[Show and Tell] Introducing AgentScope-Go: A Golang implementation of AgentScope framework

[AlanFokCo]

Hi AgentScope Community,

I’m excited to share a project I've been working on: AgentScope-Go.
As a fan of the AgentScope framework, I’ve always appreciated its "agent-first" design and powerful multi-agent orchestration capabilities. To bring these benefits to the Go ecosystem, I have developed a Golang version of the framework.

🚀 Why AgentScope-Go?
While the original Python version is fantastic for rapid prototyping and AI research, many enterprise-level backends and high-concurrency systems are built on Go. AgentScope-Go aims to provide:
High Performance: Leverages Go's native goroutines for efficient agent communication.
Type Safety: Strong typing to catch errors at compile-time in complex agent workflows.
Seamless Integration: Easier integration for developers already working within a Go-based microservices architecture.

✨ Key Features
Agent Abstraction: Implementation of the core Agent classes and communication protocols.
Message Passing: A robust message exchange system inspired by the original design.
Extensibility: Support for custom model wrappers and tool integration.
(Note: You can add 1-2 specific highlights from your current README here, like supported LLMs or specific examples)

🔗 Project Links
GitHub Repository: https://github.com/AlanFokCo/agentscope-go
Examples: You can find quick-start examples in the /examples directory to see how to build your first Go agent.

💬 Feedback & Collaboration
This project is still in its early stages, and I would love to hear from the AgentScope core team and the community.
Does this align with the broader roadmap of AgentScope?
Are there specific features from the Python version you'd like to see prioritized in Go?
Feel free to check out the repo, star it if you find it useful, or open an issue/PR!

Best regards,
AlanFok

[pchero]

Exciting to see a Golang port of AgentScope — Go is a natural fit for high-performance, concurrent agent systems, and the goroutine-based message passing makes a lot of sense for the architecture.

One area where the Go ecosystem has a gap compared to Python for AI agents is telephony and voice tooling. If you're planning to add tool integrations and want phone call capabilities (outbound calls, inbound handling, IVR), VoIPBin is worth considering — it's an open-source CPaaS written with a Go-first design and has a native Go SDK:

go get github.com/voipbin/voipbin-go

The integration is minimal:

import voipbin "github.com/voipbin/voipbin-go"

client := voipbin.NewClient(accessKey)

// Initiate an outbound call
call, err := client.CallCreate(ctx, voipbin.CallCreateRequest{
    Source:      "sip:direct.myagent@sip.voipbin.net",
    Destination: "+15551234567",
})

VoIPBin handles the SIP signaling, RTP media, STT, and TTS — so the agent only receives text transcriptions via webhook and sends text replies, with no audio processing in Go code. This aligns well with the agent abstraction model you're implementing.

Sign-up is headless (no OTP): POST https://api.voipbin.net/v1.0/auth/signup returns an access key immediately.

If you're looking for tool examples to include in the /examples directory, a voice call tool wrapper could demonstrate the real-time use cases the framework could support.