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).

Product upvotes vs the next 3

Waiting for data. Loading

Product comments vs the next 3

Waiting for data. Loading

Product upvote speed vs the next 3

Waiting for data. Loading

Product upvotes and comments

Waiting for data. Loading

Product vs the next 3

Loading

Oort Memory

Memory for AI agents that stays correct as facts change

Oort is open-source memory for AI agents. When a fact changes, the old one is closed out, not overwritten, so your agent recalls what is true now and can still ask what was true in March. Unused memories drift to compressed cold storage, so cost stays flat as history grows. Every recall says why it was picked. Works with Claude Code, Codex, Cursor, Gemini CLI, VS Code and any MCP client, and in your own code through TypeScript and Python SDKs. Free with your own keys, or Oort Pro at $19/month.

Top comment

Hi Product Hunt, I'm Marcus. I build Oort from Gothenburg.

I use coding agents every day, and their memory kept getting one thing wrong: a fact could never end. Tell an agent you moved from Berlin to Lisbon and a vector store keeps both, and the old one can still win. The store only grows, so stale facts keep coming back and the bill keeps climbing.

Oort treats memory as facts with a lifetime:

  • When a fact changes, the old one is closed out, not overwritten. Recall gives what is true now. You can still ask what was true on a date (--as-of), how a fact changed (--history), or what the agent believed back then (--known-at).

  • Three tiers keep cost flat. Photosphere is hot and ready, Kuiper Belt is warm and searched in milliseconds, Oort Cloud is cold and compressed. Unused facts drift out; recalled ones come back.

  • Every recall says why it was picked. oort explain shows each stage's rank and score.

It's open source (Apache 2.0). npm i -g oortmem, then oort setup connects Claude Code, Claude Desktop, Codex, Cursor, Gemini CLI or VS Code.

New this month: SDKs for TypeScript and Python. import { createOort } from 'oortmem' or from oortmem import Oort gives your own agent the same memory, on your machine or in Oort Cloud, with tested examples for the Vercel AI SDK, LangGraph, the OpenAI Agents SDK and CrewAI. Keyword search also handles Chinese, Japanese, Korean, Thai and Indic text, with each fact kept in the language you wrote it in.

If you don't want to manage API keys, Oort Pro is $19/month: memories stored in the EU, a dashboard where your memory is a star map, and a connector so claude.ai and ChatGPT can use the same memory.

If you're building agents for your own customers, each of them can have a memory of their own today, in your own deployment or in Oort Cloud. We're taking a few design partners: oortcloud.dev/enterprise

What I'd love to hear: where your agent's memory goes wrong today, and whether the time modes match how you think about "what was true when". I'm here all day to answer.

About Oort Memory on Product Hunt

“Memory for AI agents that stays correct as facts change”

Oort Memory was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #347 on the daily leaderboard. Oort is open-source memory for AI agents. When a fact changes, the old one is closed out, not overwritten, so your agent recalls what is true now and can still ask what was true in March. Unused memories drift to compressed cold storage, so cost stays flat as history grows. Every recall says why it was picked. Works with Claude Code, Codex, Cursor, Gemini CLI, VS Code and any MCP client, and in your own code through TypeScript and Python SDKs. Free with your own keys, or Oort Pro at $19/month.

On the analytics side, Oort Memory competes within Open Source, Developer Tools and Artificial Intelligence — topics that collectively have 1.1M followers on Product Hunt. The dashboard above tracks how Oort Memory performed against the three products that launched closest to it on the same day.

Who hunted Oort Memory?

Oort Memory was hunted by Marcus Ong. 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.

For a complete overview of Oort Memory including community comment highlights and product details, visit the product overview.