Skip to content
Agents tracked: 492 Releases (7d): 545 Agent status: 1 with issuesSince last limit reset: Claude 9d · Codex 7d For AI agents: Markdown Updated Nov 20, 2026

LangChain

A framework for building LLM applications and agents from composable parts: model integrations, tools, retrievers and prebuilt agent abstractions. Available for Python and JavaScript.

Agent frameworks and SDKs LLM application framework

Use it in: API / SDK Works with: MCP Local models Multi-agent

WebsiteDocsGitHub

Checked Nov 5, 2026. Tap a verdict to see its source.How we checkedReport an error

What LangChain does

LangChain is a LLM application framework from LangChain, first released in October 2022. You use it through a Python library and a JavaScript library. Its documentation covers MCP servers, subagents or parallel agents and local models. It can run models from Anthropic, OpenAI, Google, xAI, Mistral and DeepSeek and others. It is used from Python and TypeScript. It is free and open source (MIT); you pay only for the models it calls.

What people use it for

An assistant that calls your functions

Give a model a few of your own functions, such as a weather lookup, and let it decide when to call them.

Switch model companies without a rewrite

Try OpenAI, then Anthropic or Google, by changing one model name, while everything else in your agent stays the same.

Ask a person before risky actions

Pause the agent before it writes a file or runs a database query, and let a person approve, edit or reject it.

Answer questions from your own documents

Build a help bot that looks up your private or recent documents and answers from them.

See every step your agent took

Turn on tracing to view each prompt, tool call and answer of your agent in LangSmith when something goes wrong.

Popularity
#1 in Frameworks
Gid Score 79 / 100 · #1 of 50 ranked frameworks and SDKs
Trend
Steady
downloads down 2.7% over 30 days · up 5.7% last week
Community
150K GitHub stars
41.1M package downloads a week

Usage data: latest readings Nov 17 to Nov 19, 2026, last checked Nov 19, 06:26 UTC. Date of each number

LangChain popularity and usage data

LangChain was downloaded 41.1M times from npm and PyPI in the week ending Nov 17, 2026, up 5.7% on the week before and down 2.7% over the last 30 days compared with the 30 before. The GitHub repository has 150K stars, 2,057 of them added in the last 30 days. The latest stable release is 1.5.2, published Nov 18, 2026; there were 7 stable releases in the past 30 days. It was mentioned in 66 Hacker News posts and comments over the last 30 days.

Downloads per daynpm and PyPI, 7-day average 5.9M/day
GitHub starsrunning total 150K
Hacker News mentionsposts and comments, rolling 7-day total 10 this week
Wikipedia page viewsEnglish Wikipedia, 7-day average 259/day

Download the raw daily series: langchain.csv

Gid Score breakdown

Adoption100
Community91
Attention44
Momentum47

Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.

How fresh these numbers are

NumberLatest readingLast checked
Package downloadsNov 17, 2026Nov 19, 06:24 UTC
GitHub starsNov 19, 2026Nov 19, 06:26 UTC
Wikipedia viewsNov 18, 2026Nov 19, 06:26 UTC
Hacker News mentionsNov 18, 2026Nov 19, 06:26 UTC

We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.

Pricing

LangChain is open source and free to use; you pay only for the models and infrastructure it runs on.

Checked Nov 5, 2026. Prices change often; confirm before you buy.

Compare prices of all agents

Quick answers

  • Free to start?Yes
  • Open source?Yes (MIT)
  • Where you use itPython library, JavaScript library
  • Supports MCP?Yes
  • Model providersanthropic, openai, google, xai, mistral, deepseek, amazon, azure, openrouter, any OpenAI-compatible, local
  • Subagents / multi-agent?Yes
  • Feature comparisonAll agents
  • Closest alternativeLangGraph · all alternatives

What changed: recent LangChain releases

19 stable releases in the last 90 days · Monthly summary · Full changelog

1.5.2
  • Changes since langchain==1.5.1
  • release(langchain): 1.5.2 feat(langchain): tag synthetic HITL tool messages with source metadata
1.5.1
  • Changes since langchain==1.5.0
  • release(langchain): 1.5.1 fix(core): keep warning suppression context-local fix(langchain): avoid warning-filter races in provider inference fix(langchain): avoid warning-filter races in…
Earlier releases
1.5.0
  • langchain 1.5.0 drops support for Python 3.10, which has reached end-of-life. The minimum supported version is now Python 3.11, and the minimum langchain-core version is now 1.8.0.
  • Changes since langchain==1.4.10
  • release(langchain): 1.5.0 fix(langchain): mark ModelRouterMiddleware as beta feat(langchain): Remove EOL'd Python 3.10 from langchain_v1 feat(langchain): add model router and auto mode middleware…
1.4.10
  • Changes since langchain==1.4.9
  • release(langchain): 1.4.10 fix(langchain): keep middleware-internal model calls off the messages stream chore(deps): patch newer-python security lock resolutions fix(langchain): omit trace inputs…
1.4.9
  • Changes since langchain==1.4.8
  • release(langchain): 1.4.9 chore(deps): require langchain-core>=1.7.5 for refusal handling feat(core): standardize model refusal content blocks
1.4.8
  • > [!WARNING] > Python 3.10 support will be dropped in langchain-core 1.8.0 and langchain 1.5.0. The current minor versions are the last to support Python 3.10. Please upgrade to Python 3.11 or later.
  • Changes since langchain==1.4.7
  • chore(langchain): bump langchain-core release(langchain): 1.4.8 chore(deps): bump pyasn1 from 0.6.4 to 0.6.5 in /libs/langchain_v1 chore(deps): bump joserfc from 1.7.4 to 1.7.6 in…

Compare LangChain with another agent

vs
# Agent Gid Score Downloads 7d 7d 30d Stars Latest release Price
2
LangGraphLangChain
75 20.1M up 5.5% up 29.2% 45.1K+48/day 1.2.23yesterday Free (OSS)
3
AI SDKVercel
68 47.2M up 3.9% up 38.4% 28.1K+30/day 7.0.1772d ago Free (OSS)
4 64 29.3M up 5.9% up 37.6% 8,588+9/day 0.2.185yesterday Free (OSS)
5
MastraMastra
63 3.7M up 14.9% up 49.9% 29.6K+23/day 1.84.02d ago Free (OSS)
6 62 7.2M up 4.8% up 38.9% 30.8K+21/day 0.25.02d ago Free (OSS)
7
Deep AgentsLangChain
59 3.1M up 4.9% up 51.3% 31.4K+29/day 0.2.112d ago Free (OSS)

Head to head: LangChain vs LangGraph · LangChain vs AI SDK · LangChain vs Claude Agent SDK · LangChain vs Mastra · LangChain vs OpenAI Agents SDK · LangChain vs Strands Agents

Tell LangChain

“Use LangChain's create_agent (langchain 1.5) with my OpenAI key from .env to build an agent that answers questions and can call my get_order_status function; ask me before any tool that changes data.”

  1. Install LangChain (Python 3.10 or newer per the docs; the 1.5.0 package on PyPI asks for 3.11+).

    pip install -U langchain

    From docs.langchain.com/oss/python/langchain/install.md

  2. Install the package for your model provider, for example OpenAI or Anthropic.

    pip install -U langchain-openai
    pip install -U langchain-anthropic
    

    From docs.langchain.com/oss/python/langchain/install.md

  3. Create an agent with create_agent, a model name and your tools (see the first use above).

    From docs.langchain.com/oss/python/langchain/overview.md

Mistakes to avoid

pip install langchain and calling an OpenAI model right away
Also install the provider package (langchain-openai, langchain-anthropic) or the extra, e.g. "langchain[openai]"

Model integrations live in separate provider packages.

Using the human-approval middleware without a checkpointer
Pass a checkpointer (InMemorySaver for tests, a database-backed one in production) and a thread ID

The paused state must be saved somewhere to resume.

Answering a risky tool's approval with respond to say no
Use reject to deny an action; keep respond for "ask the user" tools

A respond message counts as a successful tool result.

Giving the agent full database or file-system credentials
Use read-only keys, limit it to the tables and folders it needs, and run it in a container

Assume the model may use any permission it has, including deleting data.

Get started with LangChain

npmnpm install langchain
PyPIpip install langchain

These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.

LangChain FAQ

How much does LangChain cost?

LangChain is open source and free to use; you pay only for the models and infrastructure it runs on.

Is LangChain open source?

Yes. LangChain is open source, released under the MIT license.

How popular is LangChain?

LangChain was downloaded 41.1M times from npm and PyPI in the week ending Nov 17, 2026, up 5.7% on the week before and down 2.7% over the last 30 days compared with the 30 before. The GitHub repository has 150K stars, 2,057 of them added in the last 30 days. The latest stable release is 1.5.2, published Nov 18, 2026; there were 7 stable releases in the past 30 days.

What is the latest version of LangChain?

The latest stable release we track is 1.5.2, published on Nov 18, 2026.

What are the alternatives to LangChain?

The closest alternatives in the same category by Gid Score are LangGraph, AI SDK, Claude Agent SDK, Mastra.

More about LangChain

What's new

What's new in LangChain: November 2026 so far

Full monthly summary

November brought Python 3.11 as the new minimum requirement and introduced standardized model refusal handling across LangChain. The release focused on middleware improvements and stability refinements.

Action needed: Python 3.10 support removed; upgrade to Python 3.11 or later.
  • Python 3.10 support dropped; minimum version is now Python 3.11.
  • Standardized model refusal content blocks for consistent handling across providers.
  • New model router and auto mode middleware for intelligent model selection.
  • Fixed middleware to prevent internal model calls from appearing in message streams.

6 releases this month · summarised from the official release notes · all months

Articles

AgentGid articles about LangChain

All guides

Add-ons

Add-ons for LangChain: save tokens, add memory and tools

All agent tooling

Listed because each tool documents support for LangChain or for agent frameworks in general. Savings and results depend on your workload.

Used with it

Tools used with LangChain

All tools

What 2,952 public GitHub projects that depend on LangChain use with it, from their dependency files.

  1. python-dotenv58.0%
  2. Pydantic45.3%
  3. OpenAI Python Library41.6%
  4. Requests38.4%
  5. FastAPI37.0%
  6. Uvicorn36.5%
  7. NumPy35.5%
  8. pandas33.8%
  9. LangGraph32.3%
  10. PyYAML28.6%

Used far more often here than in AI-built projects overall: what sets LangChain projects apart.

  1. jsonpatch18.0% · 140.6×
  2. jsonpointer18.2% · 103.6×
  3. LangSmith23.2% · 72.7×
  4. distro18.2% · 32.6×
  5. orjson19.0% · 32.2×
  6. attrs19.1% · 28.4×
  7. tiktoken (Python)25.5% · 27.0×
  8. LangGraph32.3% · 25.9×
Ratings

Ratings from people who use LangChain

No ratings yet. Used LangChain? Rate it and say what it is good and bad at.

News

LangChain news

All AI agent news

  1. Release GitHub Releases

    LangChain 1.5.2 released

    Changes since langchain==1.5.1; release(langchain): 1.5.2 feat(langchain): tag synthetic HITL tool messages with source metadata (+1 more release that day)

  2. Official AWS Machine Learning

    Build composable, interoperable multi-agent systems with A2A on AWS

    AWS demonstrates a multi-agent system using the Agent-to-Agent (A2A) protocol, with a LangChain orchestrator on ECS communicating with a Strands agent on Bedrock AgentCore via OAuth-authenticated calls.

  3. Release GitHub Releases

    LangChain 1.5.0 released

    langchain 1.5.0 drops support for Python 3.10, which has reached end-of-life. The minimum supported version is now Python 3.11, and the minimum langchain-core version is now 1.8.0.; Changes since langchain==1.4.10; release(langchain): 1.5.0 fix(langchain)…

Price history

LangChain prices over time

Token prices of Anthropic modelsnewest Anthropic model in each family, output price per 1M tokens
Anthropic OpusAnthropic SonnetAnthropic Haiku
Sources
For the makers of LangChain badges, corrections

Add a live badge to your README or site:

AgentGid: #1 in Frameworks Gid Score: 79/100 downloads: 41.1M/week ▼3% 30d

[![AgentGid: #1 in Frameworks](https://agentgid.com/badges/langchain-rank.svg)](https://agentgid.com/agents/langchain/)
[![Gid Score: 79/100](https://agentgid.com/badges/langchain-score.svg)](https://agentgid.com/agents/langchain/)
[![downloads: 41.1M/week ▼3% 30d](https://agentgid.com/badges/langchain-downloads.svg)](https://agentgid.com/agents/langchain/)

Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.

Where these numbers come from

npm: langchain. PyPI: langchain. GitHub: langchain-ai/langchain. Wikipedia: LangChain. See data sources for how each one is collected.