{"slug": "show-hn-omnesis-a-private-knowledge-layer-for-chatgpt-and-other-agents", "title": "Show HN: Omnesis – A private knowledge layer for ChatGPT and other agents", "summary": "A developer launched Omnesis, a self-hosted private context layer that connects ChatGPT, Claude, Codex, Openclaw and Hermes agents to personal data sources including WhatsApp, iMessage, bank transactions, health records, emails, call logs, meeting notes and voicemails, after 6 months of development. Omnesis indexes the data into a connected graph, transcribes voice notes and runs OCR on images in emails and PDFs, and lets users define per-agent source access plus prose privacy policies; all models can run on zero-data-retention inference providers or on the user's own hardware. The project also includes an experimental, default-disabled \"Omnesis Brain\" that continuously analyzes personal data to maintain a structured understanding of the user's life.", "body_md": "Imagine giving ChatGPT or any other agent access to your Whatsapp/iMessage, bank transactions, health data, web pages you see, metadata about all the photos you took, places you visited, all your emails/documents, call logs, meeting notes, your voice mails, and more….\n\nI built a context layer for that purpose. You can connect your Openclaw, Hermes, Claude, ChatGPT, Codex, etc to it. It gives your favorite agent \"context superpowers\". All the data is indexed and connected into a graph, self-hosted on your own hardware. Voice notes are transcribed, OCR runs on images in mails and pdfs, etc.\n\nOmnesis offers a flexible data access model. For each agent you can define which source(s) they have access to and also guard data access with a privacy policy written in prose. You can also directly talk to the Omnesis agent which has no web search / internet tools — via a web portal or companion app — to ask the most intimate questions about your digital life.\n\nI built this to be flexible. You can run all necessary models on zero-data-retention inference providers, or — if you can afford it — on your own hardware. I’ll keep investing in Omnesis’s security. Because it brings together sensitive data from many sources, please install it only on machines you control and keep secure.\n\nThe project also includes what I call “Omnesis Brain”. This is my work-in-progress take on what a “second brain” could look like on top of that context layer. Imagine an agent constantly analyzing your personal data in flux to maintain a more structured and grounded understanding of what’s happening in your life. This is experimental and disabled by default.\n\nThis has been a fun project to build over the last 6 months. Keen to answer questions!\n\nComments URL: [https://news.ycombinator.com/item?id=49877752](https://news.ycombinator.com/item?id=49877752)\n\nPoints: 2\n\n# Comments: 0", "url": "https://wpnews.pro/news/show-hn-omnesis-a-private-knowledge-layer-for-chatgpt-and-other-agents", "canonical_source": "https://omnesis.dev/", "published_at": "2026-09-28 13:35:57+00:00", "updated_at": "2026-09-28 13:47:47.413312+00:00", "lang": "en", "topics": ["ai-agents", "ai-products", "ai-tools", "artificial-intelligence"], "entities": ["Omnesis", "Omnesis Brain", "ChatGPT", "Claude", "Codex", "Openclaw", "Hermes", "Hacker News"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/show-hn-omnesis-a-private-knowledge-layer-for-chatgpt-and-other-agents", "markdown": "https://wpnews.pro/news/show-hn-omnesis-a-private-knowledge-layer-for-chatgpt-and-other-agents.md", "text": "https://wpnews.pro/news/show-hn-omnesis-a-private-knowledge-layer-for-chatgpt-and-other-agents.txt", "jsonld": "https://wpnews.pro/news/show-hn-omnesis-a-private-knowledge-layer-for-chatgpt-and-other-agents.jsonld"}}