Hindsight is open-source memory that lets AI agents learn from experience, #1 on every dataset of the Agent Memory Benchmark. Today it's 1.0, and the API is a promise. We're also launching Hindsight Memlake, a storage engine written in Rust that keeps agent memory in object storage: 100M memories at under 100 ms p99, with no database, consensus cluster or leader. Self-host it free, start on Hindsight Cloud with free credits, or run it in your own cloud with Enterprise.
When we launched Hindsight here, the idea was that agents should learn from experience the way people do, not just retrieve documents. After a year in production and #1 results on every dataset of the Agent Memory Benchmark, Hindsight is now 1.0. From here, the API is a promise.
The other half of this launch is the part I'm most excited about as the person who runs it: Hindsight Memlake, for Enterprise customers with very large memory volumes. Agent memory only grows, and every recall runs vector, keyword, graph and time search over all of it. So Nicolò and the team built a storage engine for that shape of data, in Rust:
• Object storage is the only source of truth: no database, no consensus cluster, no leader • Only two objects ever change, through conditional writes, and the protocols are model-checked in TLA+ • 100M memories at under 100 ms p99 on 4 servers, and recall on a 200k-memory bank went from 5.3 s on Postgres to 113 ms
Hat tip to turbopuffer, whose object-storage-first design inspired a lot of this.
Try Hindsight open source (MIT, runs on Postgres) or on Hindsight Cloud with free credits. Memlake comes with Hindsight Enterprise, and the full engineering write-up is here: https://hindsight.vectorize.io/b...
Happy to answer anything about agent memory, Memlake, or why we didn't just use Postgres.
Making this open source is a big plus. I'd love to see how developers use it to build agents tahat actually learn over time.
I like the idea of agents learning from past interactions instead of starting fresh every time. That could be ewally useful for long running tasks.
Storing agent memories in object storage without needing a separate database sounds interesting. The low-latency part is worth checking out too.
The API commitment caught my eye, Chris. With memory sitting inside an agent's workflow, predictable upgrades matter as much as the storage underneath.
About Hindsight 1.0 + Memlake on Product Hunt
“Open source memory for AI agents to learn from experience”
Hindsight 1.0 + Memlake launched on Product Hunt on October 14th, 2026 and earned 67 upvotes and 5 comments, placing #30 on the daily leaderboard. Hindsight is open-source memory that lets AI agents learn from experience, #1 on every dataset of the Agent Memory Benchmark. Today it's 1.0, and the API is a promise. We're also launching Hindsight Memlake, a storage engine written in Rust that keeps agent memory in object storage: 100M memories at under 100 ms p99, with no database, consensus cluster or leader. Self-host it free, start on Hindsight Cloud with free credits, or run it in your own cloud with Enterprise.
Hindsight 1.0 + Memlake was featured in Open Source (69k followers), Developer Tools (521.3k followers), Artificial Intelligence (481.3k followers) and GitHub (41.4k followers) on Product Hunt. Together, these topics include over 267.1k products, making this a competitive space to launch in.
Who hunted Hindsight 1.0 + Memlake?
Hindsight 1.0 + Memlake was hunted by Chris Bartholomew. 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.
Reviews
Hindsight 1.0 + Memlake has received 3 reviews on Product Hunt with an average rating of 5.00/5. Read all reviews on Product Hunt.
Want to see how Hindsight 1.0 + Memlake stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Chris Bartholomew
Hi Product Hunt, Chris from Vectorize here.
When we launched Hindsight here, the idea was that agents should learn from experience the way people do, not just retrieve documents. After a year in production and #1 results on every dataset of the Agent Memory Benchmark, Hindsight is now 1.0. From here, the API is a promise.
The other half of this launch is the part I'm most excited about as the person who runs it: Hindsight Memlake, for Enterprise customers with very large memory volumes. Agent memory only grows, and every recall runs vector, keyword, graph and time search over all of it. So Nicolò and the team built a storage engine for that shape of data, in Rust:
• Object storage is the only source of truth: no database, no consensus cluster, no leader
• Only two objects ever change, through conditional writes, and the protocols are model-checked in TLA+
• 100M memories at under 100 ms p99 on 4 servers, and recall on a 200k-memory bank went from 5.3 s on Postgres to 113 ms
Hat tip to turbopuffer, whose object-storage-first design inspired a lot of this.
Try Hindsight open source (MIT, runs on Postgres) or on Hindsight Cloud with free credits. Memlake comes with Hindsight Enterprise, and the full engineering write-up is here: https://hindsight.vectorize.io/b...
Happy to answer anything about agent memory, Memlake, or why we didn't just use Postgres.