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.
Active · Verified 2026-10-22 · fresh as of 2026-10-22 · 61 cited facts, 5 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- AgentStorage + AgentMemory + DBs vendor fix
- Tier
- T2
- Section
- Framework-embedded memory
- Latest release
- v3.1.8 (2026-10-21) registry fix
- License
- Apache-2.0 repo fix
- Pricing
- OSS free (Apache-2.0); Agno Cloud: usage-based, free tier; no per-event fees; no egress costs vendor fix
- Funding
- $5M total Seed · 2023-01 third-party fix
- Freshness
- 2026-10-22 fix
- Layer
- agent-infra repo fix
- Licensing
- open-source repo fix
- Protocols
- mcp-client, mcp-server vendor fix
- Developer activity
- OpenRank 54.96 (12-mo avg 66.96) · 285 participants — 2026-09 third-party fix
Memory 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
Alternatives to Agno (Phidata) Memory → 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 (60 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 AgentStorage + AgentMemory + DBs vendor
- What it does & what's distinct Agno (formerly Phidata). AgentStorage persists sessions to a DB; AgentMemory auto-classi… vendor
- Claims / benefits Rebranded from Phidata to Agno (January 2025); shifted from data engineering tool to ded… vendor
- Modalities text vendor
- Created 2022-05 vendor
- Latest release v3.1.8 (2026-10-21) registry
- License Apache-2.0 repo
- GitHub agno-agi/agno — ~42.8k stars, last release 2026-10 repo
- Mindshare 1790748/mo PyPI (agno pkg Apr third-party
- Funding $5M total Seed · 2023-01 third-party
- Customers / scale 1-10 ppl third-party
- Pricing OSS free (Apache-2.0); Agno Cloud: usage-based, free tier; no per-event fees; no egress … vendor
- Deployment Both (self-hosted open source; Agno Cloud managed) vendor
- HQ US (New York) vendor
- Founders / pedigree Ashpreet Bedi (founder & CEO); ex-Airbnb, Facebook/Instagram, Cisco; 15+ years ML/data i… third-party
- Memory volume / scale no scale claim vendor
- API surface SDK: Python (Agno/Phidata Agent + Memory classes) vendor
- Backend storage pluggable vendor
- Multi-tenancy namespace vendor
- Embedding model multiple supported vendor
- Versioning immutable append-log vendor
- Schema evolution schema with migration vendor
- Namespace primitives per-tenant vendor
- Contradiction handling always overwrite (last-write-wins) vendor
- Forgetting policy none (permanent) vendor
- MCP support via official adapter — agno MCP toolkit vendor
- OTel first-class — built-in OTel vendor
- Import / export JSON; multiple DB backends vendor
- Integration count 0 repo
- Orchestration both (single Agent or multi-Agent Teams with shared memory) vendor
- Programmatic control full CRUD via Python SDK vendor
- Pricing specifics OSS (Apache-2.0) free; Agno Cloud usage-based with free tier; no per-event fees; no egress vendor
- Agent abstraction multi-agent supervisor (Team) + actor (Agent) vendor
- Memory primitives multiple (AgentStorage DB + AgentMemory vector) vendor
- LLM lock any (BYO) vendor
- Runtimes Python repo
- Session handling persistent thread (per-session) vendor
- Validated verticals agent developers (horizontal) vendor
- Time to running <10min (pip install agno) vendor
- Anti-fit not for non-Agno stacks vendor
- Optimised for agent storage + memory + tools in one framework vendor
- Adjacent infrastructure requires Agno; BYO LLM + DBs (SQLite/Postgres) vendor
- Pros Postgres + pgvector default — operational simplicity for shops that already run Postgres. vendor
- Cons Less first-class memory abstraction than dedicated memory layers; Agno is broader-than-m… vendor
- Project & sources GitHub agno-agi/agno memory docs agno.com vendor
- commit-trajectory [{"ym":"2025-11","cum":4681},{"ym":"2025-12","cum":4875},{"ym":"2026-01","cum":5037},{"y… repo
- download-trajectory [{"ym":"2025-11","monthly":397643,"cum":397643},{"ym":"2025-12","monthly":1160316,"cum":… registry
- cost-input-usd-per-mtok 0 vendor
- cost-output-usd-per-mtok 0 vendor
- cost-tier free vendor
- cost-pricing-model free-tier vendor
- cost-last-verified 2026-06-29 vendor
- architecture-deployment-locus local vendor
- licensing-bucket open-source repo
- positioning-platform-vs-product platform vendor
- taxonomy-three-layer-rollup agent-infra repo
- developer-activity-opendigger {"activity":767.95,"as_of":"2026-09","openrank_12mo":66.96,"openrank_current":54.96,"par… third-party
- sdk-languages python repo
- protocol-support mcp-client,mcp-server 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)
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.