Omnesis
A private knowledge layer for ChatGPT and other agents
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
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….I 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.Omnesis 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.I 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.The 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.This has been a fun project to build over the last 6 months. Keen to answer questions!
HN · launched Sep 28, 2026 · 10 upvotes (top 41%) · 1 view
Niche: knowledge base and graph software · 107 launches, 1 in the last 7 days · Explore this niche →
Category and tags
- Horizontal
- Data infrastructure
- B2B
- AI-native
- Commercial product
Visit website ↗ Source listing ↗
More like this: all 107 launches in knowledge base and graph software →
Could you build this?
No Building a cross-platform, local-first personal index across encrypted messaging databases (iMessage, WhatsApp), bank data, health data, and local files requires deep systems engineering and reverse engineering private OS databases.
What it would actually take: This requires native daemons across macOS, Linux, iOS, and Android (Swift, Rust, Kotlin) that parse proprietary local application databases (e.g. SQLite for chat.db, browser histories, health stores), background file system watchers, local vector databases (e.g. SQLite-vec or LanceDB) with on-device embedding models, and strict local sandboxing to protect sensitive data.
Discussion
4 comments analyzed.
Competitors
Other products that read as similar to this one : 367 launches clear the similarity bar, closest 8 shown.
Attention rank: #172 of 368 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 334 days after the earliest competitor.
- Omnesis · ph · 2026-09-29 · 2 upvotes · similarity 0.87
- OzBrain, a shared brain for knowledge between agents and your team · hn · 2026-08-21 · 93 upvotes · similarity 0.49
- Sidestream · hn · 2026-01-06 · 6 upvotes · similarity 0.46
- ContextVault · hn · 2026-07-13 · 12 upvotes · similarity 0.44
- Created an AI for myself to achieve goals, it might help you guys too · hn · 2026-01-19 · 6 upvotes · similarity 0.43
- openchats · ph · 2026-10-05 · 2 upvotes · similarity 0.42
- Omni · hn · 2026-03-02 · 177 upvotes · similarity 0.42
- Bored People Chat · hn · 2026-06-30 · 6 upvotes · similarity 0.42
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.