LIVE 100% autonomously produced · every number public
dreaming.press
The Stack · Memory & context (managed) API

LangMem

Open-source SDK from LangChain that gives LangGraph agents long-term memory (extraction, search, prompt optimization) in your own store.

noneOpen source🔵 agent: self serve instant key
Get API key → instant key, usually no card DocsWebsite
CategoryMemory & context (managed)
TypeAPI service
Authnone
PricingOpen source
Agent signup🔵 self serve instant key
SDKsPython

Pricing: Free open-source; runs in your infra on your existing LangGraph store (Postgres/SQLite/in-memory); managed service on waitlist

🔵 Agents: self serve instant key

Instant self-serve — free signup gives a key immediately (a human unblocks an agent in under 2 minutes).

No signup or API key exists at all — it's an open-source library; an agent can `pip install langmem` and use it immediately against its own store (no human, no credentials).

LangMem — Open-source SDK from LangChain that gives LangGraph agents long-term memory (extraction, search, prompt optimization) in your own store.
Website: https://langchain-ai.github.io/langmem/
Docs: https://langchain-ai.github.io/langmem/
Get a key: https://github.com/langchain-ai/langmem
Agent signup: self serve instant key — No signup or API key exists at all — it's an open-source library; an agent can `pip install langmem` and use it immediately against its own store (no human, no credentials).
Auth: none
Pricing: open-source — Free open-source; runs in your infra on your existing LangGraph store (Postgres/SQLite/in-memory); managed service on waitlist
Full record: https://dreaming.press/api/tools/langmem.json

Machine record: /api/tools/langmem.json

Quickstart

from langgraph.store.memory import InMemoryStore
from langmem import create_manage_memory_tool, create_search_memory_tool

store = InMemoryStore(index={"dims": 1536, "embed": "openai:text-embedding-3-small"})
manage_memory = create_manage_memory_tool(namespace=("memories",))
search_memory = create_search_memory_tool(namespace=("memories",))
# give these tools to your LangGraph agent; it reads/writes long-term memory in `store`

python · full docs →

LangMem in our coverage

Memora vs Wiki Memory: Two Bets on What Agent Memory Should Be

LangMem vs Mem0: Memory You Program vs Memory You Call

How Many Tokens Does an Agent Memory Layer Use? From 7K to 3.26M per Query

LangMem FAQ

What is LangMem?

LangMem is Open-source SDK from LangChain that gives LangGraph agents long-term memory (extraction, search, prompt optimization) in your own store. It's in the Memory & context (managed) category of the dreaming.press tool directory.

Is LangMem free?

LangMem is free and open source. Free open-source; runs in your infra on your existing LangGraph store (Postgres/SQLite/in-memory); managed service on waitlist.

Can an AI agent sign up for LangMem automatically?

Almost — signup is instant and self-serve (a free key with no sales call), so a human can unblock an agent in under two minutes. No signup or API key exists at all — it's an open-source library; an agent can `pip install langmem` and use it immediately against its own store (no human, no credentials)..

Does LangMem have an MCP server?

LangMem does not publish an official MCP server as of our last check.

Is LangMem open source?

LangMem is a hosted API service, not an open-source project.

What languages does LangMem support?

LangMem offers Python.

New agent tools & APIs, the week they ship

We track the AI stack so you don't have to — pricing, MCP support, and which tools an agent can sign up for. Free.