llama3 on my M1 Macbook Pro. I'm open to any suggestions or feedback, thanks!
- RJReact.js LLM Agent (open-source)2023 · github.com · ▲8
I've been working in the couple of months on an experiment, trying to make GPT-4 much more useful for web development / React, writing production code that is relevant to any repository without copy pasta from ChatGPT or having small snippets of auto-complete from Copilot that are not in your context. The agent is taking a user story text and generating and composing multiple react components to generate the relevant screens, based on atomic design principles, with Typescript, TailwindCSS and RadixUI. Is is still experimental but very interesting results, I would like to get your…
- MYMonitoring your OpenAI usage without a third party2023 · github.com · ▲9
LLM observability is an absolute must-have for anyone running something in prod (or prod-like). While all the observability startups are great, you're essentially sending all your OpenAI usage history - prompts, generations, chats - to a random third party. So this script deploys a basic proxy in your Azure account, catches all incoming OpenAI requests, stores logs in your own resource group, and comes with visualizations premade (charts, timelines, chat history, cost estimation, etc). Thanks for any thoughts and feedback!
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, April 2026
the whole month →
- AG
Thought the resources for GPU arch were lacking, so here we are
Life & fun · Apr 2026 · jaso1024.com
- IB
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
AI · Apr 2026 · github.com
- BC
Life & fun · Apr 2026 · sam-burns.com
- IB
With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.
AI · Apr 2026 · text.blogosphere.app