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
Deuz-AI/Deuz-SDK
Deuz SDK is a TypeScript framework for agents intended to run in production, built around the argument that calling a model is the easy part and everything surrounding it is not. The core package ships with no runtime dependencies and injects clock, randomness, fetch, API keys and logging rather than reaching for ambient globals, so the same code runs on Node 22 or later, Bun, Deno and edge runtimes while tests stay deterministic. Two features are highlighted as the ones developers would otherwise build themselves. Memory is a pipeline, not a message array: it extracts durable facts from a conversation, reconciles them against existing knowledge with add, update and delete operations instead of blind appends, scores facts for importance, expires them and recalls the relevant ones on the next call, backed by a vector store, a Postgres table or an Obsidian vault. Compaction keeps long runs alive by pruning stale tool output, dropping old reasoning and folding early turns into a single running summary that is updated rather than stacked, and it force-compacts and retries a step when a provider rejects a request as too long. Around those sit parallel tool calls with self-healing errors, runaway guards and cost and token budgets, sub-agents, human-in-the-loop approval at any depth with HMAC-signed expiring tokens that deny on a missing verdict, step checkpoints stored in the developer own database with resume after a crash, guardrails that pass, block or rewrite input, tool calls and final answers, handoff that moves a conversation with its history and tools to another agent, MCP connections with OAuth 2.0, reconnect, sampling and roots, planning with CodeAct sandboxes and verification steps, SQLite, Redis and Postgres store packs, versioned trace events with a JSONL observer, a standalone HTML run report and an OpenTelemetry bridge, plus an optional React package for resumable chat interfaces.
https://github.com/Deuz-AI/Deuz-SDK
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.