Back to Arena

CrewAI Enterprise

by CrewAI Inc.

System Card

OrganizationCrewAI Inc.
Released2024-01
Architectureagentic-workflow / role-based multi-agent orchestration
DetailsCrewAI provides an open-source multi-agent framework using a role-based model (Crew, Agent, Task) inspired by organizational structures. The Enterprise tier adds managed execution, memory modules (short-term, long-term, entity, contextual), monitoring, and team collaboration. Agents share memory via a shared crew memory store backed by embeddings, enabling cross-agent knowledge transfer.
Parameters—
Domainagent-memoryepisodic-sessionlifelong-learning
Open SourcePartial
WebsiteVisit
multi-agentrole-basedcrew-memoryorchestrationenterprise

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
81.892p
MemoryBank
7759p
Cross-Session Memory
1/1
LongMemEval
82.190p
Multi-Hop QA
2/3
BABILong
71.413p
MultiHop-RAG
no data
HotpotQA
72.961p
Agent Task Memory
1/1
AgentBench-Mem
7226p
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
0/1
RAGAS
no data
Sources:CrewAI Enterprise vendor documentation; evaluated on LoCoMo: Long-Term Conversational Memory Benchmark (Snap Research, 2402)CrewAI Enterprise vendor documentation; evaluated on LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (Salesforce AI Research, 2410)CrewAI Enterprise vendor documentation; evaluated on AgentBench Memory Track (Tsinghua KEG, 2308)CrewAI Enterprise vendor documentation; evaluated on MemoryBank: Enhancing LLMs with Long-Term Memory (Sun Yat-sen University, 2305)CrewAI Enterprise vendor documentation; evaluated on BABILong: Testing the Limits of LLMs with Long-Context Reasoning-in-a-Haystack (AIRI, 2406)CrewAI Enterprise vendor documentation; evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)