Skills
Skill 2 of 22
INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access.
2 minutes · 462 words · 2 sections
Install
npx skills add langchain-ai/langchain-skills --skill deep-agents-memorynpx skills add langchain-ai/langchain-skills/plugin marketplace add langchain-ai/langchain-skillsThe first command installs just this skill, by the name in its SKILL.md; the second installs the whole repository.
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
| Use Case | Backend | Why |
|---|---|---|
| Temporary working files | StateBackend | Default, no setup |
| Local development CLI | FilesystemBackend | Direct disk access |
| Cross-session memory | StoreBackend | Persists across threads |
| Hybrid storage | CompositeBackend | Mix ephemeral + persistent |
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 endsimport { 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 endsfrom 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)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)# 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// 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 1from 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 diskimport { 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()
});Security: Never use FilesystemBackend in web servers - use StateBackend or sandbox instead.
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
)# WRONG
agent = create_deep_agent(backend=lambda rt: StoreBackend(rt))
# CORRECT
agent = create_deep_agent(backend=lambda rt: StoreBackend(rt), store=InMemoryStore())// WRONG
const agent = await createDeepAgent({ backend: (c) => new StoreBackend(c) });
// CORRECT
const agent = await createDeepAgent({ backend: (c) => new StoreBackend(c), store: new InMemoryStore() });# 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!// 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!# With routes={"/memories/": StoreBackend(rt)}:
agent.invoke(...) # /prefs.txt -> ephemeral (no match)
agent.invoke(...) # /memories/prefs.txt -> persistent (matches route)// With routes: { "/memories/": StoreBackend }:
await agent.invoke(...); // /prefs.txt -> ephemeral (no match)
await agent.invoke(...); // /memories/prefs.txt -> persistent (matches route)# WRONG # CORRECT
store = InMemoryStore() store = PostgresStore(connection_string="postgresql://...")// WRONG // CORRECT
const store = new InMemoryStore(); const store = new PostgresStore({ connectionString: "..." });backend = FilesystemBackend(root_dir="/project", virtual_mode=True) # Secureroutes = {"/mem/": StoreBackend(rt), "/mem/temp/": StateBackend(rt)}
# /mem/file.txt -> StoreBackend, /mem/temp/file.txt -> StateBackend (longer match)INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent), FilesystemMiddleware, and CompositeBackend for routing.
The verbatim description from this skill’s front matter — the string an agent matches on to decide whether to load it.
main, last pushed 23 September 2026.SKILL.md, not by matching a directory convention. One layout observed: config/skills/*/SKILL.md.h1 and no skipped levels:.claude-plugin/marketplace.json by LangChain, declaring 1 plugin. It is read for editorial metadata only — never as the skill index, which is always the repository tree./langchain-ai/langchain-skills.md, and each skill at its own .md URL.