agentscope-ai / agentscope-ai/agentscope

Roadmap & Future Development Plans Inquiry

Open
#1,457 2 comments 0 reactions 0 assignees View on GitHub
stale-issue
Dominant language
Python
Stars
31.5k
Forks
3.5k
Avg merge
1d 23h
Merged PRs (30d)
95

Description

## Question: Project Roadmap & Upcoming Features

Hi team, thank you for building AgentScope — it's a really interesting multi-agent framework!

I'm exploring AgentScope for integration into our AI agent platform and would love to understand the project's future direction.

### Specifically interested in:

1. **Roadmap & Milestones** — Is there a public roadmap for the next 6-12 months? What are the key focus areas?
2. **Multi-Agent Orchestration** — Are there plans for more sophisticated agent collaboration patterns (e.g., hierarchical, debate-based, or dynamic team formation)?
3. **Tool & Skill Integration** — Will there be a more robust tool/skill plugin system? Any plans for a shared skill marketplace?
4. **Streaming & Real-time Interaction** — Plans for improved streaming support, especially for multi-agent conversations visible to end users?
5. **Model Provider Expansion** — Any plans to support more LLM providers, particularly Chinese models (Qwen, DeepSeek, GLM, etc.)?
6. **Desktop/UI Integration** — Is there a vision for providing UI components or desktop integration for agent visualization and monitoring?

### Context

We are building a desktop AI agent application (DeepAgents Skills) with dynamic skill loading, multiple LLM providers, and a skill marketplace. We're interested in how AgentScope's multi-agent capabilities could enhance our platform.

Any insights would be greatly appreciated. Thank you!

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.