Agent framework - verified
LangChain (agents): features, install and latest version
LangChain (agents) is an AI agent framework maintained by LangChain Inc. As its docs describe it: LangChain is a framework for building agents and LLM-powered applications whose create_agent function provides a configurable agent harness of model, tools, prompt, and middleware, built on top of LangGraph. It supports Python and TypeScript. License: MIT. Latest releases: Python package langchain 1.4.6 (October 14, 2026) and TypeScript package langchain 1.5.18 (October 16, 2026).
Homepage - Source on GitHub - License - In our tools directory
- Languages
- 2
- Latest Python
- 1.4.6
- Released
- 2026-10-14
- Features documented
- 9 of 10
Install
Copied verbatim from the page linked under each command.
Python
pip install -U langchainuv add langchainTypeScript
npm install langchain @langchain/coreQuickstart
The first example from the official docs, unchanged. It may need an API key for the model provider it calls.
# pip install -qU langchain "langchain[openai]"
from langchain.agents import create_agent
def get_weather(city: str) -> str:
"""Get weather for a given city."""
return f"It's always sunny in {city}!"
agent = create_agent(
model="openai:gpt-5.5",
tools=[get_weather],
system_prompt="You are a helpful assistant",
)
result = agent.invoke(
{"messages": [{"role": "user", "content": "What's the weather in San Francisco?"}]}
)
print(result["messages"][-1].content_blocks)Features
What the LangChain (agents) docs say it supports. Not stated means the docs do not say either way.
| Feature | Value | Source |
|---|---|---|
| MCP | Yes | docs.langchain.com/oss/python/langchain/mcp |
| Multi-agent | Yes | docs.langchain.com/oss/python/langchain/multi-agent |
| Durable execution | Yes | docs.langchain.com/oss/python/langchain/overview |
| Human in the loop | Yes | docs.langchain.com/oss/python/langchain/human-in-the-loop |
| Streaming | Yes | docs.langchain.com/oss/python/langchain/streaming |
| Structured output | Yes | docs.langchain.com/oss/python/langchain/structured-output |
| Tracing | Yes | docs.langchain.com/oss/python/langchain/overview |
| Memory | Yes | docs.langchain.com/oss/python/langchain/short-term-memory |
| Evals | Not stated | Docs do not say |
| Model-agnostic | Yes | docs.langchain.com/oss/python/langchain/overview |
| Languages | Python, TypeScript | See sources below |
| License | MIT | github.com/langchain-ai/langchain/blob/master/LICENSE |
| Latest Python release | langchain 1.4.6October 14, 2026 | pypi.org/project/langchain/1.4.6 |
| Latest TypeScript release | langchain 1.5.18October 16, 2026 | npmjs.com/package/langchain/v/1.5.18 |
LangChain (agents) on Developers Digest
Compare LangChain (agents)
FAQ
Does LangChain (agents) support MCP?
Yes, per https://docs.langchain.com/oss/python/langchain/mcp
Which languages does LangChain (agents) support?
Python and TypeScript. Published packages: langchain (Python) and langchain (TypeScript).
How do I install LangChain (agents)?
For Python: "pip install -U langchain", as shown at https://docs.langchain.com/oss/python/langchain/install. This page lists 3 install commands, each copied from the linked source.
What is the latest version of LangChain (agents)?
As of October 18, 2026: Python package langchain 1.4.6 (October 14, 2026), https://pypi.org/project/langchain/1.4.6/ and TypeScript package langchain 1.5.18 (October 16, 2026), https://www.npmjs.com/package/langchain/v/1.5.18.
What license is LangChain (agents) released under?
MIT. The license is at https://github.com/langchain-ai/langchain/blob/master/LICENSE.
Does LangChain (agents) support durable execution?
Yes, per https://docs.langchain.com/oss/python/langchain/overview
Does LangChain (agents) support human-in-the-loop?
Yes, per https://docs.langchain.com/oss/python/langchain/human-in-the-loop
Is LangChain (agents) model-agnostic?
Yes, per https://docs.langchain.com/oss/python/langchain/overview
Which features does LangChain (agents) document?
9 of the 10 tracked here: MCP, Multi-agent, Durable execution, Human in the loop, Streaming, Structured output, Tracing, Memory and Model-agnostic. Not stated in its docs: Evals.
Sources
Last verified from the pages below.
- LangChain overview (docs) - docs.langchain.com
- GitHub README - github.com
- LICENSE - github.com
- PyPI langchain - pypi.org
- npm langchain - npmjs.com
- Install (Python) - docs.langchain.com
- Install (JavaScript) - docs.langchain.com
- MCP - docs.langchain.com
- Multi-agent - docs.langchain.com
- Human-in-the-loop - docs.langchain.com
- Streaming - docs.langchain.com
- Structured output - docs.langchain.com
- Short-term memory - docs.langchain.com
Newsletter
Agent frameworks, every week
One email per week. Framework releases, new agent tooling and what they mean for what you build.