AgentScope
Multi-agent framework from Alibaba (Tongyi)
AgentScope is a Python framework for agents and multi-agent systems from Alibaba. At its core is a ReAct agent with tool management for Python tools, MCP servers and skills, plus context compaction, RAG and long-term memory with backends such as Mem0 and ReMe. Multiple agents collaborate through workflows such as orchestrator-workers with handoffs, routing, debates and concurrent agents; in the Agent Service a leader agent spawns worker agents on demand (Agent Team), and remote agents are reachable via A2A. AgentScope Studio, tracing and evaluation are also included. The project is licensed under Apache-2.0.
Good fit if
Focus: Developer teams building multi-agent applications with their own serving layer, especially with Qwen and DashScope
- your project is about Task decomposition with orchestrator and workers, Debates and routing between agents or Realtime voice agents
- someone on your team writes code
Probably not if
- nobody on your team writes code (1/5 for use without developers)
Key figures
- Usable without developers
- 1/5
- Scalability
- 4/5
- Integrations
- 4/5
- Versioning
- 2/5
- Observability
- 4/5
Editorial rating on a scale from 1 to 5. Methodology
Fact sheet
- Category
- Developer
- Type
- Multi-agent framework from Alibaba (Tongyi)
- Licence
- Open Source (Apache-2.0)
- Pricing
- Open SourceFramework without license fee (Apache-2.0). Costs arise for the models used, for example via DashScope or other providers, and for your own infrastructure.
- Deployment
- Self-Hosted, Docker, Any
- Models
- DashScope (Qwen), OpenAI, Anthropic, Google Gemini, DeepSeek, Moonshot, Volcengine, xAI, Ollama
- RAG
- Yes
- Multi-Agent
- Yes
- SSO, roles (RBAC)
- SSO no, RBAC no
- Latest version
- 2.0.9 (28.09.2026)
- GitHub stars
- 33,036
Key features
- Orchestrator-workers, handoffs and Agent Team
- ReAct agent with MCP and skills
- Long-term memory (Mem0, ReMe) and RAG
- A2A and realtime voice agents
- AgentScope Studio, tracing and evaluation
- Agent Service with multi-tenancy and persistence
Typical use cases
- Task decomposition with orchestrator and workers
- Debates and routing between agents
- Realtime voice agents
- Agent services with a web UI
Market notes
Changes to AgentScope by email
We let you know when the status, pricing or license of AgentScope changes, together with the weekly market notes.
Implementation
Get AgentScope implemented
Free for you. Partners only pay for requests they accept.
Alternatives
Similar systems
Similar in category, features or use cases.
- DeveloperAG2AG2 is a Python framework for multi-agent systems that evolved from AutoGen and is maintained by volunteers from several organizations. Since version 1.0, multiple agents run via AG2 Network: a hub manages the registry, write-ahead log and audit trail, and agents communicate over typed channels (conversation, consulting, round-robin discussion, workflow with conditional handoffs). The classic API with ConversableAgent, Group Chat and Swarm moved to a separate package as AG2 Classic and is still maintained. AG2 is licensed under Apache-2.0; for organizations the website also lists the AG2 AgentOS runtime with access on request.View profile
- DeveloperCrewAICrewAI is a Python framework for teams of agents with defined roles, goals and tasks. Crews work through tasks sequentially or hierarchically, while Flows control event-driven, stateful processes. The framework is MIT licensed; for deployment, monitoring and management CrewAI offers the commercial platform CrewAI AMP.View profile
- DeveloperLangroidLangroid is a lightweight open source Python framework for applications built on LLM agents, developed by researchers from CMU and UW-Madison. Agents act as message transformers: a Task wraps an agent with instructions and orchestrates collaboration through hierarchical, recursive delegation to sub-tasks. For RAG there is the DocChatAgent with connections to vector databases such as Qdrant, Chroma, LanceDB or PGVector, and MCP tools can be integrated. Langroid is MIT licensed and works with commercial and local models.View profile
- DeveloperMicrosoft Agent FrameworkMicrosoft Agent Framework is Microsoft's open-source framework for agents and multi-agent workflows in Python and .NET. Version 1.0 shipped in April 2026 and is the unified successor of Semantic Kernel and AutoGen. A graph-based workflow engine supports branching, parallelism, checkpoints and human approvals; ready-made patterns exist for sequential, concurrent, handoff, group chat and Magentic-One orchestration. MCP and A2A are supported.View profile