Skip to content
CAI
Software that uses CAICheck a score

langchain-ai/langgraph

59.1

Adequate · 14 November 2026

72.3k

lines of production code

Python

primary language

8

measurements over time

CAI band scale
CAI trend line
CAI lens gauges

What this system is

Features

Add CLI example project with Starlette app and LangGraph configuration

A new example project has been added to the CLI library, providing a complete template for users. This includes a Starlette-based Python application demonstrating middleware and context variable usage, alongside a \langgraph.json\ configuration file that defines graph endpoints and dependencies. The example also provides a Makefile for running the graphs via \uv\, a \.env.example\ for API key setup, and a pip configuration file.

libs/cli/examples · high confidence

Add CLI graph examples using the new Context API

Added example files for the CLI, including an agent graph implementation and its configuration. The agent example demonstrates the new Context API by defining an \AgentContext\ schema and using the \Runtime\ object to select between Anthropic and OpenAI models, replacing older configuration patterns. The \langgraph.json\ file registers these graph examples for CLI usage.

libs/cli/examples/graphs · high confidence

Add InMemoryCache with namespace-aware clearing

The memory cache module now includes an InMemoryCache implementation that stores cached values in a thread-safe dictionary. Users can retrieve, set, and clear cache entries by namespace. A key behavioral addition is the clear method, which now supports deleting all cached values when called without arguments, or selectively clearing specific namespaces when provided.

libs/checkpoint/langgraph/cache/memory · high confidence

Add LangGraph benchmark suite for performance profiling

The \libs/langgraph/bench\ directory now contains a comprehensive benchmark suite to measure and profile LangGraph performance. This includes scripts for running sequential graphs, fanout-to-subgraph patterns, REACT agents, and wide-state scenarios using both TypedDict and Pydantic state schemas. The suite also provides serialization/deserialization benchmarks and allows users to measure metrics such as first-event latency and overall execution time, helping developers identify performance bottlenecks in their graph implementations.

libs/langgraph/bench · high confidence

Add Redis-based node-level caching for LangGraph

A new Redis cache implementation has been added to the LangGraph checkpoint library, enabling users to store and retrieve graph execution results in a Redis backend. This feature supports both synchronous and asynchronous operations, allows for configurable key prefixes and time-to-live (TTL) settings, and includes logic to gracefully handle Redis unavailability by returning empty results or silently failing writes, ensuring system resilience.

libs/checkpoint/langgraph/cache/redis · high confidence

Add delta-channel-dump recovery script for Postgres-backed LangGraph threads

A new example script (dump.py) and documentation have been added to examples/delta-channel-dump to help recover message state from Postgres-backed LangGraph threads that use the DeltaChannel format (introduced in langgraph \>= 1.2). This tool is designed for rollback scenarios where an older runtime (e.g., deepagents 0.5.x or langgraph \< 1.2) cannot natively interpret the new msgpack EXT\_DELTA\_SNAPSHOT blobs. The script reads raw checkpoint data directly from Postgres tables (compatible with both OSS PostgresSaver and LangGraph Server deployments), decodes the delta snapshots, and outputs a JSON file containing the seed and writes for specified channels. Users can then manually re-apply this recovered state to the older runtime using the LangGraph SDK's update\_state method.

examples/delta-channel-dump · high confidence

Introduces the \InMemoryStore\ component in \libs/checkpoint/langgraph/store/memory\, providing a dictionary-backed key-value store that optionally supports semantic vector search. Users can now store and retrieve data in memory, and by configuring an \index\ with embedding dimensions and an embedding function, they can perform similarity searches on stored items. This feature is available for both synchronous and asynchronous workflows.

libs/checkpoint/langgraph/store/memory · high confidence

Added example LangGraph agent for monorepo testing

This change introduces a new example agent application within the CLI monorepo structure, designed to demonstrate multi-package dependency resolution. The agent defines a simple LangGraph workflow that imports and utilizes functions from sibling shared libraries (\shared\ and \common\), configured via a new \langgraph.json\ manifest and supported by a \.env.example\ file.

libs/cli/python-monorepo-example/apps/agent · high confidence

Added example agent application with shared library dependency

Introduced a new example agent application located in the \apps/agent\ directory, configured to run on Python 3.12 using LangGraph. The application defines a simple workflow that utilizes a \get\_dummy\_message\ function provided by a newly created shared library (\libs/shared\), demonstrating how to structure a monorepo with inter-package dependencies and environment configuration via \.env.example\.

libs/cli/uv-examples/monorepo/apps/agent, libs/cli/uv-examples/monorepo/libs/shared · high confidence

Added monorepo example projects for CLI testing

Added JavaScript and Python example projects under \libs/cli/js-monorepo-example\ and \libs/cli/python-monorepo-example\ to support monorepo testing within the CLI. The JavaScript example includes a LangGraph agent that imports utilities from a shared library, while the Python example provides common helper functions and shared utilities to validate monorepo structure and dependency resolution.

(repo-wide) · high confidence

Added prerelease requirements example for CLI graph validation

A new example directory \libs/cli/examples/graph\_prerelease\_reqs\ has been added to demonstrate how the CLI handles graph definitions that depend on prerelease versions of libraries. The example includes a \langgraph.json\ configuration specifying Python 3.12 and local dependencies, alongside an \agent.py\ file implementing a basic LangGraph agent workflow with tool calling capabilities.

_libs/cli/examples/graph\_prerelease\reqs · high confidence

Bundled UUIDv6 generation for checkpoint IDs

The checkpoint base library now includes a bundled implementation of UUID version 6 generation (id.py) to create sortable, time-ordered identifiers for checkpoints. This implementation is included directly in the codebase to avoid external installation issues with the uuid6 package, ensuring that checkpoint IDs are generated with improved database locality while maintaining compatibility with existing UUIDv1 systems.

libs/checkpoint/langgraph/checkpoint/base · high confidence

Initial release of the LangGraph CLI

This change introduces the official LangGraph command-line interface, providing tools to create, develop, build, and run LangGraph applications. The CLI includes commands for scaffolding new projects (\langgraph new\), running a development server with hot reloading (\langgraph dev\), launching the API in Docker (\langgraph up\), and building Docker images (\langgraph build\). It also supports generating custom Dockerfiles and uses a \langgraph.json\ configuration file to manage dependencies, graph definitions, and environment settings. The package is distributed under the MIT license and relies on \uv\ for dependency management.

libs/cli · high confidence

Initial release of the LangGraph CLI (v0.4.32)

This change introduces the LangGraph CLI as a new product component, establishing the initial codebase for version 0.4.32. The CLI provides a command-line interface for managing LangGraph applications, featuring local development and debugging capabilities (via the \up\ and \dev\ commands), remote deployment workflows (via the \deploy\ command and subcommands), and project archiving for remote builds. It includes configuration parsing for \langgraph.json\, Docker image building and management, and telemetry analytics reporting to Supabase.

_libs/cli/langgraph\cli · high confidence

Introduce LangGraph CLI with deployment, Docker, and dependency management capabilities

The \langgraph-cli\ package is introduced, providing a new command-line interface for managing LangGraph applications. This includes a comprehensive \deploy\ command (with subcommands for listing, deleting, and viewing logs) that supports agent-based deployments, listener configuration, and both local and remote build strategies. The CLI handles Docker image building and management, including support for self-hosted deployments via custom image URIs and base images, and integrates with the LangSmith host backend for cloud deployments. It also features robust dependency resolution using \uv\ for lock files and workspace management, and includes utilities for parsing Docker versions and handling ignore patterns for build contexts.

langgraph-cli · high confidence

Introduce PostgreSQL-based persistent store with vector search and TTL support

Adds a new \BasePostgresStore\ implementation for the \langgraph.store\ interface, enabling persistent storage of key-value items in PostgreSQL. This feature includes support for Time-To-Live (TTL) expiration on stored items, automatic database schema migrations, and vector search capabilities using HNSW or IVFFlat indexes via the \pgvector\ extension. Users can now leverage a production-grade, connection-pooled PostgreSQL backend for state management with built-in vector similarity search.

langgraph-checkpoint-postgres · high confidence

Introduce Postgres-backed key-value store with vector search and TTL support

Users can now persist and retrieve data using a new \AsyncPostgresStore\ (and \PostgresStore\) implementation that integrates with the LangGraph store interface. This addition enables semantic search via pgvector by configuring an embedding index, supports connection pooling for performance, and includes a configurable Time-To-Live (TTL) mechanism with a background sweeper to automatically expire items. The store is exported from \langgraph.store.postgres\, making it available for use in applications requiring durable, searchable state storage in PostgreSQL.

libs/checkpoint-postgres/langgraph/store · high confidence

Introduce SQLite-backed store with vector search and TTL support

Adds a new SQLite-based implementation of the LangGraph store interface, available as both synchronous (\SqliteStore\) and asynchronous (\AsyncSqliteStore\) classes. This feature enables persistent storage of key-value pairs with hierarchical namespace support, automatic database schema migrations, and time-to-live (TTL) expiration for stored items. It also includes optional vector search capabilities via \sqlite\_vec\, allowing users to store and retrieve data based on semantic similarity using embeddings. The implementation includes security hardening by validating filter keys to prevent SQL injection and scoping namespace matching to segment boundaries.

libs/checkpoint-sqlite/langgraph/store · high confidence

Introduce SQLite-based checkpoint saver with async support

Adds a new \langgraph.checkpoint.sqlite\ library providing \SqliteSaver\ for synchronous workflows and \AsyncSqliteSaver\ for asynchronous environments. The implementation uses a two-stage streaming approach for delta channel history to keep memory usage low, includes a threading lock for thread safety in the sync saver, and enforces that synchronous calls to the async saver are only made from background threads. It also introduces parameterized metadata filtering to prevent SQL injection and requires the \aiosqlite\ package for the async variant.

libs/checkpoint-sqlite/langgraph/checkpoint · high confidence

Introduce \`langgraph.prebuilt\` package with streaming tool-call support and deprecated legacy nodes

The \libs/prebuilt/langgraph\ location now exposes a new \langgraph.prebuilt\ package that consolidates high-level agent and tool utilities. This release adds streaming infrastructure for tool calls via \ToolCallTransformer\ and \ToolCallStream\, allowing users to observe \tool-started\, \tool-output-delta\, \tool-finished\, and \tool-error\ events in real-time through the \run.tool\_calls\ projection. The package also includes \ValidationNode\ for validating tool call arguments against Pydantic schemas, \ToolNode\ for executing tools, and \create\_react\_agent\ for building ReAct-style agents. Additionally, \HumanInterruptConfig\, \ActionRequest\, and \HumanInterrupt\ are marked as deprecated in favor of \langchain.agents.interrupt\, signaling a migration path for human-in-the-loop interrupt configurations.

libs/prebuilt/langgraph · high confidence

Introduce beta custom encryption at-rest API for LangGraph SDK

The LangGraph Python SDK now includes a beta module for custom at-rest encryption, allowing developers to define server-side encryption and decryption handlers for both opaque blobs (like checkpoints) and structured JSON data. This feature introduces \EncryptionContext\ to pass model and field metadata to handlers, and a new \DecryptResult\ type that enables key rotation by returning replacement ciphertext alongside decrypted plaintext. Users can register custom encrypt/decrypt logic via decorators, with the API currently marked as beta and subject to change.

_libs/sdk-py/langgraph\sdk/encryption · high confidence

Introduce checkpoint conformance testing framework

Added a new conformance testing suite for LangGraph checkpoint savers. The \langgraph-checkpoint-conformance\ library now includes capability detection logic to identify which methods (such as \put\, \get\_tuple\, \list\, and extended features like \delta\_channel\_history\) a checkpointer implements, a registration system for test factories with optional lifespans, and a reporting module that outputs detailed pass/fail results and a conformance level (BASE, BASE+PARTIAL, or FULL) for each implementation.

langgraph-checkpoint-conformance · high confidence

Introduce dedicated authentication and authorization SDK module

The \langgraph\_sdk.auth\ package is now available, providing a structured way to manage authentication and authorization within LangGraph applications. This includes the \Auth\ class for defining custom authentication handlers and fine-grained authorization rules via resource-specific decorators (e.g., \@auth.on.threads.create\), as well as \HTTPException\ for returning specific HTTP error responses. Users can now configure auth logic in a separate file and register it via the \langgraph.json\ configuration, enabling default-deny patterns and scoped access control for threads and store operations.

_libs/sdk-py/langgraph\sdk/auth · high confidence

Introduce v3 streaming infrastructure with native projections and transformer pipeline

LangGraph now includes a new streaming infrastructure in the \langgraph.stream\ module, enabling users to drive graph execution via \graph.stream\_events(version='v3')\ and \graph.astream\_events(version='v3')\. This change introduces a \StreamMux\ event dispatcher and a \StreamTransformer\ extension point, allowing the graph to project raw events into ergonomic, per-channel streams such as \run.values\, \run.messages\, \run.custom\, and \run.updates\. The system supports both synchronous and asynchronous pumping, where iterating over these projections drives the graph forward, and provides native access to lifecycle, subgraph status, and debug data through dedicated transformer classes.

libs/langgraph/langgraph/stream · high confidence

Introduce v3 streaming transports (SSE and WebSocket) for Python SDK

The Python SDK now includes a new v3 streaming transport layer in \langgraph\_sdk.stream.transport\ that supports both Server-Sent Events (SSE) and WebSocket protocols for thread-centric streaming. This adds \ProtocolSseTransport\ and \ProtocolWebSocketTransport\ (with synchronous counterparts) to handle event streams and command sending, enabling users to stream events with filtered subscriptions and reconnect capabilities via the \since\ parameter.

_libs/sdk-py/langgraph\sdk/stream/transport · high confidence

Introduces v3 streaming primitives with shared subscriptions and projection decoders

The Python SDK now includes a new \stream\ module that implements v3 streaming primitives, allowing multiple subscriptions to share a single SSE connection via a centralized \StreamController\. This change adds support for interleaved projections on channels such as \values\, \messages\, \tool\_calls\, and \subgraphs\ through new decoders, and introduces a \MultiCursorBuffer\ to ensure late consumers see all buffered events. Users benefit from more efficient resource usage and consistent event delivery across concurrent subscriptions.

_libs/sdk-py/langgraph\sdk/stream · high confidence

Introduces v3 thread-centric streaming with async and sync clients

The Python SDK now supports the v3 streaming protocol via new \AsyncThreadStream\ and \SyncThreadStream\ classes. These clients manage a shared Server-Sent Events (SSE) connection for a thread, allowing users to dispatch commands (like \run.start\ and \run.respond\) and subscribe to typed projections such as \thread.values\, \thread.messages\, \thread.tool\_calls\, and \thread.extensions\. The implementation includes robust lifecycle management, handling root-terminal events to properly close streams, and supports reconnection logic. This change is accompanied by new type definitions for authentication (\auth/types.py\), encryption (\encryption/types.py\), and server runtime context (\runtime.py\), enabling features like custom at-rest encryption and context-aware graph factories.

langgraph-sdk · high confidence

Introduction of a base cache interface with configurable serialization

A new abstract base class, BaseCache, has been introduced in the langgraph cache module to standardize caching implementations. This class defines the core contract for cache operations (get, set, clear) and includes support for both synchronous and asynchronous methods. A key behavioral aspect is the default serialization configuration, which now uses JsonPlusSerializer with pickle\_fallback disabled, ensuring stricter data handling by default while allowing users to provide custom serializers via the constructor.

libs/checkpoint/langgraph/cache/base · high confidence

Introduction of base checkpoint and persistent store interfaces

This change introduces the foundational base classes and type definitions for the LangGraph checkpoint and persistent store systems. It defines the \Checkpoint\ and \CheckpointMetadata\ structures used to snapshot graph state, including support for delta channels and version tracking. Additionally, it establishes the \BaseStore\ interface and \Item\ types for hierarchical key-value storage with optional vector search capabilities, providing the core abstractions for long-term memory and state persistence across threads.

langgraph-checkpoint · high confidence

LangGraph v1: New functional API, graph lifecycle callbacks, and node-level error handling

LangGraph introduces a new functional API (\langgraph.func\) with \@task\ and \@entrypoint\ decorators for defining graph logic, alongside a new \langgraph.callbacks\ module that exposes graph lifecycle events (interrupts and resumes) via \GraphCallbackHandler\. The library also adds node-level error handling through \NodeError\ and \error\_handler\ parameters in \StateGraph\, and introduces a \PregelScratchpad\ for internal execution state management.

langgraph · high confidence

New CLI examples demonstrating graph execution with context and external dependencies

Added two new CLI example projects, \graphs\_reqs\_a\ and \graphs\_reqs\_b\, to showcase LangGraph capabilities. \graphs\_reqs\_a\ implements a tool-calling agent graph that dynamically selects between Anthropic and OpenAI models based on a runtime context schema, while \graphs\_reqs\_b\ extends this pattern by importing and executing an external utility function (\greet\) from a local package, demonstrating how to structure multi-module dependencies within a LangGraph CLI project.

_libs/cli/examples/graphs\_reqs\_a, libs/cli/examples/graphs\_reqs\b · high confidence

New LangGraph.js project template added to CLI examples

The CLI examples directory now includes a complete starter template for LangGraph.js applications. This addition provides a pre-configured project structure featuring a basic chatbot agent with persistent memory, complete with TypeScript configuration, ESLint and Prettier settings, Jest testing infrastructure, and a LangGraph Studio configuration file. Users can now use this template as a foundation to quickly scaffold and customize their own conversational agents.

libs/cli/js-examples · high confidence

New asynchronous batched store and embedding utilities

The store module now includes an \AsyncBatchedBaseStore\ that queues operations (get, put, search, delete, list namespaces) into a background task to improve efficiency and prevent deadlocks when called from the main event loop. Additionally, a new \embed.py\ module provides utilities to wrap arbitrary synchronous or asynchronous embedding functions into LangChain's \Embeddings\ interface, enabling custom embedding logic with both sync and async support.

libs/checkpoint/langgraph/store/base · high confidence

New checkpoint serialization library with strict security controls

The checkpoint serialization logic has been moved to a new dedicated library (libs/checkpoint/langgraph/checkpoint/serde) that introduces a secure-by-default deserialization model. By setting the environment variable LANGGRAPH\_STRICT\_MSGPACK=true, users can restrict checkpoint loading to a specific allowlist of safe types (such as standard Python types, LangChain messages, and LangGraph control objects), preventing arbitrary code execution during deserialization. The library also adds support for optional AES encryption of checkpoint payloads via the EncryptedSerializer and provides a typed protocol for custom serialization implementations.

libs/checkpoint/langgraph/checkpoint/serde · high confidence

New conformance test suite for LangGraph checkpointer implementations

A new \langgraph-checkpoint-conformance\ package has been added to provide a standardized validation framework for checkpointer implementations. This suite automatically detects which capabilities a checkpointer supports (such as PUT, GET\_TUPLE, LIST, DELETE\_THREAD, and extended features like PRUNE or DELTA\_CHANNEL\_HISTORY) and runs a corresponding test suite to verify correctness. It produces a structured report indicating the conformance level (BASE, BASE+PARTIAL, or FULL) and offers configurable progress reporting, allowing developers to ensure their checkpointer implementations adhere to the expected interface and behavior.

libs/checkpoint-conformance/langgraph/checkpoint/conformance · high confidence

New simple and monorepo UV example projects

Added two new example projects in the CLI examples directory to demonstrate LangGraph integration with the UV package manager. The 'simple' example provides a minimal single-agent graph setup with a \langgraph.json\ configuration and a \.env.example\ template, while the 'monorepo' example demonstrates a multi-package workspace structure containing 'agent', 'shared', and 'uv-monorepo-example' members, complete with generated \uv.lock\ files for dependency resolution.

libs/cli/uv-examples · high confidence

Python SDK restructured with new caching, encryption, and SSE capabilities

The Python SDK has been reorganized into a modular package structure, introducing a server-side key/value cache with stale-while-revalidate semantics, an encryption module for handling decryption results and contexts, and a robust Server-Sent Events (SSE) parser that strictly adheres to the spec for line splitting and flushing. The public API now exposes \get\_client\ and \get\_sync\_client\ factory functions alongside dedicated client classes for Assistants, Cron jobs, Runs, Threads, and the persistent Store, while also adding comprehensive error types for better API error handling.

_libs/sdk-py/langgraph\sdk · high confidence

Removals

Removal of PubSub and Topic infrastructure

The \permchain\ module has removed the entire publish-subscribe messaging system, including the \PubSub\ runnable, \Topic\ definitions, and the underlying \PubSubConnection\ abstractions. Users can no longer define or subscribe to named topics (such as \INPUT\_TOPIC\ or \OUTPUT\_TOPIC\) or use \RunnableSubscriber\ and \RunnablePublisher\ components within this package.

permchain · high confidence

Architecture

Introduction of internal module for core runtime infrastructure

LangGraph introduces a new \\_internal\ package to centralize private runtime utilities, separating implementation details from the public API. This module provides foundational components including configuration merging and patching (\\_config\), serialization and schema handling (\\_serde\, \\_pydantic\, \\_fields\), task and future management (\\_future\, \\_queue\), and constants for checkpointing and state management (\\_constants\). It also includes support for replay logic (\\_replay\), retry policies (\\_retry\), and timeout handling (\\_timeout\), establishing the internal backbone for graph execution, state persistence, and error recovery.

_libs/langgraph/langgraph/\internal · high confidence

LangGraph Pregel engine restructured into modular internal components

The LangGraph Pregel execution engine has been refactored from a single monolithic module into a set of specialized internal files (including \_algo.py, \_checkpoint.py, \_loop.py, \_executor.py, and \_io.py). This restructuring separates the core execution loop, checkpoint management, task scheduling algorithms, and I/O mapping into distinct modules while maintaining the same public API surface (Pregel, NodeBuilder). For users, this change is primarily an internal architectural improvement that enhances code maintainability and modularity without altering the external behavior of graph execution, streaming, or checkpointing.

libs/langgraph/langgraph/pregel · high confidence

Behavioural changes

2 commits (0 fixes) modifying libs/sdk-py/langgraph\_sdk/priority

A change to existing behaviour in libs/sdk-py/langgraph\_sdk/priority — 2 commits, 2 files: “feat(sdk-py): remove fairness\_weight from PrioritySettings (\#9441)”; “feat(sdk-py): add Priority for thread priority settings (\#9392)” (refs \#9441, \#9392).

_libs/sdk-py/langgraph\sdk/priority · medium confidence · unverified

30 commits (12 fixes) modifying libs/sdk-py/langgraph\_sdk/\_sync

A change to existing behaviour in libs/sdk-py/langgraph\_sdk/\_sync — 30 commits (12 fixs), 8 files: “chore: state\_updated\_at sort by (\#6857)”; “fix(sdk-py): reset the reconnect cursor on every empty id (\#9440)”; “fix(sdk-py): allow reset of config/context in assistants update (\#6862)”; and 27 more (refs \#6857, \#9440, \#6862, \#9588, \#9599, …).

_libs/sdk-py/langgraph\_sdk/\sync · medium confidence · unverified

33 commits (12 fixes) modifying libs/sdk-py/langgraph\_sdk/\_async

A change to existing behaviour in libs/sdk-py/langgraph\_sdk/\_async — 33 commits (12 fixs), 11 files: “chore: state\_updated\_at sort by (\#6857)”; “fix(sdk-py): reset the reconnect cursor on every empty id (\#9440)”; “fix(sdk-py): allow reset of config/context in assistants update (\#6862)”; and 30 more (refs \#6857, \#9440, \#6862, \#7821, \#7819, …).

_libs/sdk-py/langgraph\_sdk/\async · medium confidence · unverified

Archival notice added to information-gather-prompting example

The information-gather-prompting notebook in the examples/chatbots directory has been replaced with a placeholder file. This file informs users that the example has been moved to the consolidated LangChain documentation and that the examples directory is retained purely for archival purposes and is no longer updated.

examples/chatbots · high confidence

Archival notice for self-discover example

The self-discover example notebook in the examples directory has been replaced with a placeholder file. This file contains a link to the new location of the tutorial in the consolidated LangChain documentation and informs users that the examples directory is retained for archival purposes only and is no longer updated.

examples/self-discover · high confidence

Chatbot simulation evaluation examples moved to documentation

The \examples/chatbot-simulation-evaluation\ directory has been deprecated and replaced with archival placeholder notebooks that redirect users to the new consolidated LangChain documentation. The underlying \simulation\_utils.py\ module, which provides the \create\_chat\_simulator\ function and \SimulationState\ for evaluating chatbots via simulated user interactions, remains available for reference but is no longer actively maintained in this location.

examples/chatbot-simulation-evaluation · high confidence

Chatbot simulation evaluation examples moved to documentation

The \examples/chatbot-simulation-evaluation\ directory has been replaced with placeholder notebooks that direct users to the new location in the LangChain documentation. The underlying \simulation\_utils.py\ code, which provides utilities for creating simulated users and chat simulators using LangGraph's \StateGraph\, has been migrated to the official tutorials section. Users should now access these examples and the associated simulation logic via the consolidated LangChain documentation rather than the examples folder.

_examples/code\assistant · high confidence

Deprecation of legacy utils module in preparation for v1

The \libs/langgraph/langgraph/utils\ package has been introduced as a compatibility layer to support existing imports from the legacy utilities module, which is scheduled for removal in version 1. This change adds backward-compatible re-exports for configuration utilities (\ensure\_config\, \patch\_configurable\, \get\_config\, \get\_store\) and runnable utilities (\RunnableCallable\, \RunnableLike\) from their new internal locations (\langgraph.\_internal.\_config\, \langgraph.config\, and \langgraph.\_internal.\_runnable\). Users relying on these legacy import paths will continue to function, but should be aware that this module is deprecated and will be removed in the next major release.

libs/langgraph/langgraph/utils · high confidence

Examples directory archived and notebooks replaced with redirects

The \examples/\ directory is now retained purely for archival purposes and is no longer updated with new content. All example notebooks (such as \react-agent-from-scratch\, \subgraph\, and \tool-calling\) have been replaced with placeholder files that redirect users to the consolidated LangChain documentation. Additionally, the \runnable-pubsub.py\ example has been removed entirely. Users should refer to the LangGraph documentation for current examples and guides.

examples · high confidence

Examples directory marked as archived

The \examples/extraction\ directory has been converted into an archival placeholder. The original content has been removed and replaced with a notice indicating that examples are no longer maintained in this location and have been moved to the consolidated LangChain documentation site.

examples/extraction · high confidence

InMemorySaver now supports DeltaChannelHistory for efficient incremental state retrieval

The InMemorySaver checkpointer has been updated to implement the \get\_delta\_channel\_history\ method, allowing users to retrieve incremental channel changes by walking the checkpoint parent chain once. This change optimizes performance for scenarios requiring historical channel state reconstruction, particularly in subgraph or nested execution contexts, by collecting writes from ancestor checkpoints up to a specific seed value rather than reloading full checkpoint states.

libs/checkpoint/langgraph/checkpoint/memory · high confidence

Introduce PostgresSaver and AsyncPostgresSaver with migration tracking and shallow checkpointer deprecation

The \langgraph-checkpoint-postgres\ library now provides \PostgresSaver\ and \AsyncPostgresSaver\ classes that support automatic database schema migrations via a \setup()\ method and a \checkpoint\_migrations\ tracking table. These savers introduce a two-stage delta channel history reconstruction for improved performance and reduced wire payload. Additionally, the \ShallowPostgresSaver\ is now deprecated in favor of the standard saver with \durability='exit'\.

libs/checkpoint-postgres/langgraph/checkpoint · high confidence

Introduce new channel types and refine checkpointing behavior

The \libs/langgraph/langgraph/channels\ module now includes new channel implementations: \AnyValue\ (stores the last value, assuming equality if multiple are received), \EphemeralValue\ (stores a value for the preceding step and clears it), \UntrackedValue\ (stores the last value but never checkpoints it), and \LastValueAfterFinish\ (makes the stored value available only after the graph run finishes). Additionally, \BinaryOperatorAggregate\ and \DeltaChannel\ have been updated to support the \Overwrite\ mechanism, allowing a value to bypass the reducer and reset the channel state, with \BinaryOperatorAggregate\ specifically handling JSON roundtrips of this sentinel. \DeltaChannel\ also enforces a delta snapshot cadence based on superstep counts to bound replay depth.

libs/langgraph/langgraph/channels · high confidence

Introduce standalone langgraph-prebuilt package with ToolNode and create\_react\_agent

The \langgraph-prebuilt\ module is now a standalone package containing the \ToolNode\ for executing tools (with support for parallel calls, state/store injection, and \Command\-based control flow) and the \create\_react\_agent\ factory for building ReAct-style agents. This release deprecates the legacy \AgentState\ and \AgentStatePydantic\ classes in favor of \langchain.agents.AgentState\, removes the \state\_modifier\ argument from \create\_react\_agent\, and introduces a \post\_model\_hook\ that runs after the LLM call to allow state and store injection into tool calls. Users should update imports to use \langgraph.prebuilt.ToolNode\ and \langgraph.prebuilt.create\_react\_agent\, and migrate any custom state schemas to the new \langchain.agents.AgentState\.

langgraph-prebuilt · high confidence

LATS example notebook archived and redirected

The LATS example notebook in the examples directory has been replaced with a placeholder that redirects users to the consolidated LangChain documentation. This change indicates that the example is no longer actively maintained in this location and users should refer to the new documentation site for the latest information.

examples/lats · high confidence

Multi-agent example notebooks moved to documentation

The \hierarchical\_agent\_teams\ and \multi-agent-collaboration\ notebooks in the \examples/multi\_agent\ directory have been replaced with placeholder files. These files now contain links directing users to the consolidated LangChain documentation, indicating that the examples have been migrated out of the examples folder and are no longer maintained in this location.

_examples/multi\agent · high confidence

New graph module with message merging, UI push/delete, and deprecated MessageGraph

The \langgraph.graph\ package is introduced, exposing \StateGraph\, \add\_messages\, \MessagesState\, and the deprecated \MessageGraph\. The \add\_messages\ reducer now supports an optional \format\ argument (e.g., \langchain-openai\) to return messages in OpenAI-compatible structure, and the module exports \REMOVE\_ALL\_MESSAGES\ to support deleting messages. A new UI subsystem is added via \push\_ui\_message\ and \delete\_ui\_message\, allowing nodes to push UI component updates and remove them by ID; \push\_ui\_message\ includes a \merge\ flag to merge props with existing UI messages rather than replacing them. These changes are localized to the graph package’s public API and reducers.

libs/langgraph/langgraph/graph · high confidence

New runtime context API and deprecation warnings for LangGraph v1.0+

This change introduces a new public API for accessing runtime context within graph nodes and entrypoint tasks, specifically adding \get\_store()\ and \get\_stream\_writer()\ functions in \langgraph.config\ to replace the previous reliance on \config\['configurable'\]\. It also establishes a formal deprecation framework via \langgraph.warnings\, introducing \LangGraphDeprecatedSinceV10\ and \LangGraphDeprecatedSinceV11\ warning classes to signal that certain imports (such as \Send\ and \Interrupt\ from \langgraph.constants\) are deprecated and should be migrated to \langgraph.types\. Additionally, the package now includes \py.typed\ for proper type checking support and exposes internal type variables in \langgraph.typing\.

libs/langgraph/langgraph · high confidence

ReWOO example notebook archived and moved to documentation

The ReWOO example notebook located in the examples directory has been replaced with a placeholder indicating that the content has been moved to the consolidated LangChain documentation. This directory is now retained purely for archival purposes and is no longer updated, directing users to the new official documentation site for the latest version of the example.

examples/rewoo · high confidence

Refactor managed values into static classes and simplify IsLastStep/RemainingSteps

The managed value system in LangGraph has been refactored: \ManagedValue\ is now a static abstract base class with a \get\ method, and the previous \ChannelsManager\/\ManagedValues\ runtime instantiation is removed. \IsLastStep\ and \RemainingSteps\ are now defined as annotated types backed by dedicated manager classes (\IsLastStepManager\, \RemainingStepsManager\) that read step/stop from the scratchpad, and the public API in \langgraph.managed\ re-exports only these two types. This changes how these managed values are resolved internally and may affect code that relied on the previous runtime substitution or manager instantiation patterns.

libs/langgraph/langgraph/managed · medium confidence

Reflexion example moved to documentation

The reflexion example notebook has been relocated from the examples directory to the official LangChain documentation site. The file in the examples directory is now a placeholder containing a link to the new location and a notice that the directory is retained for archival purposes only, meaning users should refer to the consolidated LangChain documentation for the most up-to-date tutorial.

(repo-wide) · high confidence

SQL agent tutorial moved to documentation site

The SQL agent tutorial notebook in the examples directory has been replaced with a placeholder indicating that the content has been moved to the official LangChain documentation site. Users should now refer to the consolidated LangChain documentation for the latest SQL agent tutorial, as this directory is retained only for archival purposes and is no longer updated.

examples/tutorials · high confidence

SQLite-backed cache implementation with namespace-aware clearing

The SQLite cache implementation now supports clearing cached values for specific namespaces or all values at once. When the clear method is called without arguments, it deletes all entries in the cache; otherwise, it removes only the entries belonging to the specified namespaces. This change improves cache management flexibility by allowing targeted invalidation.

libs/checkpoint-sqlite/langgraph/cache · high confidence

TNT-LLM tutorial moved to documentation site

The TNT-LLM tutorial notebook has been relocated from the examples directory to the main documentation site. The file in this location is now a placeholder containing a link to the new location and an archival notice, indicating that the examples directory is no longer actively updated.

examples/tutorials/tnt-llm · high confidence

USACO example notebook archived and relocated

The USACO example notebook has been moved from the examples directory to the official LangChain documentation site. The file in this location now serves as an archival placeholder, containing links to the new documentation and a notice that the directory is no longer actively maintained.

examples/usaco · high confidence

Web Voyager example moved to documentation with archival notice

The \web\_voyager.ipynb\ file in the \examples/web-navigation\ directory has been replaced with a static notice indicating that the example has been moved to the consolidated LangChain documentation. The original example content is no longer present in this location, which is now retained purely for archival purposes, and users are directed to the new documentation site for the latest version of the tutorial.

examples/web-navigation · high confidence

Fixes

Add prerelease requirements failure example

Added a new CLI example demonstrating a failure scenario with prerelease requirements. The example includes a LangGraph agent workflow using OpenAI and Tavily Search, along with its configuration file, to illustrate how the CLI handles dependency resolution issues in prerelease contexts.

_libs/cli/examples/graph\_prerelease\_reqs\fail · medium confidence

Test coverage

Add comprehensive test infrastructure and fixtures for LangGraph; Add comprehensive test suite for langgraph-prebuilt; Added comprehensive test suite for Postgres checkpoint and store implementations; Added comprehensive test suite for checkpoint, store, and cache components; Added conformance test suite for checkpoint saver capabilities; Added conformance tests for InMemorySaver; Added example app for testing graph configuration; Added snapshot tests for LangGraph state schemas and graph structures; Added test suite for Python SDK streaming capabilities; Added test suite for SQLite checkpoint and store implementations; Comprehensive test suite for Python SDK clients and utilities; Initial test suite for the LangGraph CLI; New integration test environment for v3 streaming protocol; New integration test suite for the Python SDK.

Dependencies

Release checkpoint libraries v3/v4 and add conformance test suite

This update releases the core checkpoint libraries with significant version bumps: \langgraph-checkpoint\ is released as version 4.2.0, \langgraph-checkpoint-postgres\ as 3.1.2, and \langgraph-checkpoint-sqlite\ as 3.1.1. The core checkpoint library now requires \langchain-core\>=0.2.38\ and \ormsgpack\>=1.12.0\, while the Postgres and SQLite implementations depend on \langgraph-checkpoint\>=4.1.0,\<5.0.0\. Additionally, a new \langgraph-checkpoint-conformance\ package (v0.0.2) has been added to provide a shared test suite for validating checkpointer implementations, which is now included as a test dependency for the Postgres and SQLite libraries.

(dependencies) · high confidence

Housekeeping

Archival notice added to adaptive RAG notebook; Archival notice added to human-in-the-loop example; Archival notice for plan-and-execute example.

Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

How this codebase got here

Score

  • CAI 59 → 59 (+0.4)
  • Rubric changed (rubric-2026.10.5 → rubric-2026.11.4) — scores are not directly comparable.

Lenses

  • Code Health 68 → 59 (-8.8)
  • Architecture 92 → 93 (+1.0)
  • Maturity 54 → 57 (+3.3)
  • Readiness 52 → 53 (+1.1)
  • Security 71 → 75 (+3.6)
  • Performance 89 → 89 (+0.0)

Resolved (38)

  • Change-coupling hub: init.py → base.py, last_value.py, constants.py, base.py, _write.py, protocol.py, types.py (libs/langgraph/langgraph/pregel/init.py)
  • Duplicated block (10 lines × 2) (libs/langgraph/langgraph/_internal/_runnable.py)
  • Duplicated block (10–12 lines × 4) (libs/langgraph/bench/pydantic_state.py)
  • Duplicated block (11 lines × 2) (libs/langgraph/langgraph/_internal/_runnable.py)
  • Duplicated block (11 lines × 2) (libs/langgraph/langgraph/_internal/_runnable.py)
  • Duplicated block (15–16 lines × 2) (libs/langgraph/langgraph/_internal/_runnable.py)
  • Duplicated block (20–21 lines × 2) (libs/langgraph/langgraph/pregel/main.py)
  • Duplicated block (21 lines × 2) (libs/sdk-py/langgraph_sdk/_async/runs.py)
  • Duplicated block (27–29 lines × 2) (libs/sdk-py/langgraph_sdk/_async/http.py)
  • Duplicated block (28–29 lines × 2) (libs/sdk-py/langgraph_sdk/_async/http.py)
  • Duplicated block (40–54 lines × 2) (libs/sdk-py/langgraph_sdk/_async/threads.py)
  • Duplicated block (41–51 lines × 2) (libs/sdk-py/langgraph_sdk/_sync/threads.py)
  • Duplicated block (6 lines × 2) (libs/sdk-py/langgraph_sdk/_async/stream.py)
  • Duplicated block (67–68 lines × 2) (libs/langgraph/langgraph/pregel/remote.py)
  • Duplicated block (9 lines × 2) (libs/sdk-py/langgraph_sdk/_async/threads.py)
  • Duplicated block (9 lines × 3) (libs/cli/langgraph_cli/deploy.py)
  • Edited copy of a member (30 corresponding lines) (libs/checkpoint-postgres/langgraph/checkpoint/postgres/shallow.py)
  • High CVE: [GHSA redacted] (libs/cli/uv.lock)
  • High CVE: [GHSA redacted] (libs/cli/js-examples/yarn.lock)
  • High CVE: [GHSA redacted] (libs/langgraph/uv.lock)
  • …and 18 more

New (202)

  • Change-coupling hub: init.py → base.py, last_value.py, constants.py, base.py, _write.py, types.py (libs/langgraph/langgraph/pregel/init.py)
  • Duplicated block (10 lines × 2) (libs/sdk-py/langgraph_sdk/_async/threads.py)
  • Duplicated block (11 lines × 2) (libs/sdk-py/langgraph_sdk/_async/threads.py)
  • Duplicated block (15 lines × 2) (libs/sdk-py/langgraph_sdk/_async/http.py)
  • Duplicated block (17 lines × 2) (libs/sdk-py/langgraph_sdk/_async/runs.py)
  • Duplicated block (18 lines × 2) (libs/langgraph/langgraph/pregel/main.py)
  • Duplicated block (36–38 lines × 2) (libs/sdk-py/langgraph_sdk/_async/http.py)
  • Duplicated block (47–48 lines × 2) (libs/sdk-py/langgraph_sdk/_async/http.py)
  • Duplicated block (59 lines × 3) (libs/langgraph/bench/pydantic_state.py)
  • Duplicated block (7 lines × 2) (libs/langgraph/langgraph/pregel/_retry.py)
  • Duplicated block (72–73 lines × 2) (libs/langgraph/langgraph/pregel/remote.py)
  • Edited copies of one member (3 members, 14+ corresponding lines) (libs/checkpoint-postgres/langgraph/store/postgres/base.py)
  • Edited copies of one member (3 members, 22+ corresponding lines) (libs/cli/langgraph_cli/host_backend.py)
  • Edited copies of one member (3 members, 4+ corresponding lines) (libs/checkpoint-postgres/langgraph/store/postgres/aio.py)
  • Edited copies of one member (3 members, 4+ corresponding lines) (libs/sdk-py/langgraph_sdk/_async/stream.py)
  • Edited copies of one member (3 members, 7+ corresponding lines) (libs/sdk-py/langgraph_sdk/_async/stream.py)
  • Edited copies of one member (4 members, 11+ corresponding lines) (libs/sdk-py/langgraph_sdk/_async/http.py)
  • Edited copies of one member (4 members, 11+ corresponding lines) (libs/sdk-py/langgraph_sdk/stream/transport/http.py)
  • Edited copies of one member (4 members, 25+ corresponding lines) (libs/langgraph/langgraph/pregel/remote.py)
  • Edited copies of one member (4 members, 33+ corresponding lines) (libs/sdk-py/langgraph_sdk/_async/assistants.py)
  • …and 182 more

Changes since last survey

  • 100 commits — 74 feature/other, 26 fixes

By area

  • libs/langgraph — 33 commits
  • libs/cli — 25 commits
  • libs/sdk-py — 23 commits
  • libs/checkpoint — 6 commits
  • libs/checkpoint-postgres — 4 commits
  • libs/prebuilt — 3 commits
  • .github/workflows — 2 commits
  • libs/checkpoint-sqlite — 2 commits
  • (root) — 1 commit
  • libs/checkpoint-conformance — 1 commit

Notable commits

  • fix: chore(deps): bump filelock and langgraph-api for security fixes (#9606)
  • fix: fix(cli): remove discontinued local debugger image (#8543)
  • fix: fix(cli): remove outdated deploy private-beta notice (#9506)
  • fix: fix(langgraph): don't report a paused tool as failed on the tools stream (#9406)
  • fix: fix(langgraph): emit node-output messages from a graph streamed inside a node (#9463)
  • fix: fix(langgraph): give messages and tools events the namespace of their graph (#9458)
  • fix: fix(langgraph): keep trace_policy from rewriting streamed node payloads (#9486)
  • fix: fix(langgraph): let error_handler recover on every path and stream failed task results (#9408)
  • fix: fix(langgraph): match whole namespace segments in get_subgraphs (#9615)
  • fix: fix(langgraph): point the multiple-interrupts error at the current docs (#9590)
  • fix: fix(langgraph): read an undeclared subgraph namespace with the parent graph (#9614)
  • fix: fix(langgraph): respect subgraphs=False in RemoteGraph.stream under a streaming parent (#9453)
  • fix: fix(langgraph): return an awaited @task's value while streaming (#9407)
  • fix: fix(langgraph): stop duplicating tags at every subgraph level (#9400)
  • fix: fix(langgraph): stream a child graph on its own thread to a caller streaming subgraphs (#9698)
  • fix: fix(langgraph): stream the last checkpoint of a run stopped by interrupt_after or the recursion limit (#9409)
  • fix: fix(sdk-py): accept durability, stream_resumable and context in the runs overloads (#9403)
  • fix: fix(sdk-py): follow the SSE spec for multi-line data, empty ids and a leading BOM (#9402)
  • fix: fix(sdk-py): match Auth.on overload to optional resources (#9450)
  • fix: fix(sdk-py): preserve SSE data and cursor state across chunks (#9477)
  • …and 80 more

Architecture

  • Unchanged — 0 containers · 7 contexts · 0 edges

Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

Survey your own repository

langchain-ai/langgraph was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.

About this page

  • The score is its most recent published measurement, taken on 14 November 2026 at a pinned commit. It is not a live figure and does not change until the project is measured again.
  • Measured at commit 08a2016953789a4f579b4d36bd1967941ec62012 — the exact code this score is about.
  • Scored under rubric-2026.11.4 — the same rubric and the same method as every other entry in this index.
  • Measured by Canine Code Analyzer (cca.canine.dev) using cca measure-2026.11.65+preprod-36d4cd83012f.