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
promptise-com/Foundry
Promptise Foundry is a Python framework that bundles the layers usually assembled by hand around an LLM agent: model access, tool discovery, memory, security, a runtime and observability. The README argues that most agent stacks are glued together from a model SDK, a tool layer, a vector database, auth, guardrails, a job runner and logging, and positions Foundry as a single framework covering all of them, with each capability switched on by a parameter rather than another dependency. The entry point is an async build_agent() call that takes a model identifier such as openai:gpt-5-mini, a mapping of tool servers (for example an HTTPServerSpec pointing at an MCP endpoint), free-text instructions, and optional components: a memory provider such as ChromaProvider for state that survives across calls, a PromptiseSecurityScanner guardrail set that blocks prompt injection and redacts PII, a SemanticCache that serves similar queries from earlier results, and observe=True for step-level tracing. The agent discovers the tools published by its MCP servers on its own, so tool definitions do not have to be restated in code, and a Python decorator defines custom tools. Beyond a single agent the framework covers multi-tenancy, human approval steps and a runtime intended to run a fleet of agents from the same installation that runs one agent on a laptop. Supported model providers include OpenAI, Anthropic and Gemini as well as local models through Ollama. The package installs with pip install promptise, requires Python 3.10 or newer, is fully asynchronous, is type-checked with mypy in strict mode, and the README reports roughly 3,493 tests and no high-severity bandit findings. It is Apache 2.0 licensed with documentation at docs.promptise.com. The repository is also reachable under its earlier name cryxnet/DeepMCPAgent.
https://github.com/promptise-com/Foundry
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.