LangChainLangChain is a framework for building agents and LLM-powered applications by chaining together interoperable components and third-party integrations. It provides a standard interface for models, embeddings, vector stores, and other building blocks, so an application can swap providers as models change without rebuilding its logic.
The framework can be used standalone or with the rest of the LangChain ecosystem: Deep Agents is a higher-level package built on LangChain for agents with planning, subagents, and file-system use; LangGraph is the low-level orchestration framework for controllable agent workflows; LangSmith covers agent evals, observability, debugging, and deployment of long-running stateful workflows. A JavaScript/TypeScript equivalent, LangChain.js, is maintained separately. Model access starts from initchatmodel, which takes a provider-prefixed model name such as openai:gpt-5.5.
Features
- Standard interfaces: common abstractions for chat models, embeddings, vector stores, retrievers, and tools
- Integrations library: model providers, tools and toolkits, vector stores, and retrievers
- Model interoperability: swap models through one interface as requirements change
- Layered abstractions: high-level chains for quick starts and low-level components for fine-grained control
- Deep Agents: planning, subagents, and file-system use built on top of LangChain
- LangGraph: low-level orchestration for stateful agent workflows
- LangSmith: evals, observability, debugging, and deployment
- LangChain.js: JavaScript/TypeScript counterpart
Built with this
AgentGPT
Browser platform for assembling goal-driven autonomous agents that plan and execute tasks; the repository is archived
Bisheng
BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI wo
Deep Agents
Opinionated, model-agnostic agent harness on LangGraph with sub-agents, filesystem, and context management built in
DeerFlow
DeerFlow 2.0 is ByteDance's open-source super-agent harness.
Integrated by
AG2
Open-source framework for building AI agents and orchestrating cooperation among multiple agents
AgentOps
Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI.
AgentQL
AgentQL is a suite of tools for connecting your AI to the web. Featuring a query language and Playwright integrations for interacting with e
AtomicMemory
Portable, inspectable semantic memory for agents - one protocol across an SDK, CLI, MCP server, framework adapters and host plugins
Alternatives
724 Office
724-office runs a full AI agent loop in 3,500 lines of pure Python with three dependencies. Three-layer memory, MCP inte
Instructor
Structured, validated LLM output defined as Pydantic models, with automatic retries, streaming, and multi-provider support
Langroid
Python framework for building LLM applications with collaborating multi-agent message passing
Orkas
Open-source multi-agent AI desktop client — build and command your AI agent team through conversation. A commander LLM dispatches sub-agents
Mentioned with
Browser Use Lower-confidence signal
Python library that lets an LLM agent operate a web browser — opening pages, clicking, typing, and filling forms from a task description
Langflow Lower-confidence signal
Visual drag-and-drop builder that turns agent workflows into APIs or MCP servers, with Python-customizable components
