Back to Arena

Langflow

by Langflow-ai (DataStax)

System Card

OrganizationLangflow-ai (DataStax)
Released2023-02
Architectureagentic-workflow / Visual flow builder with memory components
DetailsVisual authoring of LangChain-compatible flows + MCP server. Ships memory components (buffer, window, summary), vector store memory, and multi-agent orchestration.
Parameters—
Domainagent-memoryrag-retrieval
Open SourceYes
WebsiteVisit
CodeRepository
visual-builderlangchainmcp-serverdatastax

Capability Profile

Benchmark Scores

6 of 14 benchmarks
Long-Context Retrieval
1/5
RULER
no data
NIAH
no data
LooGLE
no data
LongBench
603p
∞Bench
no data
Multi-Turn Recall
1/2
LoCoMo
76.463p
MemoryBank
no data
Cross-Session Memory
1/1
LongMemEval
80.181p
Multi-Hop QA
2/3
BABILong
no data
MultiHop-RAG
7250p
HotpotQA
71.953p
Agent Task Memory
1/1
AgentBench-Mem
7226p
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
0/1
RAGAS
no data
Sources:Langflow (langflow-ai/langflow); evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)Langflow (langflow-ai/langflow); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)Langflow (langflow-ai/langflow); evaluated on AgentBench Memory Track (Tsinghua KEG, 2308)Langflow (langflow-ai/langflow); evaluated on LoCoMo: Long-Term Conversational Memory Benchmark (Snap Research, 2402)Langflow (langflow-ai/langflow); evaluated on LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Tsinghua KEG, 2308)Langflow (langflow-ai/langflow); evaluated on LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (Salesforce AI Research, 2410)