LangGraph migration

pipeline/tools/docusaurus_parser.py

@@ -281,7 +281,7 @@ def replace_link(match: re.Match[str]) -> str:
 
                 return f"{link_text}({new_url})"
 
-            # Handle relative links (./file or ../category/file)
+            # Handle relative links (/oss/file or ../category/file)
             if link_url.startswith(("./", "../")) and link_url.endswith(".md"):
                 # Remove .md extension if present
                 new_url = link_url[:-3]  # Remove .md

src/docs.json

@@ -56,13 +56,229 @@
   },
   "navigation": {
     "dropdowns": [
+      {
+        "dropdown": "LangGraph",
+        "icon": "/images/brand/langgraph-pill.svg",
+        "description": "Framework for building reliable agents and workflows",
+        "tabs": [
+          {
+            "tab": "Get started",
+            "groups": [
+              {
+                "group": "Get started",
+                "pages": [
+                  "oss/overview",
+                  "oss/quickstart",
+                  "oss/run-an-agent",
+                  "oss/template-applications"
+                ]
+              },
+              {
+                "group": "General concepts",
+                "pages": [
+                  "oss/workflows-and-agents",
+                  "oss/prebuilt-vs-low-level",
+                  {
+                    "group": "Common agent architectures",
+                    "pages": [
+                      "oss/agentic-architectures",
+                      "oss/agentic-rag",
+                      "oss/agent-supervisor",
+                      "oss/sql-agent"
+                    ]
+                  }
+                ]
+              },
+              {
+                "group": "Additional resources",
+                "pages": [
+                  "oss/case-studies",
+                  "oss/faq",
+                  "oss/langgraph-academy"
+                ]
+              }
+            ]
+          },
+          {
+            "tab": "Build agents",
+            "groups": [
+              {
+                "group": "Basic configuration",
+                "pages": [
+                  "oss/prebuilts"
+                ]
+              },
+              {
+                "group": "Low-level configuration",
+                "pages": [
+                  "oss/why-langgraph",
+                  "oss/1-build-basic-chatbot",
+                  "oss/2-add-tools",
+                  "oss/3-add-memory",
+                  "oss/4-human-in-the-loop",
+                  "oss/5-customize-state",
+                  "oss/6-time-travel"
+                ]
+              },
+              {
+                "group": "Components",
+                "pages": [
+                  "oss/models",
+                  {
+                    "group": "Tools",
+                    "pages": [
+                      "oss/tools",
+                      "oss/call-tools"
+                    ]
+                  },
+                  {
+                    "group": "MCP",
+                    "pages": [
+                      "oss/mcp",
+                      "oss/use-mcp"
+                    ]
+                  },
+                  {
+                    "group": "Multi-agent",
+                    "pages": [
+                      "oss/multi-agent",
+                      "oss/multi-agent-prebuilts",
+                      "oss/multi-agent-custom"
+                    ]
+                  }
+                ]
+              }
+            ]
+          },
+          {
+            "tab": "Agent runtime",
+            "groups": [
+              {
+                "group": "Capabilities",
+                "pages": [
+                  "oss/persistence",
+                  "oss/durable-execution",
+                  {
+                    "group": "Streaming",
+                    "pages": [
+                      "oss/streaming",
+                      "oss/use-streaming"
+                    ]
+                  },
+                  {
+                    "group": "Human-in-the-loop",
+                    "pages": [
+                      "oss/human-in-the-loop",
+                      "oss/add-human-in-the-loop"
+                    ]
+                  },
+                  {
+                    "group": "Time travel",
+                    "pages": [
+                      "oss/time-travel",
+                      "oss/use-time-travel"
+                    ]
+                  },
+                  {
+                    "group": "Memory and context",
+                    "pages": [
+                      "oss/memory",
+                      "oss/context",
+                      "oss/add-memory"
+                    ]
+                  },
+                  {
+                    "group": "Subgraphs",
+                    "pages": [
+                      "oss/subgraphs",
+                      "oss/use-subgraphs"
+                    ]
+                  }
+                ]
+              },
+              {
+                "group": "Run and debug",
+                "pages": [
+                  "oss/local-server",
+                  "oss/ui",
+                  "oss/trace-agent",
+                  "oss/evals"
+                ]
+              },
+              {
+                "group": "LangGraph APIs",
+                "pages": [
+                  {
+                    "group": "Graph API",
+                    "pages": [
+                      "oss/graph-api",
+                      "oss/use-graph-api"
+                    ]
+                  },
+                  {
+                    "group": "Functional API",
+                    "pages": [
+                      "oss/functional-api",
+                      "oss/use-functional-api"
+                    ]
+                  },
+                  "oss/pregel"
+                ]
+              }
+            ]
+          },
+          {
+            "tab": "Reference",
+            "groups": [
+              {
+                "group": "LangGraph reference",
+                "pages": [
+                  "oss/reference/overview",
+                  "oss/reference/graphs",
+                  "oss/reference/functional-api",
+                  "oss/reference/pregel",
+                  "oss/reference/checkpointers",
+                  "oss/reference/storage",
+                  "oss/reference/caching",
+                  "oss/reference/types",
+                  "oss/reference/runtime",
+                  "oss/reference/config",
+                  "oss/reference/errors",
+                  "oss/reference/constants",
+                  "oss/reference/channels"
+                ]
+              },
+              {
+                "group": "Prebuilt reference",
+                "pages": [
+                  "oss/reference/agents",
+                  "oss/reference/supervisor",
+                  "oss/reference/swarm",
+                  "oss/reference/mcp"
+                ]
+              },
+              {
+                "group": "Error troubleshooting",
+                "pages": [
+                  "oss/common-errors",
+                  "oss/GRAPH_RECURSION_LIMIT",
+                  "oss/INVALID_CHAT_HISTORY",
+                  "oss/INVALID_CONCURRENT_GRAPH_UPDATE",
+                  "oss/INVALID_GRAPH_NODE_RETURN_VALUE",
+                  "oss/MULTIPLE_SUBGRAPHS"
+                ]
+              }
+            ]
+          }
+        ]
+      },
       {
         "dropdown": "LangGraph Platform",
         "icon": "/images/brand/langgraph-platform-pill.svg",
         "description": "Platform for building and deploying AI agents",
         "tabs": [
           {
-            "tab": "Get Started",
+            "tab": "Get started",
             "groups": [
               {
                 "group": "Overview",

src/index.mdx

@@ -8,7 +8,7 @@ mode: "wide"
 
 # Frameworks
 
-<CardGroup cols={2}>
+<CardGroup cols={3}>
   <Card
     title="LangChain - Python"
     href="https://python.langchain.com/docs/introduction/"
@@ -22,19 +22,10 @@ mode: "wide"
   >
   Open-source framework for developing applications powered by large language models (LLMs).
   </Card>
-</CardGroup>
 
-<CardGroup cols={2}>
   <Card
-    title="LangGraph - Python"
-    href="https://langchain-ai.github.io/langgraph/"
-  >
-  Low-level orchestration framework for building, managing, and deploying long-running, stateful agents.
-  </Card>
-
-  <Card
-    title="LangGraph - JavaScript"
-    href="https://langchain-ai.github.io/langgraphjs/"
+    title="LangGraph"
+    href="/oss"
   >
   Low-level orchestration framework for building, managing, and deploying long-running, stateful agents.
   </Card>
@@ -43,21 +34,14 @@ mode: "wide"
 
 # Platforms
 
-<CardGroup cols={3}>
+<CardGroup cols={2}>
   <Card
-    title="LangGraph Platform - Python"
-    href="https://langchain-ai.github.io/langgraph/concepts/langgraph_platform/"
+    title="LangGraph Platform"
+    href="/langgraph-platform/"
   >
     Commercial platform for developing, deploying, and scaling long-running agents and worflows.
   </Card>
 
-  <Card
-    title="LangGraph Platform - JavaScript"
-    href="https://langchain-ai.github.io/langgraphjs/concepts/#langgraph-platform"
-  >
-    Commercial platform for developing, deploying, and scaling long-running agents and workflows.
-  </Card>
-
   <Card
     title="LangSmith"
     href="https://docs.smith.langchain.com/"

src/langgraph-platform/add-human-in-the-loop.mdx

@@ -2,7 +2,7 @@
 title: Human-in-the-loop using server API
 sidebarTitle: Human-in-the-loop using server API
 ---
-To review, edit, and approve tool calls in an agent or workflow, use LangGraph's [human-in-the-loop](https://langchain-ai.github.io/langgraph/concepts/human_in_the_loop/) features.
+To review, edit, and approve tool calls in an agent or workflow, use LangGraph's [human-in-the-loop](/oss/human-in-the-loop) features.
 
 ## Dynamic interrupts
 
@@ -487,5 +487,5 @@ The following example shows how to add static interrupts:
 
 ## Learn more
 
-* [Human-in-the-loop conceptual guide](https://langchain-ai.github.io/langgraph/concepts/human_in_the_loop/): learn more about LangGraph human-in-the-loop features. 
-* [Common patterns](https://langchain-ai.github.io/langgraph/how-tos/human_in_the_loop/add-human-in-the-loop/#common-patterns): learn how to implement patterns like approving/rejecting actions, requesting user input, tool call review, and validating human input.
+* [Human-in-the-loop conceptual guide](/oss/human-in-the-loop): learn more about LangGraph human-in-the-loop features. 
+* [Common patterns](/oss/add-human-in-the-loop#common-patterns): learn how to implement patterns like approving/rejecting actions, requesting user input, tool call review, and validating human input.

src/langgraph-platform/assistants.mdx

@@ -17,7 +17,7 @@ The LangGraph Cloud API provides several endpoints for creating and managing ass
 
 ## Configuration
 
-Assistants build on the LangGraph open source concept of [configuration](https://langchain-ai.github.io/langgraph/concepts/low_level/#configuration).
+Assistants build on the LangGraph open source concept of [configuration](/oss/graph-api#configuration).
 While configuration is available in the open source LangGraph library, assistants are only present in [LangGraph Platform](/langgraph-platform/index). This is due to the fact that assistants are tightly coupled to your deployed graph. Upon deployment, LangGraph Server will automatically create a default assistant for each graph using the graph's default configuration settings.
 
 In practice, an assistant is just an _instance_ of a graph with a specific configuration. Therefore, multiple assistants can reference the same graph but can contain different configurations (e.g. prompts, models, tools). The LangGraph Server API provides several endpoints for creating and managing assistants. See the [API reference](https://langchain-ai.github.io/langgraph/cloud/reference/api/api_ref/) and [this how-to](/langgraph-platform/configuration-cloud) for more details on how to create assistants.
@@ -29,6 +29,6 @@ Once you've created an assistant, subsequent edits to that assistant will create
 
 ## Execution
 
-A **run** is an invocation of an assistant. Each run may have its own input, configuration, and metadata, which may affect execution and output of the underlying graph. A run can optionally be executed on a [thread](https://langchain-ai.github.io/langgraph/concepts/persistence/#threads).
+A **run** is an invocation of an assistant. Each run may have its own input, configuration, and metadata, which may affect execution and output of the underlying graph. A run can optionally be executed on a [thread](/oss/persistence#threads).
 
 The LangGraph Platform API provides several endpoints for creating and managing runs. See the [API reference](https://langchain-ai.github.io/langgraph/cloud/reference/api/api_ref/) for more details.

src/langgraph-platform/auth.mdx

@@ -181,7 +181,7 @@ For more information, see the [Use custom auth](/langgraph-platform/custom-auth#
 
 ### Agent authentication with MCP
 
-For information on how to authenticate an agent to an MCP server, see the [MCP conceptual guide](https://langchain-ai.github.io/langgraph/concepts/mcp/).
+For information on how to authenticate an agent to an MCP server, see the [MCP conceptual guide](/oss/mcp).
 
 ## Authorization
 

src/langgraph-platform/autogen-integration.mdx

@@ -6,8 +6,8 @@ This guide shows how to integrate AutoGen agents with LangGraph to leverage feat
 
 Integrating AutoGen with LangGraph provides several benefits:
 
-* Enhanced features: Add [persistence](https://langchain-ai.github.io/langgraph/concepts/persistence/), [streaming](/langgraph-platform/streaming), [short and long-term memory](https://langchain-ai.github.io/langgraph/concepts/memory/) and more to your AutoGen agents.
-* Multi-agent systems: Build [multi-agent systems](https://langchain-ai.github.io/langgraph/concepts/multi_agent/) where individual agents are built with different frameworks.
+* Enhanced features: Add [persistence](/oss/persistence), [streaming](/langgraph-platform/streaming), [short and long-term memory](/oss/memory) and more to your AutoGen agents.
+* Multi-agent systems: Build [multi-agent systems](/oss/multi-agent) where individual agents are built with different frameworks.
 * Production deployment: Deploy your integrated solution to [LangGraph Platform](/langgraph-platform/index) for scalable production use.
 
 ## Prerequisites
@@ -165,7 +165,7 @@ To find numbers between 10 and 30 in the Fibonacci sequence, we can generate the
 ...
 ```
 
-Since we're leveraging LangGraph's [persistence](https://langchain-ai.github.io/langgraph/concepts/persistence/) features we can now continue the conversation using the same thread ID -- LangGraph will automatically pass previous history to the AutoGen agent:
+Since we're leveraging LangGraph's [persistence](/oss/persistence) features we can now continue the conversation using the same thread ID -- LangGraph will automatically pass previous history to the AutoGen agent:
 
 ```python
 for chunk in graph.stream(

src/langgraph-platform/configure-ttl.mdx

@@ -4,7 +4,7 @@ sidebarTitle: Add TTLs to your LangGraph application
 ---
 <Tip>
   **Prerequisites**
-  This guide assumes familiarity with the [LangGraph Platform](/langgraph-platform/index), [Persistence](https://langchain-ai.github.io/langgraph/concepts/persistence/), and [Cross-thread persistence](https://langchain-ai.github.io/langgraph/concepts/persistence/#memory-store) concepts.
+  This guide assumes familiarity with the [LangGraph Platform](/langgraph-platform/index), [Persistence](/oss/persistence), and [Cross-thread persistence](/oss/persistence#memory-store) concepts.
 </Tip>
 
 <Note>
@@ -13,7 +13,7 @@ sidebarTitle: Add TTLs to your LangGraph application
 TTLs are only supported for LangGraph platform deployments. This guide does not apply to LangGraph OSS.
 </Note>
 
-The LangGraph Platform persists both [checkpoints](https://langchain-ai.github.io/langgraph/concepts/persistence/#checkpoints) (thread state) and [cross-thread memories](https://langchain-ai.github.io/langgraph/concepts/persistence/#memory-store) (store items). Configure Time-to-Live (TTL) policies in `langgraph.json` to automatically manage the lifecycle of this data, preventing indefinite accumulation.
+The LangGraph Platform persists both [checkpoints](/oss/persistence#checkpoints) (thread state) and [cross-thread memories](/oss/persistence#memory-store) (store items). Configure Time-to-Live (TTL) policies in `langgraph.json` to automatically manage the lifecycle of this data, preventing indefinite accumulation.
 
 ## Configuring Checkpoint TTL
 

src/langgraph-platform/control-plane.mdx

@@ -86,9 +86,9 @@ Database disk size for `Development` type deployments can be manually increased
 
 ### Database Provisioning
 
-The control plane and [LangGraph Data Plane](/langgraph-platform/data-plane) "listener" application coordinate to automatically create a Postgres database for each deployment. The database serves as the [persistence layer](https://langchain-ai.github.io/langgraph/concepts/persistence/#memory-store) for the deployment.
+The control plane and [LangGraph Data Plane](/langgraph-platform/data-plane) "listener" application coordinate to automatically create a Postgres database for each deployment. The database serves as the [persistence layer](/oss/persistence#memory-store) for the deployment.
 
-When implementing a LangGraph application, a [checkpointer](https://langchain-ai.github.io/langgraph/concepts/persistence/#checkpointer-libraries) does not need to be configured by the developer. Instead, a checkpointer is automatically configured for the graph. Any checkpointer configured for a graph will be replaced by the one that is automatically configured.
+When implementing a LangGraph application, a [checkpointer](/oss/persistence#checkpointer-libraries) does not need to be configured by the developer. Instead, a checkpointer is automatically configured for the graph. Any checkpointer configured for a graph will be replaced by the one that is automatically configured.
 
 There is no direct access to the database. All access to the database occurs through the [LangGraph Server](/langgraph-platform/langgraph-server).
 

src/langgraph-platform/data-plane.mdx

@@ -26,7 +26,7 @@ In other words, the data plane "listener" reads the latest state of the control
 
 ## Postgres
 
-Postgres is the persistence layer for all user, run, and long-term memory data in a LangGraph Server. This stores both checkpoints (see more info [here](https://langchain-ai.github.io/langgraph/concepts/persistence)), server resources (threads, runs, assistants and crons), as well as items saved in the long-term memory store (see more info [here](https://langchain-ai.github.io/langgraph/concepts/persistence/#memory-store)).
+Postgres is the persistence layer for all user, run, and long-term memory data in a LangGraph Server. This stores both checkpoints (see more info [here](/oss/persistence)), server resources (threads, runs, assistants and crons), as well as items saved in the long-term memory store (see more info [here](/oss/persistence#memory-store)).
 
 ## Redis