deep-agents-memory

INVOQUEZ CETTE COMPÉTENCE lorsque votre Deep Agent a besoin de mémoire, de persistance ou d’accès au système de fichiers. Couvre StateBackend (éphémère), StoreBackend (persistant),…

npx skills add https://github.com/langchain-ai/skills-benchmarks --skill deep-agents-memory
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

Use CaseBackendWhy
Temporary working filesStateBackendDefault, no setup
Local development CLIFilesystemBackendDirect disk access
Cross-session memoryStoreBackendPersists across threads
Hybrid storageCompositeBackendMix ephemeral + persistent
Default StateBackend stores files ephemerally within a thread. ```python 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.
```typescript
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
Configure CompositeBackend to route paths to different storage backends. ```python 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.
```typescript
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)
Files in /memories/ persist across threads via StoreBackend routing. ```python # 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.
```typescript
// 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
Use FilesystemBackend for local development with real disk access and human-in-the-loop. ```python 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.
```typescript
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()
});

Security: Never use FilesystemBackend in web servers - use StateBackend or sandbox instead.

Access the store directly in custom tools for long-term memory operations. ```python 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.
```python
# WRONG
agent = create_deep_agent(backend=lambda rt: StoreBackend(rt))

# CORRECT
agent = create_deep_agent(backend=lambda rt: StoreBackend(rt), store=InMemoryStore())
StoreBackend requires a store instance. ```typescript // 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.
```python
# 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!
StateBackend files are thread-scoped - use same thread_id or StoreBackend for cross-thread access. ```typescript // 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! ``` Path must match CompositeBackend route prefix for persistence. ```python # With routes={"/memories/": StoreBackend(rt)}: agent.invoke(...) # /prefs.txt -> ephemeral (no match) agent.invoke(...) # /memories/prefs.txt -> persistent (matches route) ``` Path must match CompositeBackend route prefix for persistence. ```typescript // With routes: { "/memories/": StoreBackend }: await agent.invoke(...); // /prefs.txt -> ephemeral (no match) await agent.invoke(...); // /memories/prefs.txt -> persistent (matches route) ``` Use PostgresStore for production (InMemoryStore lost on restart). ```python # WRONG # CORRECT store = InMemoryStore() store = PostgresStore(connection_string="postgresql://...") ``` Use PostgresStore for production (InMemoryStore lost on restart). ```typescript // WRONG // CORRECT const store = new InMemoryStore(); const store = new PostgresStore({ connectionString: "..." }); ``` Enable virtual_mode=True to restrict path access (prevents ../ and ~/ escapes). ```python backend = FilesystemBackend(root_dir="/project", virtual_mode=True) # Secure ``` CompositeBackend matches longest prefix first. ```python routes = {"/mem/": StoreBackend(rt), "/mem/temp/": StateBackend(rt)} # /mem/file.txt -> StoreBackend, /mem/temp/file.txt -> StateBackend (longer match) ```

Plus de skills de langchain-ai

deepagents-thread-inspector
langchain-ai
Inspecter et expliquer les conversations dans le stockage de sessions SQLite local de Deep Agents Code. À utiliser comme solution de repli lorsque l'outillage de traçage LangSmith est indisponible, pour…
deepagents-python-quickstart
langchain-ai
Créez un agent Deep minimal en local en Python en suivant le guide de démarrage rapide officiel, en utilisant la recherche web native du fournisseur au lieu de Tavily. Utilisez lorsque l’utilisateur souhaite…
deepagents-typescript-quickstart
langchain-ai
Scaffold a minimal local Deep Agent in TypeScript by following the official quickstart, using provider-native web search instead of Tavily. Use when the user…
eval-engineering
langchain-ai
Inspectez itérativement un dépôt d'agent et d'éventuelles traces fournies par l'utilisateur, interviewez l'utilisateur, puis créez, exécutez et auditez les evals Harbor un à la fois. À utiliser pour…
LangChain RAG Pipeline
langchain-ai
INVOQUEZ CETTE COMPÉTENCE lors de la construction de tout système de génération augmentée par récupération (RAG). Couvre les chargeurs de documents, RecursiveCharacterTextSplitter, les embeddings (OpenAI),…
LangChain Structured Output & HITL
langchain-ai
langchain-structured-output-&-hitl — une compétence installable pour agents IA, publiée par langchain-ai/langchain-skills.
LangSmith Datasets
langchain-ai
INVOQUEZ CETTE COMPÉTENCE lors de la création de jeux de données d'évaluation à partir de traces OU du téléchargement de jeux de données vers LangSmith OU de l'interrogation de jeux de données. Couvre les types de jeux de données (final_response,…)
langsmith-evaluator
langchain-ai
INVOQUEZ CETTE COMPÉTENCE lors de la construction de pipelines d'évaluation pour LangSmith. Couvre trois composants principaux : (1) Création d'évaluateurs - LLM comme juge, code personnalisé ; (2)…