LangChain is an agent engineering platform designed for building LLM-powered applications. It offers a modular architecture for integrating various components and third-party tools. The project is open-source under the MIT license and has been actively developed since October 17, 2022.
Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).
What it is
LangChain is a framework for building agents and LLM-powered applications. It helps you chain together interoperable components and third-party integrations to simplify AI application development.
How it works
LangChain allows developers to build applications powered by LLMs through a standard interface for models, embeddings, vector stores, and more. It supports real-time data augmentation and model interoperability, enabling quick adaptations to evolving technologies.
Getting started
To install LangChain, use the following command:
uv add langchain
To initialize a chat model, you can use the following Python code:
from langchain.chat_models import init_chat_model
model = init_chat_model("openai:gpt-5.5")
result = model.invoke("Hello, world!")
Recent releases
- langchain==1.3.13 (2026-07-10): Added
metaextra and support for langchain-meta in init_chat_model. - langchain-openai==1.3.5 (2026-07-10): Support for explicit prompt caching.
- langchain-fireworks==1.4.4 (2026-07-09): Report cached prompt token usage.
- langchain==1.3.12 (2026-07-08): Fixes for interrupt propagation and process-group kill in shell.
- langchain-openai==1.3.4 (2026-07-08): Suppressed Pydantic serializer warning.
Traction
- Stars: 141551
- Forks: 23530
- Open issues: 419
Behind the repo
LangChain is an open-source project under the MIT license, created on October 17, 2022.
Caveats
- License: MIT
- Open issues: 419
- Age: Created on 2022-10-17.