Exploring Russian Election Interference with Graphiti
Hi HN, we're Jack and Daniel from Zep. We've built a visual exploration tool and AI assistant for analyzing Russian election interference in the run-up to next week's US elections. The Explorer uses Graphiti, Zep's open-source temporal Knowledge Graph library. Graphiti autonomously creates dynamic, temporally-aware knowledge graphs representing complex, evolving relationships between entities. To offer users a detailed view of Russian state operations and related topics, we populated the graph with over 50+ sources. These include US DOJ indictments, research by US and foreign governments,…
What it does
In the maker’s words, at launch
Hi HN, we're Jack and Daniel from Zep. We've built a visual exploration tool and AI assistant for analyzing Russian election interference in the run-up to next week's US elections. The Explorer uses Graphiti, Zep's open-source temporal Knowledge Graph library. Graphiti autonomously creates dynamic, temporally-aware knowledge graphs representing complex, evolving relationships between entities. To offer users a detailed view of Russian state operations and related topics, we populated the graph with over 50+ sources. These include US DOJ indictments, research by US and foreign governments, research by non-governmental organizations, and media articles. Using the graph, you can explore which US organizations and individuals are implicated in these efforts and learn how private entities (such as OpenAI, Meta, and others) have responded. Two operations stand out in this dataset: Doppelganger and Tenet Media. - Doppelganger: A campaign that used AI-generated content and fake accounts to spread anti-Ukraine propaganda and influence Western public opinion. - Tenet Media: a media company secretly funded by RT (Russian state television), paid popular American influencers to create pro-Russian content across social media platforms. The Doppelganger operation's multinational scope required us to draw from both US and European sources to capture its full impact. For Tenet Media, we used diverse sources, ranging from federal government reports to Variety magazine's industry coverage, to detail the company's collapse and its broader implications for the media landscape. To build the app quickly, we used FastHTML and LangGraph, a fun combination. The linked article explains how we built the Explorer and some of the challenges we faced, particularly around ingesting data. Explorer: https://russia-elections24.getzep.com/ How we built it: https://blog.getzep.com/russian-influence-operations-graph/#... We've spent hours delving into the data. We hope you find it as fascinating as we did. Let us know what you think!
Does the same job
all alternatives →- SGSimple-graph – a graph database in SQLite2020 · github.com · ▲237
- GAGraPHP, a PHP graph DB web framework2015 · github.com · ▲58
- LTLinkurious, the first data visualization platform for graph databases2015 · linkurio.us · ▲86
AI Engage: Train AI Search EnginesDec 2025 · ▲35Get Cited in Google AI search, ChatGPT, Perplexity & Copilot
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, November 2024
the whole month →
- IB
I wasn't quite sure if this qualified as "Show HN" given you can't really download it and try it out. However, dang said[0]: > If it's hardware or something that's not so easy to try out over the internet, find a different way to show how it actually works—a video, for example, or a detailed post with photos. Hopefully I did that? Additionally, I've put code and a detailed guide for the netboot computer management setup on GitHub: https://github.com/kentonv/lanparty Anyway, if this shouldn't have been Show HN, I apologize! [0]…
Dev tools · 2024 · lanparty.house
