Viewing profile — amirkabbara

A few months ago, we launched Papr — a predictive memory layer for AI agents. It helps agents remember conversations, documents, and context over time, so they don’t start from scr…

Yes, you can swap it into our open source version.

Hey all, I'm one of the founders at Papr. We started building an AI project manager. Users needed to search for context about projects, and discover insights like open tasks holdin…

At papr.ai, we've been building agentic 'RAG' pipelines for 3+ years and tried almost every new thing to enable agents to search info - keyword search/grep/regex/text2sql/bmi25/sem…

Most AI systems rely on vector search. It finds similar fragments, but not the right context. It can tell you two passages are related, but not how they connect or why they matter …

Most AI systems today rely on vector search to find semantically similar information. This approach is powerful, but it has a critical blind spot: it finds fragments, not context. …

About 500 robot athletes from 16 countries competed in Beijing as the United States and China race against each other to shape the future of AI.

https://github.com/Papr-ai/papers/blob/main/v0.1%20State%20o...

try https://www.papr.ai for RAG. built it to solve this problem

actual report here: https://github.com/Papr-ai/papers/blob/main/v0.1%20State%20o...

Why so bad?

https://mlq.ai/media/quarterly_decks/v0.1_State_of_AI_in_Bus...

agree?