经 AI Skill Hub 精选评估,AgentScope Go 获评「强烈推荐」。这款Agent工作流在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 8.0 分,适合有一定技术背景的用户使用。
AgentScope Go 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
AgentScope Go 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:go install(推荐) go install github.com/AlanFokCo/agentscope-go@latest # 方式二:从源码编译 git clone https://github.com/AlanFokCo/agentscope-go cd agentscope-go go build -o agentscope-go . # 方式三:下载预编译二进制 # 访问 Releases 页面下载对应平台二进制文件 # https://github.com/AlanFokCo/agentscope-go/releases
# 查看帮助 agentscope-go --help # 基本运行 agentscope-go [options] <input> # 详细使用说明请查阅文档 # https://github.com/AlanFokCo/agentscope-go
# agentscope-go 配置说明 # 查看配置选项 agentscope-go --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export AGENTSCOPE_GO_CONFIG="/path/to/config.yml"
<p align="center"> <img src="https://img.alicdn.com/imgextra/i1/O1CN01nTg6w21NqT5qFKH1u_!!6000000001621-55-tps-550-550.svg" alt="AgentScope" width="120" /> </p>
- Tool-using assistants: connect model calls to Go functions, manage context and request human confirmation for tool execution. Use AskUser to collect structured choices through your own frontend. - Multi-agent workflows: coordinate agents with pipelines, message routing and leader/worker teams. - Applications with memory: combine retrieval, conversation state and memory middleware with your own data sources. - Services and experiments: expose an HTTP service or browser UI, record model responses, evaluate runs and inspect traces.
Install the latest tagged release from the community module path. Applications using github.com/alanfokco/agentscope-go/v2 need to update their import prefix; see the module migration notes.
From a new directory:
mkdir agentscope-demo
cd agentscope-demo
go mod init example.com/agentscope-demo
go get github.com/agentscope-ai/agentscope-go/v2@latest
You need Go 1.25+ and, for the program below, an Anthropic API key and an available model ID. Other adapters are listed under Model providers.
Examples run from a repository checkout, separately from the application above. This worker-pool demo uses simulated jobs and needs no model API key:
git clone https://github.com/agentscope-ai/agentscope-go.git
cd agentscope-go
go run ./examples/agent_pool
Start with agent_v2 for function tools, model_call for direct model streaming, or webui for a browser interface. Check each example's source for its model choice, environment variables and required services or runtimes.
<details> <summary>Browse all examples</summary>
| Example | Demonstrates |
|---|---|
| [simple](examples/simple/) | A custom agent with a single model call |
| [agent_v2](examples/agent_v2/) | UnifiedAgent with a function tool |
| [react_tool](examples/react_tool/) | A custom FunctionTool |
| [react_builtin_tools](examples/react_builtin_tools/) | The built-in coding toolkit |
| [streaming](examples/streaming/) | Agent lifecycle events and provider text deltas |
| [ask_user](examples/ask_user/) | Structured questions with a simulated model and host answer |
| [console](examples/console/) | Terminal chat and tool-call confirmation |
| [managed_routing_eval](examples/managed_routing_eval/) | Managed fixed/rules/classifier comparisons, offline fixtures and opt-in live pilot |
| [managed_routing](examples/managed_routing/) | Managed pools, classification and fallback with offline fixtures |
| [managed_task](examples/managed_task/) | Fixed-model managed text execution with a local HTTP fixture |
| [classifier](examples/classifier/) | Typed classification with offline fake results and attempt accounting |
| [model_call](examples/model_call/) | Direct model streaming, tool calls and structured output |
| [structured_output](examples/structured_output/) | Structured output through tool calling |
| [multi_provider](examples/multi_provider/) | Provider configuration and model cards |
| [multimodal](examples/multimodal/) | Image input using URLs and base64 data |
| [multiagent](examples/multiagent/) | Multi-agent conversation |
| [multiagent_multimodal](examples/multiagent_multimodal/) | Multi-agent conversation with image input |
| [openai_response](examples/openai_response/) | OpenAI Responses API |
| [middleware](examples/middleware/) | Model-call and tool-execution hooks |
| [permission](examples/permission/) | Tool permission modes |
| [tracing](examples/tracing/) | Tracing with LoggerTracer |
| [tracing_otlp](examples/tracing_otlp/) | An OTLP integration setup pattern |
| [agent_loop](examples/agent_loop/) | Loop configuration and metrics |
| [embedding](examples/embedding/) | Text embeddings and similarity |
| [long_term_memory](examples/long_term_memory/) | Long-term memory middleware |
| [agentic_memory](examples/agentic_memory/) | File-based memory and MEMORY.md |
| [rag_react](examples/rag_react/) | Retrieval with an in-memory index |
| [pipeline_multi_agent](examples/pipeline_multi_agent/) | Pipeline and MsgHub coordination |
| [agent_team](examples/agent_team/) | Leader/worker agent coordination |
| [mcp](examples/mcp/) | MCP tool discovery and calls |
| [a2a_http](examples/a2a_http/) | Agent-to-agent communication over HTTP |
| [grpc_a2a](examples/grpc_a2a/) | TCP messaging with newline-delimited JSON, not gRPC |
| [replay](examples/replay/) | Simulated response tapes and file persistence |
| [replayview](examples/replayview/) | A terminal viewer for RunJSONL logs |
| [rundiff](examples/rundiff/) | Compare RunJSONL logs |
| [eval_harness](examples/eval_harness/) | Score recorded response fixtures |
| [agent_pool](examples/agent_pool/) | A bounded worker pool with simulated jobs |
| [hotreload](examples/hotreload/) | Typed configuration reloads |
| [bench](examples/bench/) | Load testing and latency reports |
| [quality_load](examples/quality_load/) | Task quality under scheduled arrivals, with offline fixtures |
| [qdrant_filter](examples/qdrant_filter/) | Metadata filtering against a local Qdrant server |
| [wasm_sandbox](examples/wasm_sandbox/) | WASM runtime discovery and sandbox configuration |
| [hub_install](examples/hub_install/) | Component registries and installation APIs |
| [skill_partitions](examples/skill_partitions/) | Per-agent workspace skill directories |
| [workspace_sharing](examples/workspace_sharing/) | Session/workspace bindings and artifact access |
| [access_control](examples/access_control/) | Resource grants and access checks |
| [document_parser](examples/document_parser/) | Document parsing and chunking |
| [audit_logging](examples/audit_logging/) | Sandbox policy checks and audit records |
| [guardrail](examples/guardrail/) | Block, redact and warn with mock model responses |
| [spend_cap](examples/spend_cap/) | Observed-cost budgets with a mock model |
| [agent_service](examples/agent_service/) | HTTP service and SSE events |
| [webui](examples/webui/) | Embedded browser UI |
| [dingtalk_channel](examples/dingtalk_channel/) | DingTalk messages and confirmations |
| [scheduled_task](examples/scheduled_task/) | One-shot and recurring tasks |
| [realtime_echo](examples/realtime_echo/) | A realtime-interface echo client |
| [edge_offline](examples/edge_offline/) | Cloud/local routing with Ollama |
| [edge_sensor](examples/edge_sensor/) | Sensor middleware with a mock sensor |
| [edge_serial_robot](examples/edge_serial_robot/) | Device tools with a mock serial device |
| [edge_fleet](examples/edge_fleet/) | In-memory pub/sub fleet simulation |
| [werewolves](examples/werewolves/) | A multi-agent Werewolves game |
| [k8s_workspace](examples/k8s_workspace/) | Kubernetes workspace configuration and cluster tools |
</details>
The examples guide provides running instructions and links to the same catalog.
AgentScope Go是一个有前途的开源AI工作流框架
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
AI Skill Hub 点评:AgentScope Go 的核心功能完整,质量优秀。对于自动化工程师和运维人员来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | agentscope-go |
| 原始描述 | 开源AI工作流:AgentScope Golang: Agent-Oriented Programming for Building LLM Applications。⭐22 · Go |
| Topics | AIagentchatbotGo |
| GitHub | https://github.com/AlanFokCo/agentscope-go |
| License | Apache-2.0 |
| 语言 | Go |
收录时间:2026-07-02 · 更新时间:2026-07-03 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端