langchain-ai/langchain
LangChain is a versatile framework for building and deploying applications powered by large language models, offering interoperability, real-time data integration, and advanced agent orchestration capabilities.
Awesome AI Agents › Language Agent Frameworks
langchain-ai/langgraph
LangGraph is a low-level orchestration framework designed for building resilient and controllable language agents as graphs. It is used by major companies such as Replit, Uber, LinkedIn, and GitLab, highlighting its reliability and production readiness. Unlike LangChain, which provides integrations and composable components for LLM application development, LangGraph focuses on agent orchestration, offering customizable architectures, long-term memory, and human-in-the-loop capabilities to handle complex tasks effectively. The framework supports developers in creating powerful and adaptable AI agents with features like moderation checks, human approvals, and persistent context for long-running workflows, ensuring agents remain on course. LangGraph is highly extensible, allowing the construction of custom agents with low-level primitives free from rigid abstractions, enabling scalable multi-agent systems tailored to specific use cases. One of LangGraph's standout features is its first-class streaming support, which includes token-by-token streaming and streaming of intermediate steps, providing clear visibility into agent reasoning and actions in real time. This transparency is crucial for debugging and understanding agent behavior. LangGraph integrates seamlessly with the LangChain ecosystem, enhancing LLM application development with tools like LangSmith for agent evaluation and observability, and LangGraph Platform for deploying and scaling agents with features like visual prototyping, auto-scaling task queues, and centralized agent management. The project offers extensive documentation, tutorials, templates, how-to guides, and an API reference to support developers in leveraging its capabilities. It also provides a free structured course through LangChain Academy to help users get started. LangGraph is inspired by technologies like Pregel and Apache Beam and draws interface inspiration from NetworkX. It is open-source and can be used independently of LangChain, making it a versatile tool for building sophisticated AI agent workflows.
https://github.com/langchain-ai/langgraph
Also in Language Agent Frameworks
microsoft/semantic-kernel
Semantic Kernel is an enterprise-ready orchestration framework by Microsoft that enables developers to build and deploy intelligent AI agents and multi-agent systems using cutting-edge large language model technology.
dataelement/bisheng
BISHENG is an open-source LLM DevOps platform designed for enterprise AI applications, offering powerful workflow orchestration, security features, and high-precision document parsing to support complex intelligent business solutions.
VoltAgent/voltagent
VoltAgent is an open-source TypeScript framework for building and orchestrating AI agents powered by Large Language Models, enabling developers to create scalable, customizable, and maintainable AI applications with modular components and visual monitoring.
kyegomez/swarms
Swarms is an enterprise-grade, production-ready multi-agent orchestration framework designed to enable complex AI workflows with high scalability, flexibility, and robust developer and security features.
langchain-ai/langgraphjs
LangGraph.js is a low-level orchestration framework for building customizable, reliable, and controllable language agents as graphs, enabling complex AI workflows with features like long-term memory, human-in-the-loop, and real-time streaming support.
neuron-core/neuron-ai
PHP framework for creating and orchestrating AI agents, covering LLM providers, tools, RAG, MCP, event-driven workflows with checkpointing and human-in-the-loop, streaming UI protocols and monitoring.
trpc-group/trpc-agent-go
Go framework for production agent systems providing LLM agents, type-safe graph workflows, tool calling, session and memory state, knowledge retrieval, evaluation and OpenTelemetry observability.