Orchestration Frameworks
62 compositions.
- Agent Network Protocol (ANP) — Open specification (and reference implementation) for decentralised agent-to-agent communication: cross-platform DID identity, dynamic protocol negotiation, an…
- Agent Payments Protocol (AP2) — Define an open protocol for agent-led payments built on signed mandates and verifiable digital credentials that bound spending and leave a cryptographic audit…
- Agent Squad — Lightweight open-source multi-agent orchestration framework: a classifier routes each user query to the most suitable specialized agent while conversation cont…
- Agent2Agent Protocol (A2A) — A2A is an open protocol that lets independent AI agents built by different vendors or frameworks discover each other and exchange tasks, messages, and results…
- Agentic Commerce Protocol (ACP) — Open protocol (OpenAI and Stripe) by which a merchant exposes a product feed and an agentic checkout API so any compatible agent can discover products and secu…
- AgentScope — Provide a production-ready agent framework with built-in ReAct agent, MsgHub for multi-agent message routing, MCP/A2A integration, real-time steering via hooks…
- AgentVerse — Multi-agent framework with two distinct modes: task-solving (collaborative agents work toward a shared goal) and simulation (autonomous agents interact in an e…
- Agno — Provide an SDK and runtime for building agent platforms — role-defined Agents, multi-mode Teams (coordinate / route / broadcast / sequential), Workflows, persi…
- Atomic Agents — Provide a lightweight, schema-driven framework for building Agentic AI pipelines as composable LEGO-style blocks — each AtomicAgent or tool has a Pydantic inpu…
- AutoAgent — Allow non-coders to build and run LLM agents through natural-language dialogue — the framework profiles agents, generates tools and workflows, and runs them in…
- AutoGen — Build scalable, event-driven multi-agent AI applications in which conversable agents exchange asynchronous messages, optionally execute code, and coordinate th…
- AutoGPT — Provide a platform to create, deploy, and run continuous autonomous AI agents that chain LLM reasoning with a fixed Command/Tool catalogue, an episodic action…
- BabyAGI — Explore the self-building autonomous-agent direction via the functionz function framework — a database-backed store of named functions with dependency tracking…
- BeeAI Framework — Provide a multi-language (Python + TypeScript) framework for production-ready multi-agent systems with a RequirementAgent that enforces declared rules across L…
- Burr — Build stateful decision-making applications (chatbots, agents, simulations) as an explicit state machine of @action-decorated functions with pluggable persiste…
- CAMEL-AI — Study agent scaling laws by providing a multi-agent framework whose core building blocks are ChatAgent (tool-calling LLM agent), RolePlaying (AI-assistant + AI…
- Camunda 8 (Agentic Orchestration) — Camunda 8 orchestrates LLM-driven agents inside BPMN processes so an agent decides which tools to call while the Zeebe engine deterministically executes the se…
- ChatDev — Communicative multi-agent framework for software development that runs a waterfall SDLC (design → coding → testing → documentation) through role-specialised LL…
- CrewAI — Orchestrate teams of role-playing autonomous agents that collaborate on multi-step tasks under a declared Process (sequential or hierarchical), optionally driv…
- DB-GPT — Open-source AI-native data platform built around the AWEL agent workflow language, multi-model support, and natural-language access to databases (Text2SQL, vec…
- Dendron — Dendron is a Python library for programming LLM agents as behavior trees whose leaves are model and tool actions composed by control nodes.
- DSPy — Replace hand-tuned prompts with a declarative Python programming model in which you specify input/output behaviour as Signatures, compose Modules (Predict, Cha…
- Eko — Build production-ready agentic workflows in JavaScript/TypeScript from natural-language commands — decomposing a request into a multi-step workflow that runs m…
- Genkit — Provider-neutral framework for building AI-powered apps with unified APIs, tool calling and agentic workflows.
- GPTSwarm — Represent LLM-based agents and their connections as optimizable graphs whose edges and prompts are tuned automatically toward better swarm performance.
- Guardrails AI — Wrap LLM calls with composable input and output guards built from validators that detect, quantify, and mitigate specific risks.
- Hamilton — Express data and LLM pipelines as a directed acyclic graph of Python functions so transformations are testable, modular, and have automatic lineage and executi…
- Haystack — Build production-ready LLM applications — RAG, agents, and multimodal search — as explicit pipelines of typed Components with a tool-using Agent at the top.
- HippoRAG — Hippocampus-inspired RAG framework that builds a knowledge graph from documents and uses Personalized PageRank for multi-hop retrieval, replacing naive top-k v…
- Inspect AI — Inspect AI is an evaluation framework that runs labelled datasets through solvers and scorers to measure language-model and agent performance.
- JADE (Java Agent DEvelopment Framework) — Provide a FIPA-compliant Java platform where agents communicate through typed ACL messages and standard interaction protocols such as Contract Net.
- KAG (Knowledge Augmented Generation) — Knowledge-augmented generation framework built on the OpenSPG knowledge graph engine that translates natural-language questions into logical forms over a schem…
- LangChain — Provide a standard, model-agnostic Python/TypeScript interface plus a prebuilt agent (create_agent) for building LLM applications that loop over tool calls in…
- LangGraph — Provide low-level orchestration infrastructure for long-running, stateful agents with durable execution, persistent memory, and built-in human-in-the-loop inte…
- Letta — Build stateful LLM agents that remember, learn, and improve over time by self-managing a tiered memory (in-context blocks plus archival/recall stores) via tool…
- LlamaIndex — Provide an open-source Python/TypeScript framework for context-augmented LLM and agent applications combining RAG primitives (data connectors, indexes, query e…
- Machine Payments Protocol (MPP) — Open HTTP-native machine-payment protocol (Stripe and Tempo) that standardises HTTP 402 with a Challenge-Credential-Receipt flow so an agent can pay for any se…
- Marvin — Express agentic AI work as a set of structured Tasks executed by portable Agents inside Threads, producing validated Pydantic outputs.
- Mastra — Provide a TypeScript-native framework for AI agents and multi-step workflows, where Agents run an LLM tool-calling loop bounded by maxSteps, Workflows give gra…
- MetaGPT — Materialise software-engineering Standard Operating Procedures as multi-agent teams of Roles whose communication is mediated by an Environment.
- Microsoft Agent Framework — Unify Microsoft's two prior agent stacks — AutoGen's multi-agent orchestration and Semantic Kernel's enterprise plugin and connector model — into one SDK for b…
- ModelScope-Agent — Provide a lightweight, extensible Chinese-ecosystem agent framework with RolePlay agents, tool calling, hybrid RAG, and MCP-mediated multi-agent workflows.
- Not Diamond — Commercial intelligent model-routing service that predicts the best-performing model per query and dispatches automatically across configured endpoints.
- NVIDIA NeMo Guardrails — NeMo Guardrails adds programmable rails around an LLM-based conversational application so that inputs and outputs can be checked, rewritten, or rejected outsid…
- OpenAgents — Open platform for language agents in the wild, bundling three specialised agents — Data Agent (Python/SQL data analysis), Plugins Agent (200+ APIs), and Web Ag…
- OpenManus — Provide an open, no-invite-code clone of the Manus general AI agent that combines a ReAct tool-calling loop with browser-use, code execution, and MCP tools.
- OpenRouter — Hosted LLM aggregator that exposes a single OpenAI-compatible endpoint over hundreds of models from many providers, with built-in provider routing, automatic f…
- picoagents — Teach the building blocks of production multi-agent systems through small, testable primitives.
- PocketFlow — Capture the core graph abstraction of LLM frameworks in 100 lines of zero-dependency Python so Agent, Multi-Agent, Workflow, and RAG patterns can be assembled…
- Portkey (Conditional Routing) — Portkey is an AI gateway that routes each LLM request to a provider target by deterministic rules over request metadata and parameters, and falls back to anoth…
- Pydantic AI — Provide a Python-first, model-agnostic agent framework that brings the 'FastAPI feeling' to GenAI by making Pydantic-validated structured output, type-safe dep…
- Qwen-Agent — Provide a Python framework for building LLM applications that exercise the instruction-following, tool-use, planning, and memory capabilities of Alibaba's Qwen…
- Ragas (synthetic testset generation) — Ragas generates synthetic test sets across named question dimensions and scores RAG and agent outputs with LLM-based evaluation metrics.
- RAGFlow — Open-source RAG engine that pairs deep document-understanding (DeepDoc) layout-aware parsing with an agentic, graph-orchestrated workflow runtime, MCP support,…
- RouteLLM — Research framework for training and serving LLM routers that dynamically dispatch each query between a stronger, more expensive model and a cheaper but weaker…
- Semantic Kernel — Lightweight model-agnostic SDK (C#/Python/Java) that turns existing code into Plugins of KernelFunctions so LLMs can call them via auto function calling, with…
- Semantic Router — Semantic Router is a Python decision layer that routes a query to a predefined route by embedding similarity instead of an LLM call, returning the matched rout…
- smolagents — Provide a barebones (~1k LoC) Python library for multi-step ReAct agents whose default action format is executable Python code rather than JSON tool calls, wit…
- TaskWeaver — Code-first agent framework that converts user requests into executable Python code, preserves in-memory state (variables, DataFrames) across turns, and orchest…
- Together Mixture-of-Agents (MoA) — Together Mixture-of-Agents sends a prompt to several open-source LLMs acting as proposers and has a final aggregator LLM synthesize their responses into one an…
- Universal Commerce Protocol (UCP) — Google coalition protocol for agentic commerce in which merchants publish agent-readable product catalogs with real-time pricing and inventory, surfaced to sho…
- XAgent — Autonomous LLM agent for complex task solving with an outer planner / inner actor architecture, a dispatcher that spawns specialised sub-agents, a sandboxed To…