Awesome AI AgentsLanguage Agent Frameworks

neuron-core/neuron-ai

⭐ 2093 PHP repository created 2025-03-02

Neuron is a PHP framework for building and orchestrating AI agents inside PHP applications, requiring PHP 8.1 or newer and installed through Composer. Agents are written as classes that extend a base Agent class and declare an LLM provider and a set of instructions; a SystemPrompt helper assembles the instruction text into a consistent prompt, and a console command scaffolds new agent classes. The base class handles conversation memory, tool registration and function calling, so an agent remembers earlier turns of a chat without extra code. Beyond single agents the framework covers what the maintainers describe as the whole agentic application lifecycle: LLM provider interfaces including Anthropic, data loading and retrieval augmented generation, structured output, tools and toolkits, a connector for the Model Context Protocol, and multi-agent orchestration. Its Workflow component is event driven with checkpointing, human-in-the-loop interruption, loops and shared state, and the same workflow abstraction is meant to scale from a first tutorial agent to a production multi-agent system. Streaming is supported through agentic UI protocols, with adapters for AG-UI and the Vercel AI SDK protocol, and agents can also be executed asynchronously. Because agent behaviour is probabilistic rather than deterministic, the project puts weight on observability and ships monitoring and debugging integration so that individual LLM calls, tool invocations and memory access inside a multi-step run can be inspected. Around the framework the maintainers run a vertical ecosystem with a registry of extensions, tools and technologies aimed specifically at agentic applications, plus documentation, video tutorials and a newsletter. It is intended for PHP developers who want agent functionality in an existing PHP codebase instead of moving that part of the stack to Python or JavaScript.

https://github.com/neuron-core/neuron-ai

phpagent-frameworkworkflowragmcp

Also in Language Agent Frameworks

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.

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.

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.