Flowise Memory
https://docs.flowiseai.com/integrations/langchain/memory
Visual LangChain canvas. LangChain-native memory nodes (Buffer, Buffer Window, Conversation Summary Buffer) backed by internal chat_message DB table. Buffer Window limits to last K interactions; Summary Buffer compresses older turns while keeping recent verbatim.
At a glance
- Type
- Buffer + Buffer-Window + Conversation-Summary nodes
- Tier
- T1
- Section
- Framework-embedded memory
- Created
- 2023 (Flowise launched 2023; YC S23)
- Latest release
- not applicable — not OSS
- License
- not applicable — not OSS
- GitHub
- not applicable — no GitHub repo
- Pricing
- Pre-acquisition: Free OSS; Starter $35/mo; Pro $65/mo; Enterprise custom. Post-Workday acquisition Aug 2025: pricin…
- Funding
- $500K total Seed (YC) · 2023-01
Taxonomy
- storage
- vector
- retrieval
- similarity
- persistence
- session
- update
- append-only
- unit
- episode
- governance
- inspectable
- conflict
- append-only
When to use
Optimised for: visual LangChain canvas + memory nodes
Anti-fit: not for production-grade SLA workloads
Pros & cons
Pros
Visual builder lowers the bar for non-engineers to design memory pipelines; LangChain-compatible nodes.
Cons
Memory is as good as the LangChain primitive underneath — no novel architecture; less appealing to engineers building from code.
Claims & capabilities
Open source. Acquired by Workday August 2025.
Technical surface
- API surface
- REST, SDK: JS/TS
- Backend storage
- pluggable
- Deployment
- Both (OSS self-hosted; Flowise Cloud managed; air-gapped deployment supported)
- Embedding model
- multiple supported
- Multi-tenancy
- namespace
- MCP
- via official adapter — Flowise MCP node
- A2A
- searched not found
- OpenTelemetry
- searched not found
Compare Flowise Memory with…
Similar systems
Other framework-embedded memory in the catalog, ranked by inbound references.
- LangGraph Persistence T2
Distinct from LangMem. Built-in checkpointer saves graph state per super-step (short-term, thread-scoped). Store System adds long-term hierarchical key-value memory across threads with optional vector search + TTL. Postgres / Mongo / Redis stores for production.
- AutoGen Memory T2
ListMemory chronological context + teachable agents that vectorise corrections. Integrates with Mem0/Zep rather than building deep memory natively.
- CrewAI Memory T2
Memory subsystem inside the CrewAI orchestration framework; integrates with Mem0 for the long-term tier.
- AGiXT Adaptive Memory T2
Open-source AI automation platform. Routes between short-term and long-term memory adaptively across any LLM provider; plugin system for storage backends. Memory managed at the instruction-management layer — task context, instruction state, conversation history as unified agent state.
- Agno (Phidata) Memory T2
Agno (formerly Phidata). AgentStorage persists sessions to a DB; AgentMemory auto-classifies/store user preferences and conversation summaries. Single-line integrations with LanceDB, Pinecone, Weaviate, Qdrant.
- Botpress LLMz T1
Per-plan vector-DB storage quota + LLMz autonomous engine (in-session working memory) + Knowledge Base (semantic search over uploaded docs). Long-term user memory persists across sessions.
Related systems
References (2)
- LangChain (framework) integrates with — LangChain-native memory nodes (Buffer, Buffer Window, Conversation Summary Buffer)
- LangChain (framework) depends on at runtime — Visual LangChain canvas. LangChain-native memory nodes (Buffer, Buffer Window, Conversation Summary B