Hindsight Blog
Updates, insights, and deep dives into agent memory
Featured
Introducing Hindsight Memlake: serving 100M Memories at <100ms p99 on object storage
A new object-storage-native engine for Hindsight’s agent memory, built for fast retrieval, high-throughput ingest, and lower cost at scale.
What Changes Now That Hindsight Is a Hermes Plugin
Hindsight used to ship inside Hermes. It now installs from the plugin catalog. Your settings and memory are untouched, but one thing genuinely changed: where updates come from.
Enterprise Features in Hindsight Cloud
Every enterprise capability in Hindsight Cloud, and the failure each one prevents: single sign-on, MFA enforcement, role-based access, scoped API keys, audit logging, Memory Defense, webhooks, and bring-your-own-cloud or on-premise deployment.
Your OpenBot Agents Forget Between Threads. Give Them Shared Memory.
Connect an OpenBot agent to a Hindsight bank over MCP and its memory outlives the thread, survives compaction, and is shared with every teammate.
What's New in Hindsight Cloud: The API Is a Promise Now
Hindsight hit 1.0, most of Cloud moved onto a new storage engine, a bank's documents now travel in and out as a zip, and reflect shows its work.
We Got Early Access to NVIDIA Nemotron 3.5 Embed. It's Hindsight's New Top Embedding Model.
When NVIDIA gave us early access to Nemotron 3.5 Embed, we expected a solid embedding model. What we didn’t expect was for it to beat a model four times its size on memory retrieval and take the top spot on the Hindsight embedding leaderboard.
What's new in Hindsight 1.1.0
Per-document change history, tag globs and bank defaults for observation scopes, new LLM, embedding and reranker providers, knowledge-page downloads, and a long round of reliability fixes
Thirty Agents, One Memory
A swarm writes the same fact thirty times, and nothing ever merges two raw facts. Which layer turns that redundancy into evidence instead of clutter, and the three places concurrency changes the answer.
Four Things to Build With Vercel Eve and Hindsight
A team glossary that outlives the session, one customer across every channel, tenant isolation that is not a filter, and the memory your other AI tools already wrote.
50,000 GitHub Stars
Hindsight crossed 50,000 GitHub stars in 350 days, and shipped 1.0 and Hindsight Memlake in the same week.
Introducing Hindsight Memlake: serving 100M Memories at <100ms p99 on object storage
A new object-storage-native engine for Hindsight’s agent memory, built for fast retrieval, high-throughput ingest, and lower cost at scale.
Grok Bot Can Read What Your Other AI Tools Already Learned
Claude Code already knows your repo. ChatGPT already knows your preferences. With Hindsight, a Grok Bot can read those banks instead of making you explain it all again.