This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Polygres
Turn your entire database into a context window for AI
Polygres turns Postgres into working memory for AI agents. Retrieve structured rows, connected relationships, semantic matches, and full-text results through one hybrid API. All without a separate vector store, graph database, or sync pipeline. Build grounded agents over the data you already have, with relational, graph, and vector context joined at the source. Use the managed cloud or self-host with our open source components. Polygres is currently free to use, just sign up!
Hey Product Hunt 👋
We built Polygres because AI agents have a context problem.
Most teams solve this by adding more infrastructure: a vector database, a graph database, a search service, sync pipelines, and custom retrieval code to hold everything together.
We wanted a simpler model: What if the database itself became the agent’s context window? What if we could deploy graphRAG with one click?
You can use Polygres as a managed platform or work with the open-source SDK and your existing Postgres schema.
We’d especially love feedback from people building agents, copilots, memory systems, and AI-native products. Thanks for checking out Polygres. We’ll be here throughout the launch answering questions and learning from the community.
— Dale, Dalton & Damien
I saw Polygres on X and got a quick demo by its founder Dale. AMAZING PRODUCT AND EVEN AMAZING FOUNDER. would be using polygres in every one of my products from now. The infinite context window is real.
The one-store argument is the right one. Sync pipelines between a vector store and the source of truth are where most of these systems quietly go wrong, so removing the sync is worth more than any benchmark number you could put next to it.
The thing I would want to know: retrieving from the live database buys you freshness and costs you reproducibility.
If the agent's context is whatever the DB held at that moment, then the same question next Tuesday gets a different answer, and I cannot reconstruct what the agent was actually looking at when it made a call I now have to defend.
Anywhere there is an approval step, that matters more than latency does.
So does a retrieval come back with a receipt? Row ids, ranking, timestamp, stored next to the decision. Not for the agent. For the human who has to explain it three months later.
Congrats on shipping this! Turning Postgres itself into the retrieval layer instead of bolting on a vector store and a graph db is such a clean idea. I've been dealing with sync pipelines between Postgres and a separate vector store on my own agent project, this would've saved me weeks. Bookmarking for the next build.
Calling it infinite context is a stretch, but fetching more on demand instead of stuffing everything into one prompt is the right shape. Closer to how people actually recall things anyway.
Love the launch polygres team! How exactly do you guarantee an infinite context window?
ayo this is gonna solve a big old problem surely and make good relation work between claude code and codex, cant wait to use this myself 😉, my stupid claude can be good guy now thanks
I’m going to try this for my mental state agent. It always need more context
About Polygres on Product Hunt
“Turn your entire database into a context window for AI”
Polygres was submitted on Product Hunt and earned 58 upvotes and 29 comments, placing #13 on the daily leaderboard. Polygres turns Postgres into working memory for AI agents. Retrieve structured rows, connected relationships, semantic matches, and full-text results through one hybrid API. All without a separate vector store, graph database, or sync pipeline. Build grounded agents over the data you already have, with relational, graph, and vector context joined at the source. Use the managed cloud or self-host with our open source components. Polygres is currently free to use, just sign up!
Polygres was featured in Open Source (68.7k followers), Developer Tools (517.5k followers), GitHub (41.4k followers) and Database (2.2k followers) on Product Hunt. Together, these topics include over 121.9k products, making this a competitive space to launch in.
Who hunted Polygres?
Polygres was hunted by Dale Everett. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Polygres stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Dale Everett