> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agentscope.io/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> For AgentScope Python, use https://docs.agentscope.io/stable/en/index for new projects. For existing projects, check the installed agentscope version and use matching versioned documentation.
> The /latest/ alias points to the newest documentation and may move ahead of /stable/ when a development version exists. Do not mix AgentScope 1.x and 2.x APIs.
> State the AgentScope version when providing installation commands or code examples. ReMe uses its own continuously updated /reme/latest/ documentation.

# FAQ

> Find answers to common questions about using AgentScope 2.0.

Find setup guidance for AgentScope development, integrations, and service deployment.

> **Is AgentScope 2.0 compatible with 1.0?**
>
> No. AgentScope 2.0 changes the agent, message, event, tool, and state APIs. Existing applications need code changes; upgrading the package alone does not migrate them.
>
> Start new projects with 2.0. For existing applications, follow the [1.x to 2.x changes](https://docs.agentscope.io/en/versions/2.0.12dev/others/change-log.md) or keep using documentation matching the installed 1.x version.

> **Does AgentScope support sandboxed execution?**
>
> Yes. Sandboxed workspace backends include Docker, Bubblewrap, Apple Container, Kubernetes, E2B, Daytona, and OpenSandbox, among others. `LocalWorkspace` runs on the host and does not provide sandbox isolation.
>
> Workspaces manage the execution environment, MCP server lifecycles, skills, and context offloading. See [Workspaces](https://docs.agentscope.io/en/versions/2.0.12dev/building-blocks/workspace/overview.md) to choose a backend and [Workspace Management](https://docs.agentscope.io/en/versions/2.0.12dev/deploy/workspace-manager.md) to allocate workspaces across users, agents, and sessions.

> **How do I deploy an agent as a service with a web UI?**
>
> Use the built-in Agent Service and its matching web UI. Run the [backend example](https://github.com/agentscope-ai/agentscope/tree/main/examples/agent_service) and [web UI example](https://github.com/agentscope-ai/agentscope/tree/main/examples/web_ui) from the same checkout to try the application.
>
> Follow the [Agent Service setup guide](https://docs.agentscope.io/en/versions/2.0.12dev/deploy/agent-service.md#quickstart) for prerequisites and startup commands. You can also build your own frontend using the service's HTTP APIs and event streams.

> **Does AgentScope 2.0 support RAG and long-term memory?**
>
> Yes. [RAG](https://docs.agentscope.io/en/versions/2.0.12dev/building-blocks/rag.md) provides document parsing, chunking, embedding, and vector retrieval. [RAG Service](https://docs.agentscope.io/en/versions/2.0.12dev/deploy/rag.md) adds document management and indexing for hosted applications.
>
> [Long-term memory](https://docs.agentscope.io/en/versions/2.0.12dev/building-blocks/long-term-memory.md) supports file-based agentic memory, ReMe, and Mem0 through middleware. Use RAG to retrieve knowledge and long-term memory to retain information across sessions; both can be used together.

> **Do I have to use Qwen or DashScope?**
>
> No. AgentScope supports model APIs including OpenAI, Anthropic, Gemini, DashScope, and Ollama. Choose a model class and matching credentials; available features depend on the selected model and API.
>
> See [Model Configuration](https://docs.agentscope.io/en/versions/2.0.12dev/building-blocks/agent/configure-agent.md) and [Chat Models](https://docs.agentscope.io/en/versions/2.0.12dev/building-blocks/model/llm.md).

> **Does AgentScope support MCP and skills?**
>
> Yes. MCP (Model Context Protocol) connects agents to external tools through STDIO or HTTP. Skills provide instructions in `SKILL.md` files that agents read and follow using their available tools.
>
> Register them through the toolkit or manage them through a workspace. See [MCP](https://docs.agentscope.io/en/versions/2.0.12dev/building-blocks/tool/mcp.md) and [Skills](https://docs.agentscope.io/en/versions/2.0.12dev/building-blocks/tool/skill.md) for setup.

> **How do I build a multi-agent application?**
>
> You can compose agents in Python or use [Agent Team](https://docs.agentscope.io/en/versions/2.0.12dev/deploy/agent-team.md) for service-based collaboration. A leader creates workers, delegates tasks, and exchanges messages with them; each worker runs in its own session.
>
> Use teams when a task benefits from delegation or separate agent contexts. A single agent is sufficient when one model and toolkit can complete the task.

> **How do I build a multi-tenant, multi-session service?**
>
> Use Agent Service under `agentscope.app` to manage user-owned resources and persistent sessions. Storage backends include Redis and SQLAlchemy databases such as PostgreSQL, MySQL, and SQLite; workspace allocation can be configured per user, agent, or session.
>
> Integrate your own authentication to establish user identity. See [Agent Service](https://docs.agentscope.io/en/versions/2.0.12dev/deploy/agent-service.md) and [Workspace Management](https://docs.agentscope.io/en/versions/2.0.12dev/deploy/workspace-manager.md) for configuration.

> **Does AgentScope support A2A?**
>
> Yes, from version 2.0.8. `A2AAgent` connects to remote A2A agents and translates their responses into AgentScope messages and events; the remote service controls its own models and tools.
>
> See the [A2A guide](https://docs.agentscope.io/en/versions/2.0.12dev/building-blocks/a2a.md) and [client/server example](https://github.com/agentscope-ai/agentscope/tree/main/examples/a2a).

> **How do I approve tool calls or interrupt an agent?**
>
> Configure the [permission system](https://docs.agentscope.io/en/versions/2.0.12dev/building-blocks/permission-system/overview.md) to allow, deny, or request confirmation for tool calls. When confirmation is required, present the request to the user and return their decision through the [human-in-the-loop events](https://docs.agentscope.io/en/versions/2.0.12dev/building-blocks/agent/human-in-the-loop.md).
>
> To stop an ongoing run, use the separate [interruption flow](https://docs.agentscope.io/en/versions/2.0.12dev/building-blocks/agent/interrupt-agent.md).

> **How do I use AgentScope with an AI coding assistant?**
>
> Install the official [agentscope-skill](https://github.com/agentscope-ai/skills/tree/main/skills/agentscope-skill) to provide AgentScope guidance, API references, and examples. Give the assistant your installed SDK version and use the [documentation index](https://docs.agentscope.io/llms.txt) to find matching pages.
>
> Ask it to verify API names against that version and run the resulting example.

> **Are there implementations other than Python?**
>
> Yes. AgentScope also has [TypeScript](https://github.com/agentscope-ai/agentscope-typescript) and [Java](https://github.com/agentscope-ai/agentscope-java) implementations, each with its own repository and release schedule.
>
> Use the selected implementation's documentation and examples. Their APIs are not interchangeable; this documentation describes the Python SDK.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.