Haystack Memory (deepset)

https://haystack.deepset.ai/

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

Tier
T3
Latest release
v3.4.1 (2026-10-21) repo fix
License
Apache-2.0 repo fix
Freshness
2026-10-22 fix
Layer
agent-infra repo fix
Licensing
open-core vendor fix
Deployment locus
hybrid vendor fix
Platform vs product
platform vendor fix
Maturity
ga registry fix
SDK languages
python repo 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

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 changed

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

  1. 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
    #223
  2. 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
    #195

Related systems

References (1)

  • Mem0 integrates with — 18k+ stars; production via deepset Cloud; integrates Mem0 as a memory store alternative.