CherryHQ/cherry-studio

[Discussion]: Why the speed of the Agent is so slow?

Open

#14796 opened on May 2, 2026

View on GitHub
 (1 comment) (2 reactions) (0 assignees)TypeScript (45,688 stars) (4,338 forks)batch import
Performancediscussionhelp wanted

Description

[!NOTE] This issue was translated by Claude.

AI智能体的加载速度非常慢，包括以下现象：

  1. 智能体列表和话题列表一直在加载，时间长达2分钟以上；
  2. 消息发出后，模型的回复一直在加载，不显示思考；
  3. 有时候系统提示了需要批准某个步骤，但是对话界面还没加载出来；

请问使用智能体模式对硬件和网络有什么硬性需求吗？

The loading speed of AI Agents is extremely slow, accompanied by the following issues: The agent list and topic list keep loading endlessly for over two minutes; After a message is sent, the model's response remains in the loading state with no thinking process displayed; Sometimes the system prompts that approval is required for a certain step, but the dialogue interface still fails to load. Are there any mandatory hardware and network requirements for using the Agent mode?

Issue Checklist

  • I understand that issues are meant for feedback and problem-solving, not for venting, and I will provide as much detail as possible to help resolve the issue.
  • I have checked the pinned issues and searched through the existing open issues, closed issues, and discussions and did not find a similar suggestion.
  • I confirm that I am here to ask questions and discuss issues, not to report bugs or request features.

Platform

Windows

Version

v1.9.3 & v1.9.4

Your Question

AI智能体的加载速度非常慢，包括以下现象：

  1. 智能体列表和话题列表一直在加载，时间长达2分钟以上；
  2. 消息发出后，模型的回复一直在加载，不显示思考；
  3. 有时候系统提示了需要批准某个步骤，但是对话界面还没加载出来；

请问使用智能体模式对硬件和网络有什么硬性需求吗？

The loading speed of AI Agents is extremely slow, accompanied by the following issues: The agent list and topic list keep loading endlessly for over two minutes; After a message is sent, the model's response remains in the loading state with no thinking process displayed; Sometimes the system prompts that approval is required for a certain step, but the dialogue interface still fails to load. Are there any mandatory hardware and network requirements for using the Agent mode?

Context

No response

Additional Information

Priority

Medium (Would like a response soon)

Contributor guide

Tech stack
typescriptreactelectron
Domain
frontenddesktopperformanceai
Issue type
research
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
mostly clear
Prerequisites
Basic understanding of AI agent architectureFamiliarity with system performance profiling
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
40
Research direction
First, review the Agent loading flow in the source code, particularly files like `src/agents/` or similar. Check if the performance issue is due to network requests, database queries, or UI rendering. Investigate the hardware requirements by looking at the official documentation or system requirements. Consider profiling the app with browser DevTools to identify bottlenecks.