LangGraph
AI & LLMsBuild resilient language agents as graphs.
Release History
View all versions →sdk==0.4.41 featureThis release introduces the ability to route LangSmith traces from thread streams. It also includes general SDK updates.
sdk==0.4.32 fixes2 featuresThis release includes a new feature for decrypting replacement results in sdk-py and several dependency updates. It also addresses a bug in sdk-py related to clearing cron end times.
1.2.111 fix1 featureThis release introduces a new feature to expose `trace_policy` on `add_node` in langgraph and fixes a bug in checkpoint regarding delta channel history.
checkpointpostgres==3.1.21 fixThis release includes a bug fix for checkpoint-postgres related to finding plain-value seeds and updates dependencies. It also includes linting rule enforcements and conformance suite runs for checkpoint-postgres and checkpoint-sqlite.
checkpoint==4.2.01 fix1 featureThis release introduces an opt-in feature to skip expired rows on read for checkpoint and checkpoint-postgres, and fixes an issue with collecting writes in delta channel history.
checkpointsqlite==3.1.11 fixThis release addresses a bug in checkpoint-postgres and checkpoint-sqlite by scoping namespace matching to segment boundaries. It also includes several dependency updates.
checkpointpostgres==3.1.11 fix1 featureThis release includes a bug fix for namespace matching and adds an option to omit expired rows on read. Dependency updates for langsmith and idna have also been performed.
1.2.103 featuresThis release introduces type hinting for v3 stream_events and native projections in langgraph, along with exposing `trace_policy` on `add_node`. The TracePolicy class has been removed.
cli==0.4.311 featureThis release introduces the ability to use prebuilt images for langgraph deployments and updates various dependencies to their latest minor and patch versions.
1.2.91 fixRelease 1.2.9 includes a bug fix for the updateState function related to metadata and counters for the delta channel.
1.2.81 fixThis release addresses a specific bug in the delta channel related to updateState on fresh threads. It also includes dependency updates for langgraph and the Python SDK.
1.2.73 fixesThis release addresses several bugs in langgraph, including issues with snapshotting DeltaChannels and JSON roundtrips. It also ensures valid UUIDs are emitted for exit-mode delta task_ids.
1.2.62 fixesThis release addresses critical bugs in langgraph related to subgraph checkpointing and stream aborts. It also includes dependency updates and documentation standardization.
cli==0.4.301 featureThis release introduces support for compatible API version ranges in the CLI. It also standardizes the README.md structure across packages.
1.2.51 fixThis release includes a bug fix for the updateState function in langgraph related to empty threads. It also includes dependency updates and a migration of Python type checking to ty.
cli==0.4.291 featureThis release adds support for running the dev server under HTTPS by allowing the passing of certificate files. The change affects the cli module.
cli==0.4.281 featureThis release includes dependency updates and introduces tracking for ADK/other library usage during CLI deployments. It also migrates Python type checking to ty.
1.2.41 fixThis release includes a bug fix for langgraph's _on_started method to maintain backward compatibility. It also includes SDK integration tests for the server factory path.
1.2.34 fixes6 featuresThis release introduces v3 streaming support for RemoteGraph and adds various new features to sdk-py, including websocket stream transports and message/tool call projections. Several bug fixes improve configuration handling and cancellation distinctions.
sdk==0.4.21 fixThis release fixes a bug related to percent-encoding the thread_id in v3 stream transport default paths.
sdk==0.4.11 fix2 featuresThis release introduces new streaming capabilities for RemoteGraph and improves the statelessness of the `tools_agent`. It also includes internal refactoring for stream decoders.
cli==0.4.272 fixesThis release of the CLI (version 0.4.27) includes bug fixes related to pinning internal Docker deploy images and bumping the API bound. It also contains several dependency updates.
sdk==0.4.015 featuresThis release introduces a significant number of new features related to streaming, including thread stream helpers, websocket stream transports, and v3 streaming primitives. It also enhances reconnect logic and adds support for sync and async operations.
1.2.21 fixThis release includes a bug fix for assigning stable IDs to BaseMessages before checkpoint writes in Langgraph. It also bumps the version of Langgraph and the checkpoint library.
checkpoint==4.1.11 fixThis release fixes a bug related to lc:2 envelope revival and updates dependencies for idna and langsmith.
Common Errors
ModuleNotFoundError7 reportsThe "ModuleNotFoundError" in LangGraph usually indicates that required dependencies or LangGraph submodules are missing or not correctly installed. To fix this, ensure you've installed LangGraph and its dependencies using `pip install langgraph` (or `pip install "langgraph[all]"` for optional dependencies); try upgrading LangGraph to the latest version (`pip install --upgrade langgraph`) to resolve potential version-related issues. If the problem persists, double-check your Python environment and virtual environment activation.
BadRequestError6 reportsBadRequestError in langgraph usually arises from malformed requests to an external service, often an LLM, due to incorrect parameters or data. To fix it, carefully inspect the LLM's API call for configuration errors like conflicting parameters (e.g., both `max_tokens` and `max_completion_tokens`), invalid data types, or exceeding rate limits; correct any discrepancies or adjust input data to match the API's expected format. Ensure also that your loop termination condition is correctly defined in the graph.
UnicodeDecodeError4 reportsThis error typically occurs in langgraph. Check the example issues for common solutions.
TypeError4 reportsThis TypeError usually arises when your LangGraph configuration, especially within the node context or checkpointing mechanism, attempts to serialize Python objects that aren't natively JSON serializable (e.g., custom classes, database connections, or complex objects). To fix it, either convert these problematic objects into JSON-serializable formats (like strings, dictionaries, or lists) before they enter the context or checkpoint storage, or implement a custom serialization/deserialization strategy for these object types if they must be persisted. Consider using libraries like `jsonpickle` if you have complex object graphs.
ImportError3 reportsNotImplementedError2 reportsThe "NotImplementedError" in LangGraph commonly arises when a required method or function within a custom class or component (like a custom Tool or Agent) is not defined. To fix this, identify the missing method (usually indicated in the error traceback) and implement its functionality within your custom class. Ensure your custom components align with the expected interface for proper execution within the LangGraph framework.
Related AI & LLMs Packages
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.
🦜🔗 The platform for reliable agents.
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
LLM inference in C/C++
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
Subscribe to Updates
Get notified when new versions are released