Back to Arena

Tab AI

by Tab (Avi Schiffmann)

System Card

OrganizationTab (Avi Schiffmann)
Released2024-06
Architectureepisodic-buffer / Always-on wearable necklace with ambient context accumulation
DetailsTab is a wearable AI necklace created by Avi Schiffmann that listens continuously to the user's environment and accumulates life context to function as a persistent personal AI. The device raised $1.9M and ships as a hardware companion to an iOS app that surfaces contextual insights from accumulated ambient data. It targets the "ambient AI" paradigm of replacing discrete query-response interactions with a continuously present intelligence.
Parameters—
Domainepisodic-sessionlifelong-learningpersonalization
Open SourceNo
WebsiteVisit
necklacewearableambient-aialways-oncontext-accumulationavi-schiffmann

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
71.728p
MemoryBank
82.891p
Cross-Session Memory
1/1
LongMemEval
79.272p
Multi-Hop QA
1/3
BABILong
72.117p
MultiHop-RAG
no data
HotpotQA
no data
Agent Task Memory
1/1
AgentBench-Mem
7226p
Personalization
1/1
PerLTQA
87.895p
Factuality / Grounding
0/1
RAGAS
no data
Sources:Tab AI vendor documentation; evaluated on LoCoMo: Long-Term Conversational Memory Benchmark (Snap Research, 2402)Tab AI vendor documentation; evaluated on LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (Salesforce AI Research, 2410)Tab AI vendor documentation; evaluated on MemoryBank: Enhancing LLMs with Long-Term Memory (Sun Yat-sen University, 2305)Tab AI vendor documentation; evaluated on PerLTQA: A Personal Long-Term Memory Question Answering Dataset (PolyU, 2402)Tab AI vendor documentation; evaluated on AgentBench Memory Track (Tsinghua KEG, 2308)Tab AI vendor documentation; evaluated on BABILong: Testing the Limits of LLMs with Long-Context Reasoning-in-a-Haystack (AIRI, 2406)