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
Knowns
Persistent project memory for AI coding assistants
Knowns gives AI coding assistants structured access to your project's tasks, docs, specs, and memory. Open source. Local-first.
Hey Product Hunt! 👋
I'm howznguyen, and I built Knowns because I was frustrated with one thing: my AI coding assistant is incredibly smart, but it has the memory of a goldfish
Every morning I'd open Claude or Cursor and spend 10-15 minutes re-explaining my project. "We use the repository pattern." "Here's how auth works." "Remember, we decided last week to..." It felt like onboarding a new developer every single day.
So I built Knowns — a local-first project memory layer that gives AI assistants structured access to everything they need: tasks with acceptance criteria, documentation with cross-references, architectural decisions, coding conventions, and more.
The key insight: AI doesn't lack intelligence. It lacks access to what your project already knows.
With Knowns:
- Sessions start warm instead of cold
- AI follows `@doc/patterns/auth` instead of you pasting 50 lines
- Decisions persist in memory — AI recalls them automatically
- Tasks have clear "done" definitions — AI validates completion itself
It's fully open-source, local-first (no cloud, no API keys for core features), and works with any MCP-compatible AI assistant.
I'd love your feedback. What's the biggest pain point you have with AI coding assistants forgetting context?
About Knowns on Product Hunt
“Persistent project memory for AI coding assistants”
Knowns was submitted on Product Hunt and earned 3 upvotes and 1 comments, placing #160 on the daily leaderboard. Knowns gives AI coding assistants structured access to your project's tasks, docs, specs, and memory. Open source. Local-first.
On the analytics side, Knowns competes within Task Management, Open Source, Developer Tools and GitHub — topics that collectively have 706k followers on Product Hunt. The dashboard above tracks how Knowns performed against the three products that launched closest to it on the same day.
Who hunted Knowns?
Knowns was hunted by Howz Nguyen. 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 Knowns including community comment highlights and product details, visit the product overview.
Howz Nguyen