Nicheloom visits: 58,457 all-time · 7,637 in the last 7 days

The opportunity tracker for new startups.

Today: 1,008 launches · Niche of the day: specialized calculation tools · See what launched today →

Kepos

Shared memory for teams and their AI agents

Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.

Want to reach these readers? Sponsor an issue.

Most AI memory tools give one agent recall. Most team wikis give humans a shared doc. Kepos does both: multiple AI agents and humans read/write the same memory in real time, with git-backed version history — nothing silently overwritten — and self-enforcing learnings, where a correction recorded once gets automatically blocked from recurring. Memory that behaves like code, not a mutable blob.

PH · launched Sep 17, 2026 · 8 upvotes (top 5%) · 0 views

Niche: ai agent memory infrastructure · 350 launches, 11 in the last 7 days ▼ -58% · Explore this niche →

Category and tags

  • Horizontal
  • Agent / copilot
  • B2B
  • AI-native
  • Commercial product
  • Productivity
  • Developer Tools
  • Artificial Intelligence

Visit website ↗ Source listing ↗

Could you build this?

Partial While an agent memory API with vector search is common, building a real-time collaborative, git-backed conflict-free shared state mesh between concurrent AI agents and humans requires intricate distributed state engineering.

What it would actually take: Building this requires a hybrid vector and CRDT/git-backed document store to handle concurrent edits from autonomous agents without race conditions or hallucinated overwrites. It involves implementing AST-aware diffing, automated semantic merge strategies, and an asynchronous consensus engine that runs consolidation algorithms across multiple agent context windows. Distributed systems and autonomous agent coordination expertise are required to prevent memory degradation and race conditions.

Competitors

Other products that read as similar to this one : 504 launches clear the similarity bar, closest 8 shown.

Attention rank: #71 of 505 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).

Launched 277 days after the earliest competitor.

The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.