Press Kit

REM Labs is the AI memory infrastructure layer.

+15.33pp on SWE-bench Lite (n=150, 95% CI [+9.33, +22.00], p<0.05, paired bootstrap). Everything journalists, analysts, and partners need to cover REM Labs.

REM Labs builds persistent memory infrastructure for AI agents. The platform provides a simple 3-call API (remember, recall, forget), the Dream Engine — a neuroscience-inspired overnight consolidation system with 9 strategies and 5 depth levels — and delivers +15.33pp on SWE-bench Lite (n=150, 95% CI [+9.33, +22.00], p<0.05, paired bootstrap n=1000). Self-hostable. MIT license. No lock-in.

+10.67pp
SWE-bench Lite (n=150, p<0.05)
<50ms
p95 recall latency
84
Integrations
5
Depth levels
9
Dream Engine strategies
99.7%
Uptime (90 days)

LongMemEval (ICLR 2025) — 500 questions, GPT-4o judge

System Accuracy
MemPalace 96.6%
AgentMemory 96.2%
Hindsight 94.6%
REM Labs 94.6%
Mem0 66.9%
Zep 64%
GPT-4 53%

REM scores 94.6% alongside Hindsight; MemPalace and AgentMemory lead the leaderboard. Full methodology and raw results at /benchmarks

  • Progressive depth consolidation. The only memory system that processes memories through 5 depth levels — raw, consolidated, synthesized, abstracted, archetypal. Memories compound in value over time instead of degrading.
  • Non-lossy supersession. When facts change, originals are preserved with full provenance chain. Competing systems either overwrite or create duplicates.
  • Compounding wiki pages. Related memories automatically consolidate into structured knowledge pages that grow richer with each Dream Engine cycle.
  • Dream Engine overnight consolidation. 9 neuroscience-inspired strategies run autonomously — contradiction detection, entity extraction, temporal decay, pattern synthesis, and more. No other memory provider offers this.

Solo Founder

Building REM Labs since 2025. The project started from the frustration of rebuilding RAG pipelines for every new AI application and watching them plateau at ~60% accuracy. The Dream Engine — inspired by how human REM sleep consolidates memories — was the architectural breakthrough that now delivers +15.33pp on SWE-bench Lite (n=150, 95% CI [+9.33, +22.00], p<0.05, paired bootstrap).

High-resolution screenshots available on request via press@remlabs.ai

Console

Developer Console

API keys, usage analytics, memory browser

Dream Engine

Dream Engine Dashboard

9-stage pipeline visualization, depth levels

Knowledge

Knowledge Browser

Graph view, wiki pages, entity explorer

The REM Labs logo is an orbital atom mark representing interconnected memory. Please do not modify, recolor, or distort the logo.

Logo Mark — Light Download SVG
Logo Mark — Dark Download SVG

For press inquiries, interview requests, media assets, and high-resolution screenshots — reach out directly.

press@remlabs.ai