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
AmeNetwork/aser
Aser is a compact agent framework whose stated aim is that a working agent can be declared in a few lines of Python: an Agent object takes a name and a model identifier, and optional arguments attach tools, a knowledge store for retrieval, a memory backend, MCP servers, tracing and Web3 connectors. The design is modular, so each capability is an independent component that can be omitted. Installation is through PyPI or from source. The example set is organised by difficulty. Beginner examples cover model configuration, character definition, memory storage, retrieval-augmented knowledge, tools and built-in toolkits, tracing, an API server, a command line interface and chat clients for Discord, Telegram and Farcaster. Intermediate examples add chain-of-thought prompting, Model Context Protocol usage, text-to-SQL querying, custom workflows, evaluation of an agent, and five multi-agent topologies: router-based task distribution, sequential pipelines, parallel execution, reactive coordination and hierarchical teams. A separate repository provides a web interface for interacting with agents. The advanced material reflects the project origin in the Web3 ecosystem: a Model Smart Contract Protocol connects agents to on-chain contracts, the Google Agent2Agent protocol is supported on both the server and the client side, and a self-coding tool lets an agent write new tools for itself. Experimental examples register agent identity and offer paid services through the ERC-8004 standard for trustless agent interaction on Ethereum. Configuration is driven by environment variables, and only the variables for the components actually in use need to be set. The framework is MIT licensed with documentation hosted by Ame Network. It suits developers who find larger orchestration frameworks heavyweight, and particularly those building agents that must interact with blockchain contracts or identity registries alongside ordinary LLM tooling.
https://github.com/AmeNetwork/aser
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.