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.
Active · Verified 2026-10-22 · fresh as of 2026-10-22 · 54 cited facts, 5 with a third-party source · 2 recorded changes · Suggest a correction
At a glance
- Type
- Pipeline-native ChatMessageStore vendor fix
- Tier
- T3
- Section
- Framework-embedded memory
- Created
- 2019 (Haystack OSS first released 2019; deepset founded 2018) third-party fix
- Latest release
- v3.4.1 (2026-10-21) repo fix
- License
- Apache-2.0 repo fix
- Pricing
- OSS free (Apache-2.0); Haystack Enterprise Platform: custom licensing + runtime fees + optional expert services vendor fix
- Funding
- $45.2M total; Series B $30M Aug 2023 led by Balderton Capital; Series A $14M Apr 2022 led by GV vendor fix
- Freshness
- 2026-10-22 fix
- Layer
- agent-infra repo fix
- Protocols
- mcp-client, opentelemetry vendor fix
- Developer activity
- OpenRank 26.07 (12-mo avg 20.68) · 172 participants — 2026-09 third-party fix
Memory 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
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
Alternatives to Haystack Memory (deepset) → live options ranked by shared design, licence, hosting and MCP support
Similar systems
Other framework-embedded memory in the catalog, ranked by inbound references.
- Spring AI ChatMemory T3
Wraps conversation memory behind an Advisor abstraction. MessageWindowChatMemory default 20-msg sliding window (preserves system messages); pluggable ChatMemoryRepository backends (in-memory, JDBC, Cassandra, Neo4j). Memory injected as cross-cutting concern at the ChatClient level.
- Flowise Memory T1
Discontinued: Flowise (acquired by Workday, Aug 2025) was sunset in 2026 — code freeze 2026-07-29, GitHub repo archived 2026-08-13, end of life 2026-08-31. Was a visual LangChain canvas with LangChain-native memory nodes (Buffer, Buffer Window, Conversation Summary Buffer) backed by an internal chat_message DB table; Buffer Window kept the last K interactions, Summary Buffer compressed older turns while keeping recent ones verbatim.
- 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
AutoGen's memory layer: ListMemory chronological context plus teachable agents that vectorise corrections; integrates with Mem0/Zep rather than building deep memory natively. Microsoft AutoGen is in maintenance mode (community managed, bug and security fixes only), and Microsoft points new projects to Microsoft Agent Framework.
- CrewAI Memory T2
Memory subsystem inside the CrewAI orchestration framework; integrates with Mem0 for the long-term tier.
- Hermes Agent memory (Nous Research) T3
Nous Research's open-source self-improving agent keeps an agent-curated MEMORY.md/USER.md notebook injected at session start, full-text (FTS5) search over past sessions that returns raw messages without LLM summarisation, and optional Honcho user modelling. one of the most-starred agent projects of 2026.
Sources (53 cited facts, 5 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Pipeline-native ChatMessageStore vendor
- What it does & what's distinct Haystack 2.x: InMemoryChatMessageStore (experimental) + ChatMessageRetriever + ChatMessa… vendor
- Claims / benefits Production via deepset Cloud; integrates Mem0 as a memory store alternative. vendor
- Modalities text vendor
- Created 2019 (Haystack OSS first released 2019; deepset founded 2018) third-party
- Latest release v3.4.1 (2026-10-21) repo
- License Apache-2.0 repo
- GitHub deepset-ai/haystack — ~26.2k stars, last commit 2026-10 repo
- Mindshare Used by Airbus, Lufthansa Industry Solutions, Infineon, LEGO, Comcast, Accenture, Netfli… vendor
- Funding $45.2M total; Series B $30M Aug 2023 led by Balderton Capital; Series A $14M Apr 2022 le… vendor
- Customers / scale European Commission, The Economist, Oxford University Press, German Federal Ministry of … third-party
- Pricing OSS free (Apache-2.0); Haystack Enterprise Platform: custom licensing + runtime fees + o… vendor
- Data handling Enterprise: fully managed cloud, VPC, or on-prem deployment; data stays in customer envi… vendor
- Deployment Both (OSS self-hosted; Haystack Enterprise Platform: SaaS cloud, VPC, or on-prem) vendor
- HQ Germany (Berlin) third-party
- Founders / pedigree Milos Rusic (CEO), Malte Pietsch (CTO), Timo Möller (CPO) — co-founded Berlin 2018; met … third-party
- Memory volume / scale no scale claim vendor
- Versioning immutable append-log vendor
- Tombstoning append-only no delete vendor
- Schema evolution free-form / no schema vendor
- Contradiction handling always append (no resolution) vendor
- Forgetting policy none (permanent) vendor
- MCP support via official adapter — haystack-mcp-tools repo
- OTel via adapter — OTel + Langfuse vendor
- Import / export JSON; many DocumentStore backends vendor
- Integration count 1 repo
- Orchestration single-agent vendor
- Programmatic control full CRUD via pipeline component (Python) vendor
- Pricing specifics OSS (Apache-2.0) free; deepset Cloud tier flat-rate + Enterprise Platform custom vendor
- Agent abstraction DAG (declarative pipeline) vendor
- Memory primitives multiple (InMemoryChatMessageStore + ConversationSummaryMemory + external) vendor
- LLM lock any (BYO via Generators) vendor
- Runtimes Python repo
- Session handling sticky session (pipeline-scoped) vendor
- Validated verticals RAG developers, enterprise search vendor
- Time to running <10min (pip install haystack-ai) vendor
- Anti-fit not for non-Haystack pipelines (pipeline-native) vendor
- Optimised for declarative pipelines + ChatMessageStore (experimental) vendor
- Adjacent infrastructure requires Haystack 2.x; BYO LLM + vector store vendor
- Pros Long-running deepset NLP heritage; strong document pipeline integration. vendor
- Cons Smaller AI-agent mind-share than LangChain; memory features less prominent than the broa… vendor
- Project & sources haystack.deepset.ai vendor
- download-trajectory [{"ym":"2025-11","monthly":235441,"cum":235441},{"ym":"2025-12","monthly":464389,"cum":6… registry
- cost-pricing-model subscription vendor
- cost-last-verified 2026-06-29 vendor
- architecture-deployment-locus hybrid vendor
- licensing-bucket open-core vendor
- positioning-platform-vs-product platform vendor
- taxonomy-three-layer-rollup agent-infra repo
- developer-activity-opendigger {"activity":491.07,"as_of":"2026-09","openrank_12mo":20.68,"openrank_current":26.07,"par… third-party
- sdk-languages python repo
- protocol-support mcp-client,opentelemetry vendor
- maturity ga registry
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
- 2026-10-23
- Pricing “OSS free (Apache-2.0); Haystack Enterprise Platform: custom licensing + runtime fees + optional expert services; no…” → “OSS free (Apache-2.0); Haystack Enterprise Platform: custom licensing + runtime fees + optional expert services” source
- 2026-10-22
- License “not applicable — not OSS” → “Apache-2.0” source
- Latest release “not applicable — not OSS” → “v3.4.1 (2026-10-21)” source
Related systems
References (1)
- Mem0 integrates with — 18k+ stars; production via deepset Cloud; integrates Mem0 as a memory store alternative.