For a framework for orchestrating multiple AI agents, the strongest matches are foundationagents/metagpt (MetaGPT is a dedicated multi-agent orchestration framework that coordinates), cline/cline (Cline is a multi-agent orchestration engine that enables teams) and alibaba/spring-ai-alibaba (Spring AI Alibaba is a Java-based multi-agent orchestration framework). agentscope-ai/agentscope and langchain-ai/langchain round out the shortlist. Each is ranked by relevance to your query, popularity and recent activity.
These frameworks provide infrastructure for coordinating autonomous agents to collaborate on complex, multi-step technical tasks.
MetaGPT is an agentic workflow engine and multi-agent orchestration framework designed to automate complex software engineering and data analysis tasks. It functions as an automated software factory that transforms high-level natural language requirements into functional web applications, technical documentation, and production-ready code. By utilizing a runtime environment that manages the lifecycle of specialized agents, the platform bridges the gap between user intent and finished software components. The system distinguishes itself through role-based agent orchestration and dynamic task d
MetaGPT is a dedicated multi-agent orchestration framework that coordinates specialized agents through role-based orchestration, dynamic task decomposition, and shared memory, directly matching the need for agent-to-agent communication, planning, and parallel execution in an automated software engineering context.
Cline is an extensible agent runtime and multi-agent orchestration engine designed to automate complex software engineering workflows. It functions as an integrated development environment extension that bridges strategic task planning with autonomous execution, allowing users to manage multi-step projects through human-in-the-loop oversight or independent agent operation. The platform distinguishes itself by enabling the creation of specialized agent teams that share a common state and coordinate through a centralized task manager. It enforces project-specific architectural guidelines and co
Cline is a multi-agent orchestration engine that enables teams of specialized agents to share state and coordinate through a centralized task manager, with built-in task decomposition, tool execution, and human-in-the-loop oversight, directly matching your search for a full-featured orchestration framework.
This project is a Java-based framework integration that provides an AI agent runtime, a graph-based AI workflow engine, and an LLM orchestration framework for Spring applications. It enables the development of stateful autonomous agents and the implementation of retrieval-augmented generation systems using document processing and vector databases. The framework distinguishes itself through a graph-based workflow runtime for designing complex AI pipelines with conditional routing and persistent state. It supports multi-agent orchestration via service-discovery coordination and provides human-i
Spring AI Alibaba is a Java-based multi-agent orchestration framework that provides a graph-based workflow engine, service-discovery coordination, persistent memory, tool calling, parallel execution, and human-in-the-loop workflows—directly meeting the need for a platform to coordinate multiple AI agents on complex tasks.
Agentscope is a comprehensive toolkit for developing and orchestrating autonomous multi-agent systems. It provides a unified framework for building agents that can reason, execute tools, and manage memory, enabling the creation of complex, collaborative workflows where multiple specialized agents interact to solve multi-step objectives. The platform distinguishes itself through a robust orchestration engine that supports both sequential and concurrent agent pipelines. It utilizes a centralized event bus for real-time telemetry, allowing developers to track agent reasoning, tool usage, and sys
Agentscope is a comprehensive Python toolkit for building and orchestrating multi-agent systems with agent communication, tool use, memory, and concurrent execution, directly matching the need for a collaborative multi-agent orchestration framework.
LangChain is an orchestration framework designed for building, managing, and deploying applications powered by large language models. It provides a unified integration layer that normalizes disparate model provider APIs into a consistent set of primitives, enabling developers to build complex, multi-step AI workflows that manage state, memory, and tool execution. The project distinguishes itself through a durable execution runtime that maintains persistent state across long-running processes by checkpointing progress to external storage. It models agent workflows as directed graphs, allowing
LangChain (with LangGraph) is a comprehensive orchestration framework for building multi-agent LLM systems, supporting agent-to-agent communication via directed graphs, task planning, shared memory, tool calling, and human-in-the-loop oversight—exactly what you need for coordinating multiple AI agents on complex tasks.
AIOS is an LLM agent operating system and orchestration kernel designed to manage memory, resource scheduling, and tool execution for multiple autonomous AI agents. It serves as a comprehensive framework for developing and deploying agents, featuring a dedicated resource manager that coordinates model backends, GPU memory, and isolated kernel instances. The system distinguishes itself through a semantic memory engine that uses vector search and autonomous clustering for long-term knowledge management, and a semantic file system that allows users to control computer files and system operations
AIOS is an LLM agent operating system and orchestration kernel that manages memory, resource scheduling, and tool execution for multiple autonomous agents, with a semantic memory engine for shared context and support for distributed execution—making it a comprehensive framework that covers most of the requested coordination features.
Qwen-Agent is a development framework for building autonomous software applications that leverage large language models to plan, reason, and execute complex tasks. It functions as an orchestration engine that enables models to interact with external APIs, manage persistent memory, and maintain context across multi-step workflows. The framework distinguishes itself through a multi-agent collaboration platform that allows independent agent instances to exchange structured messages and delegate sub-tasks to one another. By utilizing iterative reasoning loops and dynamic prompt injection, the sys
Qwen-Agent is explicitly a multi-agent collaboration platform that enables agents to exchange messages, delegate sub-tasks, manage persistent memory, and integrate external tools—directly matching your need for orchestrated multi-agent coordination.
This project is a comprehensive framework for building and managing autonomous agent systems. It provides a unified architecture for orchestrating multi-agent societies, where specialized agents collaborate through roleplay to decompose and solve complex tasks. The system integrates language models with external environments, enabling agents to perform real-world actions through a standardized tool-calling abstraction layer. The framework distinguishes itself through its focus on iterative reasoning and data reliability. It employs automated feedback loops to refine agent outputs and self-eva
CAMEL is a comprehensive framework purpose-built for multi-agent societies where specialized agents collaborate through roleplay to decompose and solve complex tasks, with built-in tool calling and iterative reasoning—exactly the kind of orchestration platform this search targets.
LobeHub is a comprehensive multi-agent orchestration platform designed for building, configuring, and deploying specialized AI agents. It provides a unified chat-based gateway that allows users to manage autonomous agent teams across web, desktop, and mobile environments. By utilizing a framework that supports persistent memory and granular tool integration, the platform enables the execution of complex, multi-step workflows and domain-specific tasks. The platform distinguishes itself through an interactive artifact renderer that injects dynamic, visual UI elements directly into the chat stre
LobeHub is explicitly a multi-agent orchestration platform for building and deploying agent teams with persistent memory, tool integration, and complex multi-step workflows, directly matching the need for coordinated agent communication and task execution.
Nexent is an enterprise AI control plane and LLM agent orchestration platform. It provides a zero-code environment for designing, deploying, and managing production AI agents through a multi-agent collaboration framework that coordinates specialized autonomous agents using standardized messaging protocols. The platform integrates the Model Context Protocol to connect agents with external tools, plugins, and services via a universal communication interface. It further distinguishes itself with a dedicated RAG knowledge base manager that imports unstructured documents and utilizes hybrid search
Nexent is an enterprise multi-agent orchestration platform with zero-code design, standardized messaging for agent communication, MCP integration for tool calling, and a RAG knowledge base for shared context, directly meeting the need for coordinating multiple AI agents on complex tasks.
Eigent is a comprehensive platform for developing, configuring, and orchestrating autonomous AI agents. It functions as an agent development environment and workflow automation engine, enabling users to build modular agents equipped with custom toolsets, domain-specific skill packages, and external API connections to perform targeted operational tasks. The framework distinguishes itself through a robust multi-agent orchestration layer that coordinates teams of specialized agents to execute complex workflows. By utilizing hierarchical task decomposition, the system breaks high-level goals into
Eigent is a dedicated multi-agent orchestration platform with hierarchical task decomposition, agent-to-agent coordination, tool integration, and human-in-the-loop controls, squarely meeting the need for coordinating AI agents on complex workflows.
CrewAI is a multi-agent orchestration framework designed for building autonomous systems that execute complex, multi-step workflows. It provides a development platform where specialized agents are defined with specific roles, goals, and tool sets to perform tasks collaboratively. By leveraging a declarative workflow engine, the system manages task dependencies, state transitions, and execution logic, allowing for the creation of structured, stateful sequences of operations. The framework distinguishes itself through its hierarchical management capabilities, which utilize manager agents to coo
CrewAI is a dedicated multi-agent orchestration framework that lets you define specialized agents with roles, tools, and tasks, then manages their collaborative workflows, task dependencies, and shared state—exactly the platform you need for coordinating multiple AI agents, with support for planning, communication, and human oversight.
PraisonAI is an autonomous AI agent platform that coordinates multiple LLM-powered agents for research, planning, and execution of complex workflows. It functions as a multi-agent orchestration framework, a workflow builder, and a Model Context Protocol server, while also providing retrieval-augmented generation through vector knowledge bases. Agents can interact via CLI, web, or standardized protocols with sandboxed code execution. The platform distinguishes itself with a rich set of agent communication protocols, including A2A, REST, WebSocket, voice and telephony integration, and MCP, allo
PraisonAI is a multi-agent orchestration platform that coordinates LLM-powered agents for complex workflows, supporting agent-to-agent communication, task decomposition, tool execution, and a range of integration protocols—making it a comprehensive fit for coordinating multiple AI agents on complex tasks.
Goose is an extensible agentic AI platform designed for autonomous task orchestration and developer-centric assistance. It provides a workflow engine that manages complex, multi-step objectives by delegating tasks to specialized subagents, all while maintaining stateful session continuity. The system is built to integrate directly into terminal and coding environments, allowing for automated file manipulation and context-aware interaction. The platform distinguishes itself through a secure, sandboxed runtime environment that enforces granular permission controls and policy-driven guardrails.
Goose is a multi-agent orchestration platform with a workflow engine that delegates complex tasks to specialized subagents, maintains stateful session continuity, and enforces policy-driven guardrails—directly matching the need for agent-to-agent coordination, task decomposition, tool integration, and human oversight.
The agent-framework is an LLM agent orchestration framework and multi-agent workflow engine designed for building autonomous AI agents. It provides a tool integration layer for binding external functions, APIs, and sandboxed code as executable tools for language models. The framework distinguishes itself through a graph-based system for designing sequential and parallel task flows, featuring state management and checkpointing for long-running processes. It implements comprehensive conversational state management and an observability suite that uses telemetry to trace execution flows and monit
Microsoft Agent Framework is a multi-agent orchestration platform with graph-based workflow design, tool integration, and state management, directly matching the need to coordinate AI agents on complex tasks.
Langroid is a multi-agent orchestration framework and tool integration suite designed for building complex AI applications. It serves as a multi-modal integration layer that connects diverse local and remote language models with an agentic retrieval-augmented generation system. The project distinguishes itself through a collaborative message-exchange paradigm, allowing specialized agents to delegate tasks hierarchically and coordinate via structured communication. It features an advanced state management system for conversational AI, including the ability to rewind and prune conversation hist
Langroid is explicitly a multi-agent orchestration framework with collaborative message-passing, hierarchical task delegation, structured communication, advanced state management, and tool/function calling, directly matching the core need for coordinating multiple AI agents.
This project is a Python framework for building autonomous, event-driven agent systems. It provides a unified runtime for orchestrating multi-agent workflows, managing persistent conversation state, and executing code within secure, isolated sandbox environments. The framework is designed to handle complex task delegation, allowing agents to invoke other agents as tools while maintaining context across multi-turn interactions. The framework distinguishes itself through its deep integration with the Model Context Protocol, enabling agents to connect to external data sources and remote services
OpenAI Agents SDK is a Python framework specifically built for orchestrating multi‑agent workflows, with built‑in agent‑to‑agent delegation, persistent conversational context, and tool calling via the Model Context Protocol — directly addressing the need for coordinating multiple AI agents on complex tasks.
The BeeAI Framework is an LLM agent framework and multi-agent orchestration engine used to build autonomous agents that coordinate reasoning, tool execution, and complex workflows. It functions as a structured AI output controller and RAG integration library, providing a unified interface to manage multiple language model providers. The framework is distinguished by its implementation of the Model Context Protocol, allowing agents, tools, and models to be shared between different AI platforms and hosted as agentic tooling servers. It enables the design of collaborative agent teams through dec
The BeeAI Framework is a multi-agent orchestration engine that enables building collaborative agent teams with tool execution, reasoning coordination, and shared memory, exactly matching the search for a platform to coordinate multiple AI agents on complex tasks.
This project provides a comprehensive framework for building, deploying, and orchestrating autonomous agents within a decentralized network. It serves as a collection of patterns and examples for developing intelligent software entities capable of performing complex tasks, making decisions, and interacting with other agents to achieve shared goals. The framework distinguishes itself through its focus on multi-agent orchestration and decentralized communication. It enables the coordination of specialized agent teams that collaborate on workflows through structured messaging protocols, allowing
This repository provides a framework for building and orchestrating autonomous agents in a decentralized network, with agent-to-agent communication and workflow coordination, fitting the multi-agent orchestration category, though specific features like task decomposition and human-in-the-loop are not explicitly covered.
Eino is an AI agent development kit and LLM application framework designed for building autonomous agents and orchestrating complex language model workflows. It serves as a multi-agent orchestration engine and workflow orchestrator, providing a graph-based execution model to route data between models, tools, and retrievers. The framework distinguishes itself through a robust set of multi-agent coordination patterns, including supervisor-led management, sequential flows, and autonomous reasoning loops like ReAct. It features advanced agent execution controls such as active turn preemption, che
Eino is explicitly described as a multi-agent orchestration engine and LLM application framework with graph-based execution, multi-agent coordination patterns (supervisor-led, sequential, ReAct), and advanced execution controls, directly matching the need for coordinating multiple AI agents and supporting communication, planning, tool use, and human oversight.
This framework provides a development environment for building collaborative systems where autonomous agents interact to solve complex tasks through conversational workflows. It functions as a conversational workflow engine and event-driven runtime, coordinating multi-step processes by translating high-level goals into structured dialogue sequences between specialized agents. The system distinguishes itself through its message-passing orchestration, which manages state transitions and task delegation between independent participants. It supports dynamic conversation state management to provid
AutoGen is a framework purpose-built for multi-agent orchestration, enabling agent-to-agent communication, task decomposition via conversational workflows, shared context, tool calling, and human-in-the-loop oversight, making it a direct and comprehensive answer to this search.
Oh-my-opencode is an autonomous software engineering platform designed to automate complex coding tasks through the orchestration of specialized AI agents. It manages end-to-end development workflows by coordinating teams of agents that perform parallel execution, strategic planning, and automated code generation. The system ensures high-precision refactoring by utilizing a hash-anchored modification engine, which verifies file integrity through cryptographic line references before applying any changes. The platform distinguishes itself through a rigorous planning-first methodology, requiring
Oh-my-opencode is an autonomous software engineering platform that orchestrates teams of specialized AI agents for complex coding tasks, supporting parallel execution, strategic planning, and automated code generation — exactly the multi-agent coordination this search targets.
MetaGPT is an agentic workflow orchestrator and multi-agent framework designed to transform natural language requirements into complete software deliverables. It functions as an AI software engineering suite that automates the creation of technical documentation, data structures, and source code by treating natural language as a programming environment. The system distinguishes itself by assigning professional roles to large language models, creating specialized agent teams that collaborate through a shared communication structure. It utilizes standard operating procedures to convert organiza
MetaGPT is a multi-agent orchestration framework that assigns professional roles to LLM agents, enabling them to collaborate through shared communication for task decomposition and automated software engineering workflows, directly matching the need for coordinating multiple agents with planning and tool use.
LangGraph is a framework for building stateful, multi-step agentic workflows by modeling application logic as a directed graph. It provides a runtime environment where complex tasks are orchestrated through interconnected nodes and edges, allowing developers to manage state transitions, persistent memory, and control flow across long-running automated processes. The platform distinguishes itself through its native support for human-in-the-loop automation, enabling developers to define breakpoints that pause execution for manual review, modification, or approval. It also features checkpoint-ba
LangGraph is a graph-based framework for orchestrating multi-agent workflows with built-in state management, human-in-the-loop breakpoints, and support for tool calling and parallel execution—exactly what you need for coordinating multiple AI agents.
This is an LLM agent framework and symbolic learning system designed for building self-evolving autonomous agents. It functions as a computational graph orchestrator that organizes agent interactions and tool sequences as a trainable graph of nodes. The framework focuses on data-centric agent optimization, allowing agent pipelines and prompts to be upgraded through data-driven training rather than manual engineering. It utilizes a symbolic learning process that applies language-based loss and textual reflections to refine the operational logic and symbolic components of an agent. The system
aiwaves-cn/agents is a computational graph orchestrator for multi-agent systems that explicitly supports agent interactions and tool sequences as trainable nodes, squarely fitting the search for a multi-agent orchestration framework and covering agent communication, tool calling, and planning via its graph structure.
ChatDev is an automated software engineering platform that orchestrates the end-to-end development lifecycle through a multi-agent framework. It functions as a programmable engine that coordinates specialized autonomous agents to handle design, coding, testing, and documentation tasks by transitioning through predefined phases of a software project. The system distinguishes itself by using role-based agent specialization to simulate a professional engineering team, assigning distinct personas and knowledge bases to individual agents. It employs prompt-driven task decomposition to break high-l
ChatDev is a multi-agent orchestration platform built specifically for automating software development, coordinating specialized agents through predefined phases with task decomposition and role-based collaboration, making it a clear fit for coordinating AI agents on complex tasks, though its focus on software engineering may limit generality and human-in-the-loop features.
Openclaw is a platform for managing agent execution environments, providing the infrastructure to control agent lifecycles, session state, and workspace persistence. It features a centralized gateway that handles model loops, tool invocation, and streaming events, while supporting multi-agent routing and persistent memory management. The system is designed to normalize tool execution signatures and provide a standardized interface for cross-provider compatibility. The platform includes extensive developer tooling, such as a command-line interface for workspace management, diagnostic logging,
Openclaw is a TypeScript platform for managing multi-agent execution environments with centralized routing, persistent memory, and tool invocation, which fits the core need for coordinating multiple AI agents; it may not explicitly cover task decomposition or human-in-the-loop oversight but squarely belongs to the multi-agent orchestration category.
UFO is a multi-device task orchestrator and LLM agent orchestration framework designed to decompose natural language requests into executable task graphs. It functions as a cross-platform UI automation tool capable of performing interactions on Windows and mobile devices while routing tasks to distributed agents based on their hardware and software capabilities. The system is distinguished by its RAG-enhanced agent architecture, which integrates external documentation and previous execution traces to improve decision-making. It employs a hybrid UI detection approach that combines computer vis
UFO is a multi-device task orchestrator that decomposes natural language requests into executable task graphs and routes them across distributed LLM agents, covering agent communication, task decomposition, shared memory via RAG, and tool calling — though its focus on UI automation on Windows and mobile devices makes it narrower than a general multi-agent orchestration platform.
GPT Researcher is an autonomous agent framework designed to automate the process of gathering, synthesizing, and documenting information from diverse web and local sources. It functions as a research-oriented execution environment that orchestrates specialized agents to perform complex, multi-branch research tasks, transforming raw data into structured, factual, and cited reports. The project distinguishes itself through a graph-based orchestration layer that manages state transitions and information flow between specialized agents. It employs recursive tree-search execution to explore comple
GPT Researcher orchestrates multiple specialized agents via a graph-based state machine for research tasks, making it a genuine multi-agent orchestration framework even though its scope is concentrated on automated research rather than general-purpose coordination.
Agent Zero is an LLM agent framework and multi-agent orchestrator that provides an AI-powered interface for operating system tasks. It functions as a containerized AI workspace, allowing large language models to interact with a filesystem and terminal within an isolated Linux environment. The system distinguishes itself through a hierarchical orchestration model that decomposes complex goals by spawning specialized sub-agents to collaborate and consolidate results. It features a plugin-based architecture for extending capabilities via a community plugin hub, a custom skills system, and extern
Agent Zero is an LLM-based multi-agent orchestrator with hierarchical task decomposition and plugin-based tool integration, directly addressing the need for a platform that coordinates multiple AI agents on complex tasks.
mcp-agent is a framework for building AI agents that integrate with Model Context Protocol servers to execute tools and access data. It functions as a multi-agent orchestrator and protocol-compliant server, enabling the creation of agents that can discover and invoke tools from connected external servers. The project distinguishes itself through a durable workflow engine that supports long-running tasks capable of pausing, resuming, and surviving restarts. It implements complex orchestration patterns, including iterative evaluator-optimizer loops, hierarchical workflow nesting, and specialist
mcp-agent is a framework that explicitly calls itself a multi-agent orchestrator, enabling agents to discover and invoke tools via the Model Context Protocol and supporting durable, long-running workflows with nested orchestration patterns—exactly the kind of coordination you are looking for, though it does not emphasize human-in-the-loop or shared memory features.
PentestGPT is an autonomous security testing framework that leverages large language models to plan, execute, and coordinate end-to-end penetration testing engagements. By functioning as an autonomous agent, the system automates the entire testing lifecycle, from initial reconnaissance and vulnerability analysis to the generation of custom exploits and the execution of post-exploitation tasks. The platform distinguishes itself through a multi-agent orchestration system that coordinates specialized AI agents to collaborate on complex, multi-stage attack chains. It integrates multimodal context
PentestGPT is a multi-agent orchestration framework that coordinates specialized AI agents for complex penetration-testing tasks, squarely matching the category, though its domain is security testing rather than a general-purpose agent coordination platform.
FinRobot is an AI-powered financial analysis framework that coordinates multiple specialized agents to automate equity research, financial analysis, and investment risk assessment. At its core, it functions as a multi-agent orchestration system where a director and task manager allocate financial tasks to the most suitable large language models based on performance metrics and task requirements. The framework distinguishes itself through its ability to execute complex multi-step financial workflows by routing tasks through perception, reasoning, and action modules. It generates professional e
FinRobot is a multi-agent orchestration framework that coordinates specialized agents for financial analysis using a director and task manager, fitting the core intent but limited to the finance domain and not covering all requested features like human oversight.
TradingAgents is an autonomous financial research and simulation framework that coordinates specialized agents to analyze market data and execute investment strategies. The system functions as a multi-agent debate environment where independent units critique financial insights through structured, adversarial reasoning to improve decision accuracy and mitigate investment risks. The platform distinguishes itself through a risk-gated transaction pipeline that validates all proposed financial actions against market volatility and liquidity constraints before execution on a simulated exchange. To
TradingAgents is a multi-agent orchestration framework that coordinates specialized AI agents in a structured adversarial debate and risk-gated pipeline, making it a domain-specific but genuine fit for coordinating multiple agents on complex tasks.
Paseo is an LLM coding agent orchestrator and multi-agent workflow manager designed to coordinate multiple AI agents across isolated git worktrees. It provides a unified control interface for managing these agents and their associated environments to execute complex programming tasks. The system distinguishes itself through a remote agent daemon that enables secure access to local coding agents via encrypted relays. It employs a git worktree environment manager to isolate parallel tasks into dedicated directories and branch-based server URLs, preventing file collisions and network port confli
Paseo is an orchestrator and workflow manager that coordinates multiple AI agents across isolated environments for complex programming tasks, covering agent communication, task scheduling, and distributed execution—exactly the kind of multi-agent coordination framework this search is after.
This project is an AI content automation pipeline and LLM agent orchestration framework. It provides a system for generating research-backed text, images, and videos, and scheduling their distribution to social platforms. The framework allows for the development of specialized AI agents and custom tool servers. These servers expose capabilities such as video editing and story generation as API endpoints, enabling agents to execute complex tasks through a combination of AI models and custom tooling. The system covers automated content creation across text, image, and video media, utilizing hu
This repository is a multi-agent orchestration framework focused on AI content automation, allowing you to coordinate specialized agents and custom tool servers for tasks like text, image, and video generation, which directly matches the request for a platform to coordinate multiple AI agents.
AgenticSeek is a multi-agent orchestration system designed to decompose complex user objectives into granular, actionable tasks. By coordinating a team of specialized autonomous workers, the platform manages end-to-end workflows, ensuring that each component of a project is assigned to the most capable agent for execution. The system operates as a local-first runtime, executing all artificial intelligence models directly on user hardware to maintain data sovereignty and privacy. It integrates a browser automation engine for autonomous web research and interaction, alongside a sandboxed enviro
AgenticSeek is a multi-agent orchestration platform that decomposes complex objectives into tasks and coordinates specialized agents, fitting the search for an agent coordination framework; however, features like shared memory and human-in-the-loop oversight are not clearly indicated in the available evidence.
Swarm is a framework for building conversational systems that coordinate multi-agent workflows. It functions as an orchestration engine that manages persistent, multi-turn dialogues by routing tasks between specialized agents and executing local functions. The system is designed to handle complex, multi-step processes by maintaining shared state and context across agent interactions. The framework distinguishes itself through its approach to dynamic task delegation and execution control. It enables agents to hand off tasks to one another by returning agent objects, allowing for modular, domai
Swarm is a Python framework designed to coordinate multi-agent conversations by routing tasks between specialized agents and maintaining shared state, which directly addresses the core need for agent-to-agent communication and task orchestration, though it may not fully cover parallel execution or built-in human oversight loops.
TaskWeaver is an LLM agent framework that interprets natural language requests and executes them as Python code, SQL queries, or shell commands. It functions as a conversational code interpreter that maintains stateful data structures across turns, generating executable code from user prompts within a session-based environment. The system is designed as a self-hosted AI agent platform that can be deployed in Docker, managing sessions and providing a web UI for data analytics and automation tasks. The framework distinguishes itself through a role-based multi-agent architecture that divides the
TaskWeaver is a role-based multi-agent framework for LLM-powered conversational code interpretation, which fits the multi-agent orchestration category, but its focus on code execution and session-based interaction means it does not fully address the required features like task decomposition planning, parallel execution, or human-in-the-loop oversight.
CAMEL is a framework dedicated to multi-agent systems and agent-to-agent communication, making it a genuine candidate for orchestrating multiple AI agents, though the evidence doesn't confirm every requested feature like shared memory or human-in-the-loop oversight.
This project is a framework for developing and orchestrating autonomous software agents within JVM-based applications. It provides a toolkit for embedding artificial intelligence directly into business logic, enabling agents to perform complex tasks through dynamic, goal-oriented planning rather than rigid state machines. By leveraging declarative annotations, the framework allows developers to define agent capabilities and integrate them into existing object-oriented domain models. The framework distinguishes itself through a vendor-neutral abstraction layer that allows for the seamless swap
embabel/embabel-agent is a Kotlin-based multi-agent orchestration framework for the JVM, which matches the intent for coordinating multiple AI agents, though the brief description does not confirm all the specific features like shared memory or human-in-the-loop oversight.
A2A is a standardized framework designed to enable interoperability, discovery, and orchestration among independent artificial intelligence agents. It provides a common communication protocol that allows heterogeneous agents to exchange data, verify identities, and collaborate across diverse programming languages and computing environments. By establishing a unified messaging standard, the project facilitates the creation of complex, multi-agent workflows where tasks are routed and managed between specialized services. The project distinguishes itself through a capability-based architecture t
A2A is a standardized framework for orchestrating independent AI agents through a common communication protocol, task routing, and discovery, which makes it a genuine multi-agent orchestration platform; while it may not include built-in shared memory or human-in-the-loop oversight, its core purpose aligns directly with your search.
| Repository | Stars | Language | License | Last push |
|---|---|---|---|---|
| foundationagents/metagpt | 68.8K | Python | MIT | |
| cline/cline | 63.8K | TypeScript | Apache-2.0 | |
| alibaba/spring-ai-alibaba | 8.4K | Java | apache-2.0 | |
| agentscope-ai/agentscope | 26.9K | Python | Apache-2.0 | |
| langchain-ai/langchain | 139.5K | Python | MIT | |
| agiresearch/aios | 5.2K | Python | other | |
| qwenlm/qwen-agent | 13.3K | Python | apache-2.0 | |
| camel-ai/camel | 17.3K | Python | Apache-2.0 | |
| lobehub/lobehub | 78.7K | TypeScript | NOASSERTION | |
| modelengine-group/nexent | 5.3K | Python | MIT |