langgraph-events
Opinionated event-driven abstraction for LangGraph. State IS events.
Quick Start
Group related commands and events into a Namespace; colocate the handler on the command.
from langgraph_events import Command, DomainEvent, EventGraph, Namespace
class Order(Namespace):
class Place(Command):
customer_id: str
class Placed(DomainEvent):
order_id: str
def handle(self) -> Order.Place.Placed:
return Order.Place.Placed(order_id=f"o-{self.customer_id}")
graph = EventGraph([Order.Place])
log = graph.invoke(Order.Place(customer_id="alice"))
print(log.latest(Order.Place.Placed))
@on(...) handlers add invariants, declared exceptions, and cross-namespace reactions. See Concepts and Control Flow.
Installation
pip install langgraph-events
# With AG-UI adapter support
pip install "langgraph-events[agui]"
# From source (development)
pip install git+https://github.com/cadance-io/langgraph-events.git
Documentation
- Docs site (GitHub Pages): https://cadance-io.github.io/langgraph-events/
- Local docs index:
docs/index.md - Getting started:
docs/getting-started.md - Core concepts:
docs/concepts.md - Patterns:
docs/patterns.md - Reflection (agent-queryable event log):
docs/reflection.md - API reference:
docs/api.md - AG-UI adapter:
docs/agui.md - Checkpointer and graph evolution:
docs/checkpointer-evolution.md
Development
uv sync --group dev
uv run pytest tests/
uv run ruff check src/ tests/
uv run mypy src/
License
MIT - see LICENSE.
1 maintainer
Metadata
1 maintainer
Release files for langgraph-events 0.38.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| langgraph_events-0.38.0.tar.gz | 728.6 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| langgraph_events-0.38.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 949.0 kB
Release files / langgraph_events-0.38.0.tar.gz
| Download URL | langgraph_events-0.38.0.tar.gz |
|---|---|
| Size | 728.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
03405c882ed07db8affa1ed42a75bbb059cff2230b399b48ac9021e78e23897c
|
|
BLAKE2b-256 checksum How to use checksums |
ad92ea84cb0a0c7654cc42432ace0cb7b98a0c1466c82c859a2e11fd2de7876a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.13.4 {"installer":{"name":"uv","version":"0.13.4","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / langgraph_events-0.38.0-py3-none-any.whl
| Download URL | langgraph_events-0.38.0-py3-none-any.whl |
|---|---|
| Size | 220.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
d2d1e52f99c463e7abb0d28ec8cab2d8e9fe28826a6c1210605d9dc8ce8482a1
|
|
BLAKE2b-256 checksum How to use checksums |
c002118c06653c529c5ce1e5f50992cce3de5c423b882b3e84a3d1bf8d5de0d3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.13.4 {"installer":{"name":"uv","version":"0.13.4","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Security for langgraph-events 0.38.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
