You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: src/oss/deepagents/overview.mdx
+31Lines changed: 31 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -4,7 +4,13 @@ sidebarTitle: Overview
4
4
description: Build agents that can plan, use subagents, and leverage file systems for complex tasks
5
5
---
6
6
7
+
:::python
7
8
[`deepagents`](https://pypi.org/project/deepagents/) is a standalone library for building agents that can tackle complex, multi-step tasks. Built on LangGraph and inspired by applications like Claude Code, Deep Research, and Manus, deep agents come with planning capabilities, file systems for context management, and the ability to spawn subagents.
9
+
:::
10
+
11
+
:::js
12
+
[`deepagents`](https://www.npmjs.com/package/deepagents) is a standalone library for building agents that can tackle complex, multi-step tasks. Built on LangGraph and inspired by applications like Claude Code, Deep Research, and Manus, deep agents come with planning capabilities, file systems for context management, and the ability to spawn subagents.
13
+
:::
8
14
9
15
## When to use deep agents
10
16
@@ -14,7 +20,13 @@ Use deep agents when you need agents that can:
14
20
-**Delegate work** to specialized subagents for context isolation
15
21
-**Persist memory** across conversations and threads
16
22
23
+
:::python
17
24
For simpler use cases, consider using LangChain's [`create_agent`](/oss/langchain/agents) or building a custom [LangGraph](/oss/langgraph/overview) workflow.
25
+
:::
26
+
27
+
:::js
28
+
For simpler use cases, consider using LangChain's [`createAgent`](/oss/langchain/agents) or building a custom [LangGraph](/oss/langgraph/overview) workflow.
29
+
:::
18
30
19
31
## Core capabilities
20
32
@@ -42,6 +54,7 @@ Deep agents applications can be deployed via [LangSmith Deployment](/langsmith/d
0 commit comments