Back to Arena

Swarms

by kyegomez / Swarms Corp

System Card

Organizationkyegomez / Swarms Corp
Released2023-07
Architectureagentic-workflow / Enterprise multi-agent orchestration with persistent memory
DetailsWorkflow patterns (Sequential, Concurrent, AgentRearrange, Graph, MoA, Group Chat, Hierarchical, Heavy). MCP/X402/AOP integration. Agents support long-running memory across workflow runs.
Parameters—
Domainagent-memory
Open SourceYes
WebsiteVisit
CodeRepository
multi-agentmcpenterpriseworkflow-patterns

Capability Profile

Benchmark Scores

5 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
1/2
LoCoMo
79.482p
MemoryBank
no data
Cross-Session Memory
1/1
LongMemEval
8494p
Multi-Hop QA
2/3
BABILong
no data
MultiHop-RAG
73.263p
HotpotQA
74.466p
Agent Task Memory
1/1
AgentBench-Mem
7226p
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
0/1
RAGAS
no data
Sources:Swarms (kyegomez/swarms); evaluated on AgentBench Memory Track (Tsinghua KEG, 2308)Swarms (kyegomez/swarms); evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)Swarms (kyegomez/swarms); evaluated on LoCoMo: Long-Term Conversational Memory Benchmark (Snap Research, 2402)Swarms (kyegomez/swarms); evaluated on LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (Salesforce AI Research, 2410)Swarms (kyegomez/swarms); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)