About Polign.
The idea behind building Polign is to make agent memory infrastructure lightweight, simple, and private. The software should be capable of running entirely in your own cloud or on your own devices, and the data should never leave your control.
The idea in three steps
The problem
Have you ever had a situation where an AI agent provided outdated information, or hallucinated, or simply made up facts? As AI and agentic systems developed over the last few years, much attention has been paid to the intelligence of the agent itself. As a quick and dirty solution, vector databases and semantic retrieval systems have been used to store and retrieve relevant content to feed the intelligence of the agent.
The insight
The answer to the AI problem is very human. How do you make informed decisions? You understand, you infer, you remember the lessons of the past and you recall the facts you have learned over time. The same is true for agents. The intelligence of an agent is only as good as the memory it has to draw upon.
The product
Polign Recall is memory for agents built on that idea: typed facts that are corrected by rule, with every earlier value durably kept, in a bucket you control. It runs on polign_db, or any compatible database with similarity search, BM25 and filtering capabilities for typed metadata. Recall is capable of running entirely in your own cloud or devices and present you with a simple APIs to store and retrieve facts, with the ability to correct and update them over time.
Behind Polign
Anup Talwalkar
Founder and CEO · LinkedIn
As an early engineer on AWS S3, Anup helped build the global bucket namespace platform, and define the APIs and how users interact with one of the largest storage platforms in the world, continuing to build products such as S3 lifecycle and event notifications from the ground up.
At Google Cloud Storage, Anup led the data orchestration platforms (Storage Transfer) and built the event-driven transfer framework that powers the near real-time workflows and Cross-bucket Replication services.
At Uber, built Uber/Fx, the dependency injection framework that powers Uber's Go microservices and is now used by thousands of Go developers worldwide.
Reachable at anup@polign.com
Polign Recall and polign_db are built and published by Polign, Inc., a Delaware corporation.
Be part of the next chapter.
Tell us what you are building, and we will get back to you.