deepagents

Create a deep agent.

By default, this agent has access to the following tools:

• write_todos: manage a todo list
• ls, read_file, write_file, edit_file, glob, grep: file operations
• execute: run shell commands
• task: call subagents

The execute tool allows running shell commands if the backend implements SandboxBackendProtocol. For non-sandbox backends, the execute tool will return an error message.

Specification for an async subagent running on a remote Agent Protocol server.

Async subagents connect to any Agent Protocol-compliant server via the LangGraph SDK. They run as background tasks that the main agent can monitor and update.

Compatible with LangGraph Platform (managed) and self-hosted servers. Authentication for LangGraph Platform is handled automatically by the SDK via environment variables (LANGGRAPH_API_KEY, LANGSMITH_API_KEY, or LANGCHAIN_API_KEY). For self-hosted servers, pass custom auth via headers.

Middleware for async subagents running on remote Agent Protocol servers.

This middleware adds tools for launching, monitoring, and updating background tasks on remote Agent Protocol servers. Unlike the synchronous SubAgentMiddleware, async subagents return immediately with a task ID, allowing the main agent to continue working while subagents execute.

Works with any Agent Protocol-compliant server — LangGraph Platform (managed) or self-hosted (e.g. a FastAPI server implementing the Agent Protocol spec).

Task IDs are persisted in the agent state under async_tasks so they survive context compaction/offloading and can be accessed programmatically.

Middleware for providing filesystem and optional execution tools to an agent.

This middleware adds filesystem tools to the agent: ls, read_file, write_file, edit_file, glob, and grep.

Files can be stored using any backend that implements the BackendProtocol.

If the backend implements SandboxBackendProtocol, an execute tool is also added for running shell commands.

This middleware also automatically evicts large tool results to the file system when they exceed a token threshold, preventing context window saturation.

A single access rule for filesystem operations.

Middleware for loading agent memory from AGENTS.md files.

Loads memory content from configured sources and injects into the system prompt.

Supports multiple sources that are combined together.

A pre-compiled agent spec.

When the subagent completes, the final message in the 'messages' list will be extracted and returned as a ToolMessage to the parent agent.

Specification for an agent.

When using create_deep_agent, subagents automatically receive a default middleware stack (TodoListMiddleware, FilesystemMiddleware, SummarizationMiddleware, etc.) before any custom middleware specified in this spec.

Middleware for providing subagents to an agent via a task tool.

This middleware adds a task tool to the agent that can be used to invoke subagents. Subagents are useful for handling complex tasks that require multiple steps, or tasks that require a lot of context to resolve.

A chief benefit of subagents is that they can handle multi-step tasks, and then return a clean, concise response to the main agent.

Subagents are also great for different domains of expertise that require a narrower subset of tools and focus.

Edits applied to the auto-added general-purpose subagent.

These settings only affect the default subagent that create_deep_agent inserts when the caller does not explicitly provide a subagent named general-purpose.

Runtime configuration for deep agent behavior.

A HarnessProfile describes prompt-assembly, tool visibility, middleware, and default-subagent adjustments applied by create_deep_agent once a chat model has been constructed. Profiles are registered via register_harness_profile under a provider key ("openai") or a full provider:model key ("openai:gpt-5.4").

This complements ProviderProfile, which controls the model-construction phase (e.g. init_chat_model kwargs, pre-init side effects). Concerns that shape how the model is built belong in ProviderProfile; concerns that shape how the agent runs belong here.

For YAML/JSON-backed profiles, use HarnessProfileConfig, which contains only the declarative subset and can be passed directly to register_harness_profile.

The extra_middleware field expects langchain.agents.middleware.types.AgentMiddleware instances or a factory returning a sequence of them.

Declarative harness-profile config for YAML/JSON-backed profiles.

A HarnessProfileConfig contains the file-friendly subset of harness settings: plain strings, bools, lists, and nested dicts that can be loaded from YAML or JSON. For in-code/runtime-only adjustments such as extra_middleware or class-form excluded_middleware, use HarnessProfile instead.

Config objects may be passed directly to register_harness_profile; the helper converts them to runtime HarnessProfile objects automatically.

Declarative configuration for constructing a chat model.

A ProviderProfile describes provider- or model-specific kwargs, pre-initialization side effects, and runtime-derived kwargs that should be applied when resolve_model turns a string spec (e.g. "openai:gpt-5.4") into a BaseChatModel. Profiles are registered via register_provider_profile under a provider key ("openai") or a full provider:model key ("openai:gpt-5.4").

Profiles handle model-construction concerns only — things that shape how init_chat_model assembles the client instance. Typical examples: constructor kwargs like use_responses_api, temperature, max_tokens, or base_url; provider-specific headers such as OpenRouter app attribution; pre-construction checks like minimum-version enforcement; and env-var-aware defaults.

Runtime and harness behavior — system-prompt assembly, tool description overrides, excluded tools, extra middleware, general-purpose subagent configuration — belongs in HarnessProfile, the separate harness profile system consumed by create_deep_agent, not here.

Primary graph assembly module for Deep Agents.

Provides create_deep_agent, the main entry point for constructing a fully configured deep agent with planning, filesystem, subagent, and summarization middleware.

Middleware for the Deep Agents agent.

Overview

The LLM receives tools through two paths:

1. SDK middleware (this package) -- tools, system-prompt injection, and request interception that any SDK consumer gets automatically.
2. Consumer-provided tools -- plain callable functions passed via the tools parameter to create_deep_agent(). The CLI uses this path for lightweight, consumer-specific tools.

Both are merged by create_deep_agent() into the final tool set the LLM sees.

Why middleware instead of plain tools?

Middleware subclasses AgentMiddleware, overriding its wrap_model_call() hook that intercepts every LLM request before it is sent. This lets middleware:

• Filter tools dynamically -- e.g. FilesystemMiddleware removes the execute tool at call-time when the resolved backend doesn't support it.
• Inject system-prompt context -- e.g. MemoryMiddleware and SkillsMiddleware inject relevant instructions into the system message on every call so the LLM knows how to use the tools they provide.
• Transform messages -- e.g. SummarizationMiddleware counts tokens, truncates old tool arguments, and replaces history with summaries when the context window fills up.
• Maintain cross-turn state -- middleware can read/write a typed state dict that persists across agent turns (e.g. summarization events).

A plain tool function in a tools=[] list cannot do any of this -- it is only invoked by the LLM, not before the LLM call.

When to use each path

Use middleware when the tool needs to:

• Modify the system prompt or tool list per-call
• Track state across turns
• Be available to all SDK consumers (not just the CLI)

Use a plain tool when:

• The function is stateless and self-contained
• No system-prompt or request modification is needed
• The tool is specific to a single consumer (e.g. CLI-only)

Public beta APIs for model and harness profiles.

Exposes the public ProviderProfile, HarnessProfile, and HarnessProfileConfig APIs for customizing how resolve_model constructs chat models and how create_deep_agent shapes agent runtime behavior.

Registration helpers are additive: re-registering under an existing key merges on top of the prior registration.

Memory backends for pluggable file storage.

Register a harness profile for a provider or specific model.

Accepts either a runtime HarnessProfile or a declarative HarnessProfileConfig. Config objects are converted to runtime profiles at registration time so YAML/JSON-backed callers do not need a separate manual conversion step.

Registrations are additive: if a profile is already registered under key (including a built-in profile loaded during lazy bootstrap), the new profile is merged on top rather than replacing it. The incoming profile's fields win on conflicts; unspecified fields inherit from the existing profile. Excluded-tool sets union, middleware sequences merge by type, and general_purpose_subagent settings merge field-wise.

To extend an existing registration, call register_harness_profile again under the same key:

from deepagents import HarnessProfile, register_harness_profile

# Layer a system-prompt suffix on top of the previous registration.
register_harness_profile(
    "openai:gpt-5.4",
    HarnessProfile(system_prompt_suffix="Respond in under 100 words."),
)

Register a ProviderProfile for a provider or specific model.

Registrations are additive: if a profile is already registered under key (including a built-in profile loaded during lazy bootstrap), the new profile is merged on top rather than replacing it. The incoming profile's fields win on conflicts; unspecified fields inherit from the existing profile. pre_init callables chain (existing runs first), and init_kwargs_factory callables chain — both factories are invoked at every resolution (base first, then override) and their outputs merge with the override's values winning on shared keys.

To layer additional kwargs onto a built-in profile, register under the same provider key. To override a built-in default (e.g. disable the OpenAI Responses API), set the conflicting key explicitly:

from deepagents import ProviderProfile, register_provider_profile

# Adds temperature alongside the built-in `use_responses_api=True`.
register_provider_profile("openai", ProviderProfile(init_kwargs={"temperature": 0}))

# Explicitly disables Responses API for OpenAI. (This will break usage,
# this example is purely illustrative.)
register_provider_profile(
    "openai",
    ProviderProfile(init_kwargs={"use_responses_api": False}),
)