Agno (Phidata) Memory
https://docs.phidata.com/agents/memory
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.
At a glance
- Type
- AgentStorage + AgentMemory + DBs
- Tier
- T2
- Section
- Framework-embedded memory
- Created
- 2022-05
- Latest release
- v2.6.4 2026-04-28
- License
- Apache-2.0
- GitHub
- 39.9k★ +131/mo Python
- Pricing
- OSS free (Apache-2.0); Agno Cloud: usage-based, free tier; no per-event fees; no egress costs
- Funding
- $5M total Seed · 2023-01
Taxonomy
- storage
- relational
- retrieval
- similarity
- persistence
- cross-session
- update
- overwrite
- unit
- episode
- governance
- inspectable
- conflict
- overwrite
When to use
Optimised for: agent storage + memory + tools in one framework
Anti-fit: not for non-Agno stacks
Pros & cons
Pros
Postgres + pgvector default — operational simplicity for shops that already run Postgres.
Cons
Less first-class memory abstraction than dedicated memory layers; Agno is broader-than-memory framework.
Claims & capabilities
Rebranded from Phidata to Agno (January 2025); shifted from data engineering tool to dedicated agentic AI runtime. AgentOS runs in customer's own cloud (no data leaves system); flexible memory primitives from short-term context to long-term user-learning; built-in session management for many concurrent sessions
Technical surface
- API surface
- SDK: Python (Agno/Phidata Agent + Memory classes)
- Backend storage
- pluggable
- Deployment
- Both (self-hosted open source; Agno Cloud managed)
- Embedding model
- multiple supported
- Multi-tenancy
- namespace
- MCP
- via official adapter — agno MCP toolkit
- A2A
- searched not found
- OpenTelemetry
- first-class — built-in 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.
- 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.
- 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 (5)
- LanceDB integrates with — Single-line integrations with LanceDB, Pinecone, Weaviate, Qdrant.
- pgvector builds on — Postgres + pgvector default — operational simplicity for shops that already run Postgres.
- Pinecone integrates with — Single-line integrations with LanceDB, Pinecone, Weaviate, Qdrant.
- Qdrant integrates with — Single-line integrations with LanceDB, Pinecone, Weaviate, Qdrant.
- Weaviate integrates with — Single-line integrations with LanceDB, Pinecone, Weaviate, Qdrant.