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
ArtificialAnalysis/Stirrup
Stirrup is a Python framework and starting template for building LLM agents, published by Artificial Analysis and paired with a TypeScript implementation called StirrupJS. Its design premise is that rigid hard-coded workflows degrade model performance, so the framework keeps the scaffolding thin and lets the model choose its own approach to a task, in the manner of coding agents such as Claude Code and Codex. The core is an Agent class that runs a tool-calling loop until a finish tool is invoked or a turn limit is reached, wrapped in a session context manager that sets up tool providers, manages working files and output directories, records logs and cleans up afterwards. Tools are declared through a generic Tool interface with Pydantic parameter models, and a ToolProvider abstraction covers tools that need connection or directory lifecycles. The default tool set includes shell and code execution plus web search and page fetching. Code can run locally, inside Docker, or in an E2B sandbox. Further built-in capabilities cover an MCP client for connecting to Model Context Protocol servers and using their tools and resources, document import and file output, a skills system that packages domain instructions as modular units, a human-in-the-loop tool that lets the agent ask a person for clarification mid-run, automatic conversation summarisation as the context limit approaches, and multimodal handling of images, video and audio with automatic format conversion. Model access is provider-agnostic: there is prebuilt support for OpenAI-compatible chat completion endpoints and LiteLLM, and any custom client can be supplied. The package installs from PyPI with optional extras for litellm, docker, e2b, mcp and browser support, and it can also be cloned and installed in editable mode when the intent is to fork it as the base of a bespoke agent. It suits developers who want a small readable agent core they can extend rather than a large opinionated platform.
https://github.com/ArtificialAnalysis/Stirrup
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.