# agentscope-ai/agentscope

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/agentscope-ai-agentscope).**

16,395 stars · 1,468 forks · Python · apache-2.0

## Links

- GitHub: https://github.com/agentscope-ai/agentscope
- Homepage: https://doc.agentscope.io/
- awesome-repositories: https://awesome-repositories.com/repository/agentscope-ai-agentscope.md

## Topics

`agent` `chatbot` `large-language-models` `llm` `llm-agent` `mcp` `multi-agent` `multi-modal` `react-agent`

## Description

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 system performance. By employing a provider-agnostic interface, the framework abstracts diverse language model APIs, while its middleware-based execution hooks allow for the injection of custom logic to intercept, validate, or transform agent behavior at runtime.

Beyond core orchestration, the project includes extensive capabilities for tool integration, including dynamic schema parsing from function docstrings and support for secure, sandboxed code execution. It also features built-in support for retrieval-augmented generation, long-term memory management, and systematic performance evaluation, providing a complete environment for the lifecycle management of agentic applications.

The library is designed for extensibility, offering base classes for custom memory backends, prompt formats, and tool providers. It is distributed as a Python package, with documentation and interactive development tools available to assist in prototyping and managing multi-agent projects.

## Tags

### Artificial Intelligence & ML

- [Agentic LLM Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-llm-frameworks.md) — Provides a comprehensive toolkit for building LLM-powered agents with multimodal and streaming support.
- [Multi-Agent Orchestration Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/agent-orchestrators/multi-agent-orchestration-frameworks.md) — Orchestrates multi-agent systems with shared memory, reasoning, and tool execution capabilities.
- [Agentic Workflow Orchestration](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/orchestration-engines/ai-agent/agentic-workflow-orchestration.md) — Orchestrates complex multi-agent workflows through sequential and concurrent execution pipelines. ([source](https://doc.agentscope.io/tutorial/task_pipeline.html))
- [Model Provider Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/model-integration-serving/ai-model-orchestration/model-provider-integrations.md) — Provides a unified interface for connecting to and orchestrating multiple language model providers for reasoning and tool use. ([source](https://doc.agentscope.io/tutorial/task_model.html))
- [Agentic Workflow Engines](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-workflow-engines.md) — Defines and executes complex agent pipelines for automated reasoning and decision-making.
- [Model Provider Abstractions](https://awesome-repositories.com/f/artificial-intelligence-ml/model-provider-abstractions.md) — Abstracts diverse language model APIs into a unified interface for text generation, reasoning, and structured output formatting.
- [Multi-Agent Orchestration Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-agent-orchestration-systems.md) — Provides a comprehensive framework for orchestrating autonomous agents capable of reasoning, tool execution, and memory management. ([source](https://cdn.jsdelivr.net/gh/agentscope-ai/agentscope@main/README.md))
- [Conversational AI Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/conversational-voice-interaction/conversational-ai-agents.md) — Facilitates the construction of conversational agents capable of multimodal interactions, tool calling, and streaming. ([source](https://doc.agentscope.io/tutorial/task_realtime.html))
- [Agentic Workflow Automation](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-workflow-automation.md) — Orchestrates complex, multi-step agentic workflows through sequential and concurrent pipelines.
- [Workflow Orchestrators](https://awesome-repositories.com/f/artificial-intelligence-ml/workflow-orchestrators.md) — Structures complex multi-step tasks into sequential or concurrent execution chains to automate reasoning and decision-making processes.
- [Message-Passing Agent Orchestrators](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/orchestration-engines/ai-agent/multi-agent-coordination-systems/message-passing-agent-orchestrators.md) — Uses a unified message object structure to facilitate asynchronous data exchange and state persistence between autonomous agents.
- [Agent Delegation](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-delegation.md) — Provides mechanisms for agents to assign sub-tasks to specialized worker agents to complete complex objectives. ([source](https://doc.agentscope.io/tutorial/workflow_handoffs.html))
- [Agent Evaluation Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-evaluation-tools.md) — Executes systematic benchmarks against agent solutions to measure quality using custom metrics. ([source](https://doc.agentscope.io/tutorial/task_eval.html))
- [Agent Memory Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-memory-systems.md) — Maintains long-term state and context retention for autonomous agents across multi-turn interactions. ([source](https://doc.agentscope.io/))
- [Agentic Reasoning Loops](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-reasoning-loops.md) — Enables middleware-based injection into the reasoning-action loop to customize agent behavior. ([source](https://cdn.jsdelivr.net/gh/agentscope-ai/agentscope@main/README.md))
- [Agent Orchestrators](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/agent-orchestrators.md) — Manages agent lifecycles, reasoning loops, and multi-agent delegation strategies for complex workflows. ([source](https://doc.agentscope.io/tutorial/quickstart_key_concept.html))
- [Agent Tool Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/tool-use-and-execution/agent-tool-execution.md) — Invokes defined functions to allow agents to interact with external environments, retrieve information, or perform specific actions. ([source](https://doc.agentscope.io/))
- [External Tool Integration](https://awesome-repositories.com/f/artificial-intelligence-ml/external-tool-integration.md) — Enables agents to connect to and execute external tools and APIs to perform actions beyond native model capabilities. ([source](https://doc.agentscope.io/_sources/index.rst.txt))
- [Retrieval Augmented Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/language-model-orchestration/retrieval-augmented-generation.md) — Integrates knowledge retrieval into agent workflows to provide context-aware responses. ([source](https://doc.agentscope.io/_sources/index.rst.txt))
- [Multi-Agent Orchestration Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-agent-orchestration-frameworks.md) — Coordinates multiple agent instances within a shared environment to enable collaborative interactions and message broadcasting. ([source](https://doc.agentscope.io/tutorial/task_realtime.html))
- [RAG Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/rag-frameworks.md) — Provides base classes for implementing custom document readers and knowledge retrieval logic in RAG workflows. ([source](https://doc.agentscope.io/tutorial/task_rag.html))
- [Task Planning Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/task-planning-systems.md) — Decomposes complex objectives into sequences of manageable sub-tasks to support systematic agent execution and planning. ([source](https://doc.agentscope.io/tutorial/task_plan.html))
- [Long-term Memory Stores](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/memory-management-systems/long-term-memory-stores.md) — Provides persistent storage mechanisms for retaining context across multiple sessions and interactions. ([source](https://doc.agentscope.io/tutorial/quickstart_key_concept.html))
- [Concurrent Agent Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/orchestration-engines/ai-agent/multi-agent-coordination-systems/concurrent-agent-execution.md) — Supports running multiple autonomous agents simultaneously using asynchronous processing to improve workflow efficiency. ([source](https://doc.agentscope.io/tutorial/workflow_concurrent_agents.html))
- [Execution Hooks](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/orchestration-engines/ai-agent/runtime-execution-control/execution-message-injection/execution-hooks.md) — Injects custom logic into the agent reasoning loop to intercept, validate, or transform messages and tool calls at runtime.
- [Agent State Persistence](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-state-persistence.md) — Captures and restores the internal attributes of agents and memory components to support session continuity and recovery.
- [Agent Capability Extensions](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-capabilities-skills-tooling/agent-capability-extensions.md) — Allows injection of custom logic into agent functions to modify execution flow without altering core code. ([source](https://doc.agentscope.io/tutorial/task_agent.html))
- [Agent Skill Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-capabilities-skills-tooling/agent-skill-frameworks.md) — Manages collections of task-specific instructions injected into system prompts to enhance agent performance. ([source](https://doc.agentscope.io/tutorial/task_agent_skill.html))
- [Custom Agent Builders](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-development/custom-agent-builders.md) — Allows developers to define specialized agent behaviors by extending base classes with custom logic. ([source](https://doc.agentscope.io/tutorial/quickstart_agent.html))
- [Agent Streaming Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/agent-runtimes/agent-streaming-interfaces.md) — Converts agent-generated content into asynchronous generators for real-time processing of message chunks. ([source](https://doc.agentscope.io/tutorial/task_pipeline.html))
- [Agent Tool Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/tool-use-and-execution/agent-tool-integrations.md) — Provides a middleware layer for connecting agents to external tools via dynamic schemas.
- [External Knowledge Integrators](https://awesome-repositories.com/f/artificial-intelligence-ml/external-service-integrations/external-knowledge-integrators.md) — Empowers agents to dynamically query external knowledge bases as part of their reasoning process for retrieval-augmented generation. ([source](https://doc.agentscope.io/tutorial/task_rag.html))
- [Tool Calling](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/decoding-generation-controls/tool-calling.md) — Uses a standardized format for models to request tool execution and return results through unified data structures. ([source](https://doc.agentscope.io/tutorial/task_model.html))
- [Structured Output Enforcements](https://awesome-repositories.com/f/artificial-intelligence-ml/structured-output-enforcements.md) — Enforces predefined schemas on agent responses to ensure consistent, machine-readable output for programmatic use. ([source](https://doc.agentscope.io/tutorial/task_agent.html))
- [Tool Schema Definitions](https://awesome-repositories.com/f/artificial-intelligence-ml/tool-schema-definitions.md) — Extracts tool definitions and JSON schemas directly from function docstrings to enable seamless integration with language models. ([source](https://doc.agentscope.io/tutorial/task_tool.html))
- [Agent-to-Agent Communication](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-communication-protocols/agent-to-agent-communication.md) — Exchanges messages and tasks between different systems using standard communication protocols to ensure interoperability with external agents. ([source](https://doc.agentscope.io/tutorial/task_a2a.html))
- [Agent Memory Persistence](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-memory-persistence.md) — Maintains long-term state and continuity in agent sessions using developer-defined triggers. ([source](https://doc.agentscope.io/tutorial/task_long_term_memory.html))
- [Agent Memory Storage](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-memory-storage.md) — Supports custom memory backends by inheriting from base classes for proprietary database integration. ([source](https://doc.agentscope.io/tutorial/task_memory.html))
- [Tool Access Controls](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-capabilities-skills-tooling/agent-tooling/tool-access-controls.md) — Provides granular control over tool availability at the server or function level for secure agent interactions. ([source](https://doc.agentscope.io/tutorial/task_mcp.html))
- [Execution Interrupts](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/control-flow-and-workflows/execution-interrupts.md) — Enables graceful cancellation of ongoing agent tasks with support for custom post-processing routines. ([source](https://doc.agentscope.io/tutorial/task_agent.html))
- [Agent Routing Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/coordination-and-routing/agent-routing-frameworks.md) — Delegates incoming queries to specialized agents by wrapping them as executable tools for the routing model. ([source](https://doc.agentscope.io/tutorial/workflow_routing.html))
- [Parallel Tool Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/tool-use-and-execution/parallel-tool-execution.md) — Runs multiple asynchronous tool functions concurrently to reduce total processing time for complex agent tasks. ([source](https://doc.agentscope.io/tutorial/task_agent.html))
- [Chat Message Formats](https://awesome-repositories.com/f/artificial-intelligence-ml/chat-message-formats.md) — Converts conversation history into the specific schema required by model providers while optionally truncating content to fit token limits. ([source](https://doc.agentscope.io/tutorial/task_prompt.html))
- [Code Execution Environments](https://awesome-repositories.com/f/artificial-intelligence-ml/code-execution-environments.md) — Executes agent-driven code within secure, isolated environments. ([source](https://cdn.jsdelivr.net/gh/agentscope-ai/agentscope@main/README.md))
- [Context Injection](https://awesome-repositories.com/f/artificial-intelligence-ml/context-injection.md) — Attaches relevant knowledge to user prompts before processing to ensure agents have the necessary information for every interaction. ([source](https://doc.agentscope.io/tutorial/task_rag.html))
- [Conversation Memory Stores](https://awesome-repositories.com/f/artificial-intelligence-ml/conversation-memory-stores.md) — Persists message history across sessions to maintain context for multi-agent systems. ([source](https://doc.agentscope.io/tutorial/task_memory.html))
- [Conversational Session Management](https://awesome-repositories.com/f/artificial-intelligence-ml/conversational-session-management.md) — Isolates conversation history by tracking unique session identifiers to support concurrent interactions. ([source](https://doc.agentscope.io/tutorial/task_memory.html))
- [Embedding Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/embedding-generators.md) — Provides a unified interface for generating vector embeddings from text, images, or videos using multiple third-party providers. ([source](https://doc.agentscope.io/tutorial/task_embedding.html))
- [Human-in-the-Loop Workflows](https://awesome-repositories.com/f/artificial-intelligence-ml/human-in-the-loop-workflows.md) — Integrates human input into automated agent workflows to enable real-time collaboration and intervention. ([source](https://doc.agentscope.io/tutorial/workflow_conversation.html))
- [Multi-Agent Debate Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-agent-debate-frameworks.md) — Facilitates structured debate between agents to evaluate progress and reach consensus on complex tasks. ([source](https://doc.agentscope.io/tutorial/workflow_multiagent_debate.html))
- [Agent Execution Tracing](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-execution-tracing.md) — Provides real-time telemetry and visualization of agent reasoning and tool usage through a centralized event bus. ([source](https://doc.agentscope.io/tutorial/task_studio.html))
- [Agent Optimization](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-optimization.md) — Provides techniques for refining agent performance through strategic workflow configuration and optimization. ([source](https://doc.agentscope.io/tutorial/task_tuner.html))
- [Distributed Agent Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/coordination-and-routing/distributed-agent-systems.md) — Facilitates message exchange and task coordination between distributed agents.
- [External Server Connectivity](https://awesome-repositories.com/f/artificial-intelligence-ml/external-server-connectivity.md) — Establishes connections to remote servers using standard transport protocols to enable communication between agents and external tools. ([source](https://doc.agentscope.io/tutorial/task_mcp.html))
- [Task Offloaders](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-deployment-and-serving/local-and-on-device-inference/local-model-inference-servers/remote-inference-offloaders/task-offloaders.md) — Delegates long-running operations to background processes, resuming agent conversations automatically upon completion. ([source](https://cdn.jsdelivr.net/gh/agentscope-ai/agentscope@main/README.md))
- [Model Format Converters](https://awesome-repositories.com/f/artificial-intelligence-ml/model-format-converters.md) — Provides utilities for mapping internal message structures to the specific input formats required by various language model APIs. ([source](https://doc.agentscope.io/tutorial/quickstart_key_concept.html))
- [Multimodal Retrieval Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/multimodal-retrieval-systems.md) — Processes information from text and image sources to help agents answer queries based on diverse data formats. ([source](https://doc.agentscope.io/tutorial/task_rag.html))
- [Prompt Formatting](https://awesome-repositories.com/f/artificial-intelligence-ml/prompt-formatting.md) — Supports custom prompt formatting and message transformation strategies through extensible base classes. ([source](https://doc.agentscope.io/tutorial/task_prompt.html))
- [Reasoning Process Controllers](https://awesome-repositories.com/f/artificial-intelligence-ml/reasoning-workflows/reasoning-process-controllers.md) — Processes internal model thinking steps alongside final text output to support complex problem-solving workflows during agent interactions. ([source](https://doc.agentscope.io/tutorial/task_model.html))

### Software Engineering & Architecture

- [Agent Task Routers](https://awesome-repositories.com/f/software-engineering-architecture/model-routing-configurations/agent-task-routers.md) — Direct incoming queries to specific downstream agents by forcing the routing model to produce a structured data object defining the target. ([source](https://doc.agentscope.io/tutorial/workflow_routing.html))
- [Configuration-Driven Schemas](https://awesome-repositories.com/f/software-engineering-architecture/configuration-driven-schemas.md) — Parses function signatures and docstrings into structured schemas to enable dynamic tool discovery and invocation by language models.
- [Realtime Control Event Handlers](https://awesome-repositories.com/f/software-engineering-architecture/event-controllers/realtime-control-event-handlers.md) — Standardizes model-specific events into consistent messages for real-time frontend integration and monitoring. ([source](https://doc.agentscope.io/tutorial/task_realtime.html))
- [Execution Interrupts](https://awesome-repositories.com/f/software-engineering-architecture/execution-interrupts.md) — Provides mechanisms to intercept agent execution at runtime for user steering and custom interruption handling. ([source](https://doc.agentscope.io/tutorial/quickstart_agent.html))

### Development Tools & Productivity

- [Agentic Workflow Automations](https://awesome-repositories.com/f/development-tools-productivity/workflow-automation-tools/automation-execution-frameworks/automation-frameworks/agentic-workflow-automations.md) — Structures complex agent behaviors through pipelines and routing to automate multi-step reasoning and decision-making. ([source](https://doc.agentscope.io/))
- [Tool Execution Interceptors](https://awesome-repositories.com/f/development-tools-productivity/execution-middleware/tool-execution-interceptors.md) — Wraps tool calls in middleware to pre-process, validate, or transform execution inputs and outputs. ([source](https://doc.agentscope.io/tutorial/task_middleware.html))
- [Planning](https://awesome-repositories.com/f/development-tools-productivity/workflow-automation-tools/workflow-lifecycle-management/progress-tracking/planning.md) — Supports the creation and management of task plans to handle interruptions and prioritize urgent requests. ([source](https://doc.agentscope.io/tutorial/task_plan.html))
- [Event Bus Management](https://awesome-repositories.com/f/development-tools-productivity/debugging-profiling-testing/event-bus-management.md) — Provides a centralized event bus for real-time telemetry to track agent reasoning, tool usage, and system performance.
- [Execution Hooks](https://awesome-repositories.com/f/development-tools-productivity/execution-hooks.md) — Provides mechanisms to register and clear custom logic hooks for controlling agent behavior across scopes. ([source](https://doc.agentscope.io/tutorial/task_hook.html))

### Data & Databases

- [Agent State Persistence](https://awesome-repositories.com/f/data-databases/agent-state-persistence.md) — Captures and restores runtime data snapshots for agents and memory components to support stateful recovery. ([source](https://doc.agentscope.io/tutorial/quickstart_key_concept.html))
- [JSON Message Serializers](https://awesome-repositories.com/f/data-databases/data-serialization-formats/json-serialization/json-message-serializers.md) — Converts message objects to and from JSON format to facilitate storage, transmission, and persistence of communication history. ([source](https://doc.agentscope.io/tutorial/quickstart_message.html))
- [Multi-Tenant Data Management](https://awesome-repositories.com/f/data-databases/multi-tenant-data-management.md) — Provides service isolation to support multiple users and concurrent sessions within a single deployment. ([source](https://cdn.jsdelivr.net/gh/agentscope-ai/agentscope@main/README.md))
- [Result Persistence Layers](https://awesome-repositories.com/f/data-databases/result-persistence-layers.md) — Records performance data and execution trajectories in structured storage to track agent progress. ([source](https://doc.agentscope.io/tutorial/task_eval.html))

### System Administration & Monitoring

- [Agent Performance Monitoring](https://awesome-repositories.com/f/system-administration-monitoring/agent-performance-monitoring.md) — Tracks agent execution and system interactions to optimize performance and reliability. ([source](https://doc.agentscope.io/))
- [Event Monitoring Streams](https://awesome-repositories.com/f/system-administration-monitoring/event-monitoring-streams.md) — Exposes a unified event bus to track agent reasoning and tool usage in real-time. ([source](https://cdn.jsdelivr.net/gh/agentscope-ai/agentscope@main/README.md))
- [Monitoring and Observability](https://awesome-repositories.com/f/system-administration-monitoring/monitoring-and-observability.md) — Captures telemetry data across agents, models, and tools to visualize application performance. ([source](https://doc.agentscope.io/tutorial/task_tracing.html))
- [Activity Progress Monitors](https://awesome-repositories.com/f/system-administration-monitoring/activity-monitors/activity-progress-monitors.md) — Triggers hooks during plan state changes to enable real-time tracking of task execution status. ([source](https://doc.agentscope.io/tutorial/task_plan.html))
- [Observability Platform Log Exporting](https://awesome-repositories.com/f/system-administration-monitoring/monitoring-and-observability/observability-platforms/log-management-systems/log-management-services/observability-platform-log-exporting.md) — Forwards execution logs to external observability platforms for centralized analysis. ([source](https://doc.agentscope.io/tutorial/task_tracing.html))

### Content Management & Publishing

- [Conversation Formatters](https://awesome-repositories.com/f/content-management-publishing/content-processing-transformation/document-processing-conversion/document-processing-tools/format-conversion-toolkits/conversation-formatters.md) — Structures complex dialogue histories from multiple participants into unified message formats compatible with large language model input requirements. ([source](https://doc.agentscope.io/tutorial/workflow_conversation.html))

### Networking & Communication

- [Response Streaming](https://awesome-repositories.com/f/networking-communication/api-integration-frameworks/http-client-libraries/http-client-utilities/response-streaming.md) — Returns asynchronous generators that yield cumulative response chunks as they are produced by the model. ([source](https://doc.agentscope.io/tutorial/task_model.html))
- [Tool Response Streamers](https://awesome-repositories.com/f/networking-communication/api-integration-frameworks/http-client-libraries/http-client-utilities/response-streaming/tool-response-streamers.md) — Returns tool execution results incrementally using synchronous or asynchronous generators as they are produced. ([source](https://doc.agentscope.io/tutorial/task_tool.html))
- [Message Routing](https://awesome-repositories.com/f/networking-communication/message-routing.md) — Routes messages automatically between agents to eliminate manual passing within shared contexts. ([source](https://doc.agentscope.io/tutorial/workflow_conversation.html))

### Security & Cryptography

- [Isolated Execution Sandboxes](https://awesome-repositories.com/f/security-cryptography/application-and-system-security/sandbox-and-isolation/isolated-execution-sandboxes.md) — Runs tools and code in sandboxed environments to ensure security and resource separation. ([source](https://github.com/agentscope-ai/agentscope/blob/main/README_zh.md))
- [Workflow Session Persistence](https://awesome-repositories.com/f/security-cryptography/identity-access-management/session-management/stateful-session-persistence/messaging-session-persistence/workflow-session-persistence.md) — Resumes sessions across workflow executions to maintain continuity for agents and components. ([source](https://doc.agentscope.io/tutorial/task_state.html))

### Business & Productivity Software

- [Tool Group Configurators](https://awesome-repositories.com/f/business-productivity-software/group-management/tool-group-configurators.md) — Organizes collections of related tools into groups that can be activated or deactivated to control agent capabilities. ([source](https://doc.agentscope.io/tutorial/task_tool.html))

### Education & Learning Resources

- [Tool Use and Function Calling](https://awesome-repositories.com/f/education-learning-resources/technical-domain-education/ai-machine-learning-education/tool-use-and-function-calling.md) — Retrieves and executes functions from external servers by listing capabilities and accessing callable objects for use in automated workflows. ([source](https://doc.agentscope.io/tutorial/task_mcp.html))