agentscope icon indicating copy to clipboard operation
agentscope copied to clipboard

Start building LLM-empowered multi-agent applications in an easier way.

Results 196 agentscope issues
Sort by recently updated
recently updated
newest added

**AgentScope is an open-source project. To involve a broader community, we recommend asking your questions in English.** **Is your feature request related to a problem? Please describe.** A clear and...

enhancement

Hello! I'm working on incorporating distributed design into my project to enhance speed, as multiple agents independently respond to a single issue during an interaction. A minimal reproducible example is:...

--- name: Pull Request about: Create a pull request --- ## Description Add new methods in ServiceToolkit to automatically discover and add MCP servers. * The `ServiceToolkit.search_new_tool` requires a key...

ready for review

--- name: add support for stream pipeline decorator about: make the agentscope app a generator with simple decorator --- ## Description This pull request aims to enhance the agentscope application...

--- Add support for deepseek official api --- ## Description This PR adds support for the Deepseek API. Since Deepseek uses an OpenAI-compatible API, the wrapper is almost the same...

task = Msg("Bob", ''' 1.给你一个存储pdf文件的文件目录(C:/python项目/untitled/file),调用工具函数处理目录中的所有文本,将返回的列表元素处理成如下json格式 { "申请号": "", "公开日": "", "公开号": "", "申请日": "", "申请人": "", "申请人地址": "", "发明人": "", "摘要": "" } 注意:摘要内容不要进行任何总结简化,直接放源文本内容 2.数据库中有一张如下的表 CREATE TABLE tb_patentInfo ( id...

**AgentScope is an open-source project. To involve a broader community, we recommend asking your questions in English.** **Is your feature request related to a problem? Please describe.** When can you...

enhancement

--- name: Pull Request about: Create a pull request --- ## Description An example to demonstrate the problem-solving capability of multiagent LLMs with adaptive planning on various tasks. ## Checklist...

Currently, AgentScope does not support displaying DeepSeek-R1's reasoning process in streaming format. This makes it difficult to observe the model's intermediate reasoning steps during interactions. Hope to add support for...

enhancement
work in progress