← Back to the radar

Cross-platform governed memory for a fleet of agents

github.com · 1 day on the radar

RISING
Where is the demand coming from?
Mixed
Some genuine outside demand, some founder reach. This is the read that decides whether the traction would transfer to you.
Roughly what does it earn?
Not disclosedNo basis to estimate
We do not publish a figure until we have something to base it on. When we do, the method that produced it is shown alongside the range.
Could you build it?
Yes, in about 3 weeks
Nothing patented, no network effect, and no proprietary data set standing in the way.

What it is

Strata is a local-first shared memory system for coordinating fleets of AI coding agents on a single project. It uses an LLM judge to validate agent contributions before they enter shared state, preventing corruption from agent errors. The project launched on GitHub with minimal traction (1 HN point) but targets the emerging multi-agent orchestration problem.

The one thing to knowThe technical depth is high (embedded MCP server, SQLite storage, LLM-judged writes, audit trails) but the use case is nascent and unclear: it assumes a market for managed agent fleets that may not exist yet, and competitive tools from Anthropic or OpenAI could ship this as a feature rather than a standalone product.

Proof we found, with sources

HNThe Show HN post reached 1 points on Hacker News.23 Sept 2026 · source
HNThe Show HN post reached 1 points on Hacker News.23 Sept 2026 · source
HNThe Show HN post reached 1 points on Hacker News.23 Sept 2026 · source
HNThe Show HN post reached 1 points on Hacker News.23 Sept 2026 · source
HNThe Show HN post reached 1 points on Hacker News.23 Sept 2026 · source
HNThe Show HN post reached 1 points on Hacker News.23 Sept 2026 · source
HNThe Show HN post reached 1 points on Hacker News.23 Sept 2026 · source
HNThe Show HN post reached 1 points on Hacker News.23 Sept 2026 · source

The scores behind the verdict

Directional reads from public signals, 0 to 100
Show the four scores
TractionWeak8 / 100
How much demand shows up from people outside the founder's own circle.
CopyabilityFair45 / 100
How feasible it is for a competent builder to ship something comparable.
Wedge potentialFair35 / 100
How much room is left for a new entrant: gaps, ignored segments, pricing openings.
MonetizationUnproven0 / 100
How much evidence there is that people actually pay: visible pricing, revenue claims, a paid tier in use.

Unlock the full brief

How it works under the hood, how it gets customers, where it is weak, and the opening we would take, with a bottom-line verdict.

Sign in to unlock
One-time payment. Delivered in about a minute. Yours to keep.

Revenue, user and tactic numbers are evidence we found and attributed, with a confidence rating.
They are directional reads, never verified guarantees.