AutoGineer
Generated banner for Deep Agents Memory
Generated logo for Deep Agents Memory

Deep Agents Memory

LangChainOfficialPublished by LangChain

  • Skill
  • Tool integration
  • Agent tooling
  • MIT
  • No issues found
Download ZIP

From the author

INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent), FilesystemMiddleware, and CompositeBackend for routing.
— the description by LangChain

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

Deep Agents memory provides a flexible system for managing agent state and file access through pluggable backends. It supports ephemeral storage for single-thread tasks, persistent storage for cross-session memory, and direct filesystem access for local development. By using a CompositeBackend, developers can route specific file paths to different storage types, enabling hybrid memory architectures within a single agent.

What it does

  • Provides StateBackend for thread-scoped ephemeral file storage.
  • Enables StoreBackend for persistent, cross-session memory.
  • Supports FilesystemBackend for direct disk access during local development.
  • Allows routing of different file paths to specific backends via CompositeBackend.
  • Includes standard file operation tools like read, write, edit, and grep.
  • Supports secure local development with virtualized path restrictions and human-in-the-loop interrupts.

When to use it

  • When an agent needs to maintain state across multiple conversation threads.
  • When you need to separate temporary working files from long-term user preferences.
  • When building local CLI tools that require reading or writing to the host filesystem.
  • When you need to implement custom memory logic using a persistent store.

Advantages

  • Highly configurable storage architecture.
  • Prevents accidental data loss by choosing the appropriate persistence layer.
  • Enhances security for local development through virtualized path modes.
  • Seamless integration with existing agent workflows and toolsets.

Usage examples

“Configure my agent to save files in /memories/ to a persistent store while keeping other files ephemeral.”
The agent is initialized with a CompositeBackend that routes /memories/ paths to a StoreBackend, ensuring persistence across threads.
“How do I safely allow my agent to edit local files during development?”
The agent is configured with a FilesystemBackend in virtual_mode=True, with interrupts enabled for write and edit operations to ensure human oversight.

Install

  1. Download the skill as a ZIP:

    https://autogineer.com/agent-skills/langchain-ai/deep-agents-memory/download

  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip deep-agents-memory.zip -d .agents/skills

Documentation by LangChain

<overview> Deep Agents use pluggable backends for file operations and memory:

Short-term (StateBackend): Persists within a single thread, lost when thread ends Long-term (StoreBackend): Persists across threads and sessions Hybrid (CompositeBackend): Route different paths to different backends

FilesystemMiddleware provides tools: ls, read_file, write_file, edit_file, glob, grep </overview>

<backend-selection>

Use CaseBackendWhy
Temporary working filesStateBackendDefault, no setup
Local development CLIFilesystemBackendDirect disk access
Cross-session memoryStoreBackendPersists across threads
Hybrid storageCompositeBackendMix ephemeral + persistent

</backend-selection>

<ex-default-state-backend> <python> Default StateBackend stores files ephemerally within a thread.

from deepagents import create_deep_agent

agent = create_deep_agent()  # Default: StateBackend
result = agent.invoke({
    "messages": [{"role": "user", "content": "Write notes to /draft.txt"}]
}, config={"configurable": {"thread_id": "thread-1"}})
# /draft.txt is lost when thread ends

</python> <typescript> Default StateBackend stores files ephemerally within a thread.

import { createDeepAgent } from "deepagents";

const agent = await createDeepAgent();  // Default: StateBackend
const result = await agent.invoke({
  messages: [{ role: "user", content: "Write notes to /draft.txt" }]
}, { configurable: { thread_id: "thread-1" } });
// /draft.txt is lost when thread ends

</typescript> </ex-default-state-backend>

<ex-composite-backend-for-hybrid> <python> Configure CompositeBackend to route paths to different storage backends.

from deepagents import create_deep_agent
from deepagents.backends import CompositeBackend, StateBackend, StoreBackend
from langgraph.store.memory import InMemoryStore

store = InMemoryStore()

composite_backend = lambda rt: CompositeBackend(
    default=StateBackend(rt),
    routes={"/memories/": StoreBackend(rt)}
)

agent = create_deep_agent(backend=composite_backend, store=store)

# /draft.txt -> ephemeral (StateBackend)
# /memories/user-prefs.txt -> persistent (StoreBackend)

</python> <typescript> Configure CompositeBackend to route paths to different storage backends.

import { createDeepAgent, CompositeBackend, StateBackend, StoreBackend } from "deepagents";
import { InMemoryStore } from "@langchain/langgraph";

const store = new InMemoryStore();

const agent = await createDeepAgent({
  backend: (config) => new CompositeBackend(
    new StateBackend(config),
    { "/memories/": new StoreBackend(config) }
  ),
  store
});

// /draft.txt -> ephemeral (StateBackend)
// /memories/user-prefs.txt -> persistent (StoreBackend)

</typescript> </ex-composite-backend-for-hybrid>

<ex-cross-session-memory> <python> Files in /memories/ persist across threads via StoreBackend routing.

# Using CompositeBackend from previous example
config1 = {"configurable": {"thread_id": "thread-1"}}
agent.invoke({"messages": [{"role": "user", "content": "Save to /memories/style.txt"}]}, config=config1)

config2 = {"configurable": {"thread_id": "thread-2"}}
agent.invoke({"messages": [{"role": "user", "content": "Read /memories/style.txt"}]}, config=config2)
# Thread 2 can read file saved by Thread 1

</python> <typescript> Files in /memories/ persist across threads via StoreBackend routing.

// Using CompositeBackend from previous example
const config1 = { configurable: { thread_id: "thread-1" } };
await agent.invoke({ messages: [{ role: "user", content: "Save to /memories/style.txt" }] }, config1);

const config2 = { configurable: { thread_id: "thread-2" } };
await agent.invoke({ messages: [{ role: "user", content: "Read /memories/style.txt" }] }, config2);
// Thread 2 can read file saved by Thread 1

</typescript> </ex-cross-session-memory>

<ex-filesystem-backend-local-dev> <python> Use FilesystemBackend for local development with real disk access and human-in-the-loop.

from deepagents import create_deep_agent
from deepagents.backends import FilesystemBackend
from langgraph.checkpoint.memory import MemorySaver

agent = create_deep_agent(
    backend=FilesystemBackend(root_dir=".", virtual_mode=True),  # Restrict access
    interrupt_on={"write_file": True, "edit_file": True},
    checkpointer=MemorySaver()
)

# Agent can read/write actual files on disk

</python> <typescript> Use FilesystemBackend for local development with real disk access and human-in-the-loop.

import { createDeepAgent, FilesystemBackend } from "deepagents";
import { MemorySaver } from "@langchain/langgraph";

const agent = await createDeepAgent({
  backend: new FilesystemBackend({ rootDir: ".", virtualMode: true }),
  interruptOn: { write_file: true, edit_file: true },
  checkpointer: new MemorySaver()
});

</typescript>

Security: Never use FilesystemBackend in web servers - use StateBackend or sandbox instead. </ex-filesystem-backend-local-dev>

<ex-store-in-custom-tools> <python> Access the store directly in custom tools for long-term memory operations.

from langchain.tools import tool, ToolRuntime
from langchain.agents import create_agent
from langgraph.store.memory import InMemoryStore

@tool
def get_user_preference(key: str, runtime: ToolRuntime) -> str:
    """Get a user preference from long-term storage."""
    store = runtime.store
    result = store.get(("user_prefs",), key)
    return str(result.value) if result else "Not found"

@tool
def save_user_preference(key: str, value: str, runtime: ToolRuntime) -> str:
    """Save a user preference to long-term storage."""
    store = runtime.store
    store.put(("user_prefs",), key, {"value": value})
    return f"Saved {key}={value}"

store = InMemoryStore()

agent = create_agent(
    model="gpt-4.1",
    tools=[get_user_preference, save_user_preference],
    store=store
)

</python> </ex-store-in-custom-tools>

<boundaries> ### What Agents CAN Configure

  • Backend type and configuration

  • Routing rules for CompositeBackend

  • Root directory for FilesystemBackend

  • Human-in-the-loop for file operations

What Agents CANNOT Configure

  • Tool names (ls, read_file, write_file, edit_file, glob, grep)

  • Access files outside virtual_mode restrictions

  • Cross-thread file access without proper backend setup

    </boundaries>

<fix-storebackend-requires-store> <python> StoreBackend requires a store instance.

# WRONG
agent = create_deep_agent(backend=lambda rt: StoreBackend(rt))

# CORRECT
agent = create_deep_agent(backend=lambda rt: StoreBackend(rt), store=InMemoryStore())

</python> <typescript> StoreBackend requires a store instance.

// WRONG
const agent = await createDeepAgent({ backend: (c) => new StoreBackend(c) });

// CORRECT
const agent = await createDeepAgent({ backend: (c) => new StoreBackend(c), store: new InMemoryStore() });

</typescript> </fix-storebackend-requires-store>

<fix-statebackend-files-dont-persist> <python> StateBackend files are thread-scoped - use same thread_id or StoreBackend for cross-thread access.

# WRONG: thread-2 can't read file from thread-1
agent.invoke({"messages": [...]}, config={"configurable": {"thread_id": "thread-1"}})  # Write
agent.invoke({"messages": [...]}, config={"configurable": {"thread_id": "thread-2"}})  # File not found!

</python> <typescript> StateBackend files are thread-scoped - use same thread_id or StoreBackend for cross-thread access.

// WRONG: thread-2 can't read file from thread-1
await agent.invoke({ messages: [...] }, { configurable: { thread_id: "thread-1" } });  // Write
await agent.invoke({ messages: [...] }, { configurable: { thread_id: "thread-2" } });  // File not found!

</typescript> </fix-statebackend-files-dont-persist>

<fix-path-prefix-for-persistence> <python> Path must match CompositeBackend route prefix for persistence.

# With routes={"/memories/": StoreBackend(rt)}:
agent.invoke(...)  # /prefs.txt -> ephemeral (no match)
agent.invoke(...)  # /memories/prefs.txt -> persistent (matches route)

</python> <typescript> Path must match CompositeBackend route prefix for persistence.

// With routes: { "/memories/": StoreBackend }:
await agent.invoke(...);  // /prefs.txt -> ephemeral (no match)
await agent.invoke(...);  // /memories/prefs.txt -> persistent (matches route)

</typescript> </fix-path-prefix-for-persistence>

<fix-production-store> <python> Use PostgresStore for production (InMemoryStore lost on restart).

# WRONG                              # CORRECT
store = InMemoryStore()              store = PostgresStore(connection_string="postgresql://...")

</python> <typescript> Use PostgresStore for production (InMemoryStore lost on restart).

// WRONG                                    // CORRECT
const store = new InMemoryStore();          const store = new PostgresStore({ connectionString: "..." });

</typescript> </fix-production-store>

<fix-filesystem-backend-needs-virtual-mode> <python> Enable virtual_mode=True to restrict path access (prevents ../ and ~/ escapes).

backend = FilesystemBackend(root_dir="/project", virtual_mode=True)  # Secure

</python> </fix-filesystem-backend-needs-virtual-mode>

<fix-longest-prefix-match> <python> CompositeBackend matches longest prefix first.

routes = {"/mem/": StoreBackend(rt), "/mem/temp/": StateBackend(rt)}
# /mem/file.txt -> StoreBackend, /mem/temp/file.txt -> StateBackend (longer match)

</python> </fix-longest-prefix-match>

Files

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Needs Python

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by
LangChain
Publisher
LangChain (Official)
Source
langchain-ai/langchain-skills · config/skills/deep-agents-memory · commit 126c384
Licence
MIT License (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by LangChain or LangChain.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download deep-agents-memory.zip