Catalog Systems Framework-embedded memory Pydantic-AI MemoryTool

Pydantic-AI MemoryTool

https://pydantic.dev/docs/ai/tools-toolsets/native-tools/

Pydantic AI Harness ships a Memory capability: a MEMORY.md notebook plus extra Markdown notes, exposed via write/read/delete/search memory tools and auto-injected into context; backends InMemory, File, SQLite, Postgres with per-user namespaces. Provider memory tools (e.g. Anthropic) remain available as builtin tools.

Active · Verified 2026-10-29 · fresh as of 2026-10-29 · 53 cited facts, 6 with a third-party source · 3 recorded changes · Suggest a correction

At a glance

Type
Tool-delegated to model provider vendor fix
Tier
T3
Section
Framework-embedded memory
Created
2024-12 (pydantic-ai launched December 2024) third-party fix
Latest release
not applicable — not OSS fix
License
MIT repo fix
GitHub
pydantic/pydantic-ai — ~19.6k stars, last commit n/a repo fix
Pricing
OSS free (MIT for pydantic-ai); pay for model provider API usage; Pydantic Logfire observability has separate pricing vendor fix
Funding
Pydantic (company) raised $17.2M total; Series A $12.5M Oct 2024 third-party fix
Freshness
2026-10-29 fix
Layer
agent-infra repo fix
Licensing
open-source repo fix
Deployment locus
local vendor fix
Platform vs product
platform vendor fix
Accelerator
sequoia-arc third-party fix
Maturity
ga registry fix
SDK languages
python vendor fix
Protocols
mcp-client vendor fix
Developer activity
OpenRank 63.72 (12-mo avg 80.15) · 384 participants — 2026-09 third-party fix

Memory taxonomy

storage
proprietary
retrieval
agentic
persistence
cross-session
update
agent-controlled
unit
fact
governance
opaque
conflict
none

When to use

Optimised for: model-provider memory delegation (DX)

Anti-fit: not for non-Anthropic providers (delegates to Anthropic memory tool)

Pros & cons

Pros

Type-safe memory primitive inside Pydantic-AI's agent design; clean SDK ergonomics.

Cons

Thinner feature surface than dedicated memory layers.

Claims & capabilities

Memory capability entirely delegated to model provider.

Technical surface

API surface
not applicable — research paper
Backend storage
not applicable — research paper
Deployment
Both (OSS self-hosted; Pydantic Logfire cloud for observability)
Embedding model
not applicable — research paper
Multi-tenancy
not applicable — research paper
MCP
native (first-party)
A2A
supported — Pydantic-AI A2A
OpenTelemetry
first-class — Logfire

Alternatives to Pydantic-AI MemoryTool → 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 (52 cited facts, 6 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. 2026-10-29
    • Homepage “https://pydantic.dev/docs/ai/tools-toolsets/builtin-tools/” → “https://pydantic.dev/docs/ai/tools-toolsets/native-tools/”
    #305
  2. 2026-10-23
    • Funding / ownership “Pydantic (company) raised $17.2M total; Series A $12.5M Oct 2024; investors include Sequoia Capital and Partech Par…” → “Pydantic (company) raised $17.2M total; Series A $12.5M Oct 2024” source
    #223
  3. 2026-10-22
    • License “not applicable — not OSS” → “MIT” source
    #195

Related systems

References (1)