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
go-kratos/blades
Blades is a multimodal AI agent framework for Go, maintained under the go-kratos organization and named after the weapons of the game character Kratos. It targets Go developers who want to build LLM applications without adopting a Python stack, and it is designed so the resulting code reads like ordinary idiomatic Go. The framework is organized around a small set of composable primitives. Agent is the central interface: any executable component implements a Run method, which gives the framework a single execution paradigm and lets agents, chains and other units nest inside each other. Prompt provides templated text for model interaction with dynamic variable substitution and structured context assembly. Chain connects several agents or other chains into larger workflows. ModelProvider is the pluggable abstraction over language model services, so switching between vendors such as OpenAI and others is a configuration change rather than a rewrite. Tool exposes external capabilities that an agent may invoke, including HTTP APIs, database queries and file system access. Memory supplies short-term or long-term state so a conversation can carry context across turns. Middleware, borrowed conceptually from the Kratos web framework, wraps agent execution for cross-cutting concerns, and the documentation names observability and guardrails as the primary examples. The stated use cases are multi-turn conversation, chain-of-thought style reasoning and structured output generation. Because everything is expressed through unified interfaces and pluggable components, the architecture aims for decoupling: model backends, tools and memory implementations can be swapped independently. The project publishes Go module documentation on pkg.go.dev, a separate documentation site under go-kratos.dev, and repository topics covering agent SDK, agent workflow and multi-agent scenarios. It fits backend teams already running Go services who want agent capabilities inside their existing runtime and deployment tooling.
https://github.com/go-kratos/blades
Also in Language Agent Frameworks
langchain-ai/langgraph
LangGraph is a low-level orchestration framework for building resilient, controllable AI language agents with customizable architectures, long-term memory, and real-time streaming support, used by major companies and integrated with the LangChain ecosystem.
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.