CrewAI Memory
Memory subsystem inside the CrewAI orchestration framework; integrates with Mem0 for the long-term tier.
At a glance
- Type
- Short-term + long-term + entity
- Tier
- T2
- Section
- Framework-embedded memory
- Created
- 2023-10
- Latest release
- 1.14.4 2026-04-30
- License
- MIT
- GitHub
- 50.7k★ +1.6k/mo Python
- Pricing
- Free + paid
- Funding
- $36M total Series A · 2024-10
Taxonomy
- storage
- vector
- retrieval
- similarity
- persistence
- long-term
- update
- extraction
- unit
- episode
- governance
- inspectable
- conflict
- llm-arbitrate
When to use
Optimised for: multi-agent orchestration with built-in memory tiers
Anti-fit: not for non-CrewAI stacks
Pros & cons
Pros
Memory tuned for multi-agent crews — handles per-agent and shared-crew memory cleanly.
Cons
Crew-specific framing; less idiomatic for single-agent designs.
Claims & capabilities
CrewAI raised $18M; reports use by ~60% of Fortune 500 companies; v0.28 (December 2025) added improved memory management. Short-term memory backed by ChromaDB + RAG; long-term + entity memory layers built in. Mature multi-agent ecosystem
Technical surface
- API surface
- SDK: Python (ShortTermMemory / LongTermMemory / EntityMemory)
- Backend storage
- pluggable (ChromaDB default)
- Deployment
- Both
- Embedding model
- multiple supported
- Multi-tenancy
- not applicable — library; namespace via crew/agent IDs
- MCP
- via official adapter — crewai-tools MCP
- A2A
- searched not found
- OpenTelemetry
- via adapter — AgentOps + OTel
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.
- 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.
- DSPy History T3
dspy.History primitive — typed field holding messages: list[dict] that slots into any Signature . No persistent memory of its own; purely a structured context-injection contract. DSPy's optimisation loop (MIPRO, BootstrapFewShot) treats historical turns as trainable few-shot structure.
Related systems
References (3)
- Chroma depends on at runtime — . Short-term memory backed by ChromaDB + RAG; long-term + entity memory layers built in. Mature mu
- Mem0 integrates with — Memory subsystem inside the CrewAI orchestration framework; integrates with Mem0 for the long-term tier.
- Mem0 depends on at runtime — adjacent-infrastructure cell: requires CrewAI; integrates Mem0 for long-term
Referenced by (1)
- mcp-memory-service (doobidoo) integrates with — Agent-pipeline focused (LangGraph, CrewAI, AutoGen)