Back to Arena

Charlie Mnemonic

by GoodAI

System Card

OrganizationGoodAI
Released2024-03
Architecturehybrid / Long-term + short-term + episodic triad
DetailsPersonal assistant combining Long-Term, Short-Term, and Episodic Memory. Learns facts, instructions, and skills from every interaction. Supports Chain-of-Thought and integrated recall. Local install with MIT license.
Parameters—
Domainpersonalizationagent-memorylifelong-learning
Open SourceYes
PaperView Paper
WebsiteVisit
CodeRepository
personal-assistantltm-stmlocalopen-sourcechain-of-thought

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
69.925p
MemoryBank
81.182p
Cross-Session Memory
1/1
LongMemEval
73.837p
Multi-Hop QA
1/3
BABILong
7768p
MultiHop-RAG
no data
HotpotQA
no data
Agent Task Memory
1/1
AgentBench-Mem
7226p
Personalization
1/1
PerLTQA
81.955p
Factuality / Grounding
0/1
RAGAS
no data
Sources:Charlie Mnemonic paper (); evaluated on LoCoMo: Long-Term Conversational Memory Benchmark (Snap Research, 2402)Charlie Mnemonic paper (); evaluated on LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (Salesforce AI Research, 2410)Charlie Mnemonic paper (); evaluated on MemoryBank: Enhancing LLMs with Long-Term Memory (Sun Yat-sen University, 2305)Charlie Mnemonic paper (); evaluated on PerLTQA: A Personal Long-Term Memory Question Answering Dataset (PolyU, 2402)Charlie Mnemonic paper (); evaluated on AgentBench Memory Track (Tsinghua KEG, 2308)Charlie Mnemonic paper (); evaluated on BABILong: Testing the Limits of LLMs with Long-Context Reasoning-in-a-Haystack (AIRI, 2406)