Haystack Memory (deepset)
Haystack 2.x: InMemoryChatMessageStore (experimental) + ChatMessageRetriever + ChatMessageWriter components in declarative pipelines. Legacy: ConversationSummaryMemory with LLM-compressed rolling summaries. Memory is an explicit pipeline component with swappable backends.
At a glance
- Type
- Pipeline-native ChatMessageStore
- Tier
- T3
- Section
- Framework-embedded memory
- Created
- 2019 (Haystack OSS first released 2019; deepset founded 2018)
- Latest release
- not applicable — not OSS
- License
- not applicable — not OSS
- GitHub
- not applicable — no GitHub repo
- Pricing
- OSS free (Apache-2.0); Haystack Enterprise Platform: custom licensing + runtime fees + optional expert services; no…
- Funding
- $45.2M total; Series B $30M Aug 2023 led by Balderton Capital; Series A $14M Apr 2022 led by GV
Taxonomy
- storage
- kv
- retrieval
- exact-match
- persistence
- session
- update
- append-only
- unit
- document
- governance
- inspectable
- conflict
- append
When to use
Optimised for: declarative pipelines + ChatMessageStore (experimental)
Anti-fit: not for non-Haystack pipelines (pipeline-native)
Pros & cons
Pros
Long-running deepset NLP heritage; strong document pipeline integration.
Cons
Smaller AI-agent mind-share than LangChain; memory features less prominent than the broader pipeline.
Claims & capabilities
18k+ stars; production via deepset Cloud; integrates Mem0 as a memory store alternative.
Technical surface
- API surface
- not applicable — research paper
- Backend storage
- not applicable — research paper
- Deployment
- Both (OSS self-hosted; Haystack Enterprise Platform: SaaS cloud, VPC, or on-prem)
- Embedding model
- not applicable — research paper
- Multi-tenancy
- not applicable — research paper
- MCP
- via official adapter — haystack-mcp-tools
- A2A
- searched not found
- OpenTelemetry
- via adapter — OTel + Langfuse
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 (1)
- Mem0 integrates with — 18k+ stars; production via deepset Cloud; integrates Mem0 as a memory store alternative.