#2828th of 48 in Agent frameworks and SDKs
langchainjs
TypeScript framework for building LLM apps and agents with swappable model integrations
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 18.3k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- TypeScript
Missed the latest GitHub check; these facts may be older.
LangChain is hiring: 98 open roles
Overview
LangChain.js is a TypeScript library that gives agents, chat models, embeddings, vector stores and retrievers a common interface, with integrations for many providers. It runs on Node.js 20, 22 and 24, Cloudflare Workers, Deno, Bun, Vercel/Next.js and in the browser. Deep Agents (higher-level) and LangGraph.js (lower-level orchestration) are separate packages built on or alongside it.
Who it is for: TypeScript and JavaScript developers building LLM apps and agents
Strengths
- Runs on Node.js (ESM and CommonJS), Deno, Bun, Cloudflare Workers, Supabase Edge and browsers
- Common interface across models, embeddings, vector stores and retrievers makes providers swappable
- Large integration library covering model providers, tools and vector stores
- Pairs with LangGraph.js for orchestration and Deep Agents for planning and subagents
Weaknesses
- Monitoring and evaluation depend on LangSmith, a separate hosted product
- Abstraction layers add indirection over direct provider SDK calls
- Advanced orchestration requires learning a second package, LangGraph.js
- README gives no resource requirements or version-compatibility details for integrations
What it needs
- no GPU
- Needs Node.js 20/22/24 or Deno/Bun, LLM provider API
- Models: Multiple providers via integrations
Also in Agent frameworks and SDKs
See all 48| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 93 out of 100 |
| 2 | browser-usePython library that lets an LLM agent control a web browser | 89 out of 100 |
| 3 | langchainPython framework for building LLM agents and apps from interoperable components | 88 out of 100 |
| #4 | tradingagentsLangGraph multi-agent framework simulating a trading firm to analyze tickers | 88 out of 100 |
| #5 | copilotkitSDK for adding agent chat, generative UI and shared state to apps | 87 out of 100 |