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
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.
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.
amd/gaia
AMD open-source framework for building LLM agents that run entirely locally on Ryzen AI hardware, with tool orchestration, RAG, voice, vision and MCP client support.
ThousandBirdsInc/chidori
Chidori is an open-source reactive runtime and IDE for building durable AI agents with advanced debugging, state management, and observability features.
Deuz-AI/Deuz-SDK
Deuz SDK is a zero-dependency TypeScript agent runtime that adds long-term memory, context compaction, durable checkpointed execution, guardrails, human approval, MCP tool calling and agent handoff over 28 chat providers on Node, Bun, Deno and edge runtimes.
promptise-com/Foundry
Python agent framework bundling model access, MCP tool discovery, memory, guardrails, semantic caching, multi-tenancy, human approvals, a runtime and tracing behind one build_agent call.
go-kratos/blades
Go framework from the Kratos project for building multimodal LLM agents with pluggable model providers, prompts, chains, tools, memory and middleware for observability and guardrails.
MaestroError/LarAgent
Laravel package for building AI agents with an Eloquent-style API, covering tools and MCP servers, pluggable memory, structured output, events and multi-agent workflows backed by queues.
ArtificialAnalysis/Stirrup
Lightweight Python framework and starting template for building LLM agents, with a thin tool-calling loop, code execution locally or in Docker and E2B, MCP client support, skills and context summarisation.
AmeNetwork/aser
Aser is a minimal modular Python agent framework that assembles an agent from model, tools, memory, knowledge and MCP components in a few lines, with multi-agent patterns, A2A support and on-chain Web3 connectors.
howl-anderson/agentsilex
AgentSilex is a minimal Python agent framework with a core of about 300 lines, built on LiteLLM, that provides agents, typed tools, sessions, streaming, handoffs and OpenTelemetry tracing.
Kong/volcano-sdk
Volcano is a TypeScript SDK from Kong for building agents that chain LLM reasoning with MCP tools across multiple model providers, with parallel steps, branching, loops, multi-agent crews, streaming and OpenTelemetry tracing.
orra-dev/orra
Orra is a resilient AI agent workflow infrastructure that ensures reliable execution and recovery of multi-agent tasks through intelligent planning, state persistence, and real-time monitoring.