Back to Arena

Heyday AI

by Heyday (shut down 2025)

System Card

OrganizationHeyday (shut down 2025)
Released2021-06
Architecturevector-rag / Browser-extension passive memory resurface
DetailsHeyday was a browser extension that silently saved every page visited, then automatically resurfaced relevant saved content alongside active Google and web searches. It built a personal knowledge graph from browsing history without requiring manual saves. The product raised $6.5M seed from Spark Capital in June 2022 but shut down in 2025 due to monetization challenges and competition.
Parameters—
Domainrag-retrievalpersonalizationlifelong-learning
Open SourceNo
WebsiteVisit
browser-extensionpassive-capturesecond-brainweb-memorydefunct

Capability Profile

Benchmark Scores

6 of 14 benchmarks
Long-Context Retrieval
0/5
RULER
no data
NIAH
no data
LooGLE
no data
LongBench
no data
∞Bench
no data
Multi-Turn Recall
2/2
LoCoMo
54.92p
MemoryBank
61.89p
Cross-Session Memory
1/1
LongMemEval
59.210p
Multi-Hop QA
2/3
BABILong
58.70p
MultiHop-RAG
no data
HotpotQA
67.236p
Agent Task Memory
0/1
AgentBench-Mem
no data
Personalization
1/1
PerLTQA
62.90p
Factuality / Grounding
0/1
RAGAS
no data
Sources:Heyday AI vendor documentation; evaluated on LoCoMo: Long-Term Conversational Memory Benchmark (Snap Research, 2402)Heyday AI vendor documentation; evaluated on LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (Salesforce AI Research, 2410)Heyday AI vendor documentation; evaluated on MemoryBank: Enhancing LLMs with Long-Term Memory (Sun Yat-sen University, 2305)Heyday AI vendor documentation; evaluated on PerLTQA: A Personal Long-Term Memory Question Answering Dataset (PolyU, 2402)Heyday AI vendor documentation; evaluated on BABILong: Testing the Limits of LLMs with Long-Context Reasoning-in-a-Haystack (AIRI, 2406)Heyday AI vendor documentation; evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)