09 Jan 10:18

eb18e35

v1.7.9.1

🚀 Nexent：开源智能体平台 / Nexent: Open Source Intelligent Agent Platform

我们很高兴地宣布Nexent v1.7.9.1正式发布！🎉
Nexent 是一个开源智能体平台，能够将流程的自然语言转化为完整的多模态智能体 —— 无需编排，无需复杂拖拉拽。基于 MCP 工具生态，Nexent 提供强大的模型集成、数据处理、知识库管理、零代码智能体开发能力。我们的目标很简单：将数据、模型和工具整合到一个智能中心中，使日常工作流程更智能、更互联。

We are excited to announce that Nexent v1.7.9.1 is released! 🎉
Nexent is an open-source agent platform that turns process-level natural language into complete multimodal agents — no diagrams, no wiring. Built on the MCP tool ecosystem, Nexent provides model integration, data processing, knowledge-base management, and zero-code agent development. Our goal is simple: to bring data, models, and tools together in one smart hub, making daily workflows smarter and more connected.

🔔 本周核心BUG修复 / This Week's Key Bug Fixes

1️⃣ 智能体空间显示异常：修复了当智能体数量超过限制时，智能体空间显示异常的问题

Display Issue of Agent Space: Fixed display issue when agent quantity exceeds limit

2️⃣ 本地部署配置问题：从环境配置示例文件中移除了可能影响本地部署的 DOCKER_HOST 参数

Local Deployment Configuration Issue: Removed DOCKER_HOST parameter from .env.example which could cause issues with local deployment

3️⃣ 知识库搜索参数错误：修复了chunk搜索中传递了错误的参数名（knowledge_name 应为 index_name）的问题

Incorrect Parameter in Knowledge Search: Fixed chunk search passing knowledge_name rather than index_name

4️⃣ 调试对话记忆创建逻辑错误：修复了调试对话会错误创建记忆的问题

Debug Conversation Memory Creation Logic: Fixed issue where debug conversation would incorrectly create memory

5️⃣ 其他BUG修复：修复了其他4个BUG，持续提升系统稳定性和用户体验

Other bug fixes: Fixed 4 other bugs, continuously improving system stability and user experience

What's Changed

🐛 Bugfix: Display Issue of Agent Space When Agent Quantity Exceeds Limit #2160 by @xuyaqist in #2171
🎨 Reduce the gap between the port and input box when starting the MCP container, and widen the input box to display the full hint. by @YehongPan in #2176
🐛 Bugfix: chunk search passes knowledge_name rather than index_name by @Jasonxia007 in #2195
🐛 Remove the DOCKER_HOST parameter from .env.example, which can cause issues with local deployment. #2170 by @YehongPan in #2173
✨config ModelEngine Service by @Zhi-a in #2164
✨config ModelEngine Service part2 delete model engine healthy check interface by @Zhi-a in #2165
✨config ModelEngine Service part3 repair model engine edit and delete web interface by @Zhi-a in #2169
♻️ Refactoring Agent Config by @xuyaqist in #2177
✨ MCP Service Containerization Integration #1368 by @YehongPan in #2181
✨Added ModelEngine ENV Config by @Zhi-a in #2205
📝 Update app version to 1.7.9.1 by @WMC001 in #2206
🐛 Bugfix: Debug conversation will not create memory config anymore by @Jasonxia007 in #2207
🐛 Adjust main page layout by @xuyaqist in #2212
🐛 Adjust main page layout by @xuyaqist in #2213
[release] 🐛 Remove cache of tenant config by @WMC001 in #2226
🐛 Bugfix in createmode cannot edit tool & cannot change agent model id by @xuyaqist in #2228
Release/v1.7.9.1 by @WMC001 in #2229

Full Changelog: v1.7.9...v1.7.9.1

Contributors

xuyaqist, Jasonxia007, and 3 other contributors

Assets 2

27 Dec 10:02

SimengBian

v1.7.9

d4afa9c

v1.7.9

🚀 Nexent：开源智能体平台 / Nexent: Open Source Intelligent Agent Platform

我们很高兴地宣布Nexent v1.7.9正式发布！🎉
Nexent 是一个开源智能体平台，能够将流程的自然语言转化为完整的多模态智能体 —— 无需编排，无需复杂拖拉拽。基于 MCP 工具生态，Nexent 提供强大的模型集成、数据处理、知识库管理、零代码智能体开发能力。我们的目标很简单：将数据、模型和工具整合到一个智能中心中，使日常工作流程更智能、更互联。

We are excited to announce that Nexent v1.7.9 is released! 🎉
Nexent is an open-source agent platform that turns process-level natural language into complete multimodal agents — no diagrams, no wiring. Built on the MCP tool ecosystem, Nexent provides model integration, data processing, knowledge-base management, and zero-code agent development. Our goal is simple: to bring data, models, and tools together in one smart hub, making daily workflows smarter and more connected.

🔔 核心功能更新 / Key Enhancements

1️⃣ MCP 服务一键容器化部署 / One-Click Containerized Deployment for MCP Services

本次更新支持用户通过单一 npx 命令，在 Nexent 平台内自动完成 MCP 服务的容器化部署与 URL 配置，无需手动部署并接入外部服务。

This release enables one-click containerized deployment of MCP services within the Nexent platform via a single npx command. Services are automatically deployed and their URLs configured, eliminating the need for manual deployment and external service integration.

2️⃣ ModelEngine 模型一键同步 / On-Click Synchronization of ModelEngine Models

支持在 Nexent 中配置 API Key，一键同步已部署的 ModelEngine 平台中的所有模型，供智能体开发直接选用。

Users can now configure an API Key in Nexent to seamlessly synchronize all models from a deployed ModelEngine platform, making them available for direct use in agent development.

3️⃣ 智能体市场更新 / New Update for Agent Marketplace

智能体市场现已支持下载使用新增的“法律专家”、“周报生成助手”等专业智能体，进一步扩展应用场景。

The Agent Marketplace now supports downloading and using new professional agents, such as the “Legal Expert” and “Weekly Report Assistant,” to further expand application scenarios.

4️⃣ BUG 修复 / Bug Fixes

本次更新还修复了其他3个已知问题，持续提升系统稳定性与用户体验。

This release also addresses 3 other known issues, further enhancing system stability and user experience.

🧭 特性预览 / Feature Preview

支持多租户资源隔离与团队协作 / Support for Multi-Tenancy and Team Collaboration

即将推出完善的用户管理机制，支持多租户资源隔离及团队内协作。

An enhanced user management system is coming soon, supporting multi-tenancy resource isolation and team collaboration.

What's Changed

♻️ Revert package declare by @xuyaqist in #2110
📝 Updates app version by @WMC001 in #2114
Update opensource-memorial-wall.md by @feng8403000 in #2117
✨ Adapt MCP protocal to different program language #416 by @YehongPan in #2084
🐛 Memory error cause by embedding model name with / by @Jasonxia007 in #2120
♻️ Delete Radix UI Dependency: Tooltip by @Jasonxia007 in #2130
♻️ Revise a tiny mistake in prompt by @SimengBian in #2129
♻️ Justify global layout: header+footer+content(sider+innercontent) by @xuyaqist in #2124
✨Improvement tool config test page inconsistency by @loveTsong in #2123
✨Model services that connect to ModelEngine model enablement by @Zhi-a in #2128
feat: Add PathologyAI - 智能病理诊断助手 by @hud0567 in #2118
Include additional user testimonial for Nexent platform by @jinmo666 in #2132
Update opensource-memorial-wall.md by @Saint-xc in #2134
Update opensource-memorial-wall.md by @1-xiaozheng-1 in #2138
♻️ Delete Radix UI Dependency: Tabs by @Jasonxia007 in #2131
📝 docker-build Updates by @YehongPan in #2143
🐛 Fix redundant line breaks in agent prompts generated by thinking models. #2107 by @YehongPan in #2157
♻️ Repeated calls in chat page (Agent list & conversation list) #2082 by @YehongPan in #2121
📖 User-guide update：MCP JSON containerized deployment and enables ModelEngine connectivity by @geruihappy-creator in #2156
♻️ Delete Radix UI Dependency: Button #2079 by @WMC001 in #2127
Add new entry for local deployment preparation by @chenyyinjun in #2162
♻️ Delete Radix UI Dependency: Tabs by @Jasonxia007 in #2163
🐛 Port uses a purely numeric text input box, the MCP service name uses a unified tooltip. #2158 by @YehongPan in #2161
Release/v1.7.9 by @WMC001 in #2166

New Contributors

@feng8403000 made their first contribution in #2117
@jinmo666 made their first contribution in #2132
@Saint-xc made their first contribution in #2134
@1-xiaozheng-1 made their first contribution in #2138
@chenyyinjun made their first contribution in #2162

Full Changelog: v1.7.8.1...v1.7.9

Contributors

loveTsong, SimengBian, and 12 other contributors

Assets 2

19 Dec 09:52

SimengBian

v1.7.8.1

9da494a

v1.7.8.1

🚀 Nexent：开源智能体平台 / Nexent: Open Source Intelligent Agent Platform

我们很高兴地宣布Nexent v1.7.8.1正式发布！🎉
Nexent 是一个开源智能体平台，能够将流程的自然语言转化为完整的多模态智能体 —— 无需编排，无需复杂拖拉拽。基于 MCP 工具生态，Nexent 提供强大的模型集成、数据处理、知识库管理、零代码智能体开发能力。我们的目标很简单：将数据、模型和工具整合到一个智能中心中，使日常工作流程更智能、更互联。

We are excited to announce that Nexent v1.7.8.1 is released! 🎉
Nexent is an open-source agent platform that turns process-level natural language into complete multimodal agents — no diagrams, no wiring. Built on the MCP tool ecosystem, Nexent provides model integration, data processing, knowledge-base management, and zero-code agent development. Our goal is simple: to bring data, models, and tools together in one smart hub, making daily workflows smarter and more connected.

🔔 本周核心BUG修复 / This Week's Key Bug Fixes

1️⃣ 提示词包含思考过程：修复了使用深度思考模型时，生成的提示词中包含思考过程的问题

Prompt Includes Thought Process: Fixed issue where the generated prompts include the thought process while using deep-thinking models

2️⃣ 部署脚本执行失败：修复了部署流水线中deploy.sh脚本执行失败的问题

Deployment Script Execution Failure: Fixed issue where the deployment pipeline deploy.sh failed to execute

3️⃣ 取消向量模型时弹窗重复弹出：修复了取消向量模型时，弹窗会重复弹出的问题

Duplicate Pop-up: Fixed issue where warning window would pop up twice when deselect the embedding model

What's Changed

Add new tip for 开源新手 on Nexent platform by @Magic026 in #2085
Add user testimonials to memorial wall documentation by @Decksweeper20 in #2057
♻️ Unify frontend code style by @xuyaqist in #2090
♻️ Unify dialog&modal by @xuyaqist in #2089
♻️ Refactoring TopNavbar & SideNavigation by using antd default style by @xuyaqist in #2077
📝 User-Guide Updates by @geruihappy-creator in #2091
🐛 The prompt includes the thought process #2038 by @YehongPan in #2083
♻️ The agent import performance improvement: add existing tool check by @WMC001 in #2088
♻️ Unify global dialog&modal, delete unused code by @xuyaqist in #2095
🐛 Bugfix: the deployment pipeline deploy.sh failed to execute by @WMC001 in #2097
♻️ Unify global modal, delete unused code by @xuyaqist in #2099
♻️ Delete unused navbar by @xuyaqist in #2102
🎨 Standardize frontend icons into lucide icon and antd icons by @Jasonxia007 in #2103
🎨 Change some modal button style from danger to normal by @Jasonxia007 in #2109
Bugfix: when clearing modal, modal popup twice by @xuyaqist in #2108
♻️ Revert package declare by @xuyaqist in #2111
[release] 📝 Updates app version by @WMC001 in #2115
Release/v1.7.8.1 by @WMC001 in #2113

New Contributors

@Magic026 made their first contribution in #2085
@Decksweeper20 made their first contribution in #2057
@geruihappy-creator made their first contribution in #2091

Full Changelog: v1.7.8...v1.7.8.1

Contributors

xuyaqist, Jasonxia007, and 5 other contributors

Assets 2

12 Dec 10:25

SimengBian

v1.7.8

60fb82a

v1.7.8

🚀 Nexent：开源智能体平台 / Nexent: Open Source Intelligent Agent Platform

我们很高兴地宣布Nexent v1.7.8正式发布！🎉
Nexent 是一个开源智能体平台，能够将流程的自然语言转化为完整的多模态智能体 —— 无需编排，无需复杂拖拉拽。基于 MCP 工具生态，Nexent 提供强大的模型集成、数据处理、知识库管理、零代码智能体开发能力。我们的目标很简单：将数据、模型和工具整合到一个智能中心中，使日常工作流程更智能、更互联。

We are excited to announce that Nexent v1.7.8 is released! 🎉
Nexent is an open-source agent platform that turns process-level natural language into complete multimodal agents — no diagrams, no wiring. Built on the MCP tool ecosystem, Nexent provides model integration, data processing, knowledge-base management, and zero-code agent development. Our goal is simple: to bring data, models, and tools together in one smart hub, making daily workflows smarter and more connected.

🔔 核心功能更新 / Key Enhancements

1️⃣ 一键升级支持 / One-Click Upgrade Support

本次更新推出一键升级特性，用户仅需执行一个upgrade脚本即可完成全流程无缝升级，大幅简化版本更新操作，提升使用体验。

This release introduces a one-click upgrade feature. Users can now seamlessly upgrade the system by simply running an upgrade script, significantly simplifying the version update process and enhancing the overall experience.

2️⃣ Agent 导入逻辑优化 / Agent Import Logic Optimization

优化了 Agent 导入流程。当导入的 Agent 依赖不存在的 MCP 服务时，系统会主动提醒用户安装相应服务，避免配置中断，使导入流程更加顺畅可靠。

The Agent import process has been optimized. If an imported Agent relies on MCP services that are not installed, the system will proactively prompt the user to install them, preventing configuration interruptions and ensuring a smoother, more reliable import flow.

3️⃣ Agent 复制功能 / Agent Duplication Feature

新增 Agent 复制功能，用户可通过点击复制按钮快速创建当前 Agent 的副本，便于进行多版本调试、实验与并行开发，提升工作效率。

A new Agent duplication feature is now available. With a single click, users can create a duplicate of an existing Agent, facilitating multi-version debugging, experimentation, and parallel development to improve workflow efficiency.

4️⃣ MCP 协议支持扩展 / Expanded MCP Protocol Support

新增对 Streamable HTTP 协议的 MCP 服务接入支持，此前仅支持 SSE 协议。用户现在可以连接更多类型的 MCP 服务，扩展智能体能力范围。

Support for MCP services using the Streamable HTTP protocol has been added, complementing the existing SSE protocol support. Users can now connect to a wider variety of MCP services, extending the capabilities of their agents.

5️⃣ 知识库体验优化 / Knowledge Base Experience Improvements

知识库模块迎来多项优化：取消命名限制，支持使用中英文自由命名；新增文件处理进度环，创建知识库时可实时查看处理进度；创建失败时提供详细错误原因，帮助用户快速定位问题。

The Knowledge Base module has been enhanced with several improvements: naming restrictions have been removed, allowing free use of Chinese and English characters; a progress ring now displays real-time file processing status during creation; and detailed failure reasons are provided if creation fails, helping users quickly identify and resolve issues.

6️⃣ BUG 修复 / Bug Fixes

本次更新还修复了其他9个已知问题，持续提升系统稳定性与用户体验。

This release also addresses 9 other known issues, further enhancing system stability and user experience.

🧭 特性预览 / Feature Preview

更健全的用户管理机制 / Enhanced User Management Mechanism

即将推出更完善的用户权限与安全管理功能，助力团队协作更安全、更高效。

Upcoming improvements in user management will deliver more robust permission controls and security features for smoother team collaboration.

更丰富的智能体市场 / Expanded Agent Marketplace

我们将持续引入更多优质智能体，覆盖更广泛的场景与需求。

We will continue to enrich the marketplace with high-quality agents designed for diverse scenarios and user needs.

支持MCP服务一键部署及接入 / One-Click MCP Service Deployment & Integration

我们将支持MCP服务的一键部署与快速接入，进一步降低开发与集成门槛。

Soon, you'll be able to deploy and integrate MCP services with just one click, streamlining development and integration processes.

What's Changed

🐛 Fixing the inability to download datamate data source files by @Zhi-a in #2028
🐛 Bugfix: Build frontend arm image failed by @WMC001 in #2018
Update opensource-memorial-wall.md by @Came11ious in #2007
Add user testimonials to memorial wall by @Papaver01 in #2020
Add user feedback on Nexent platform improvements by @aschenmo in #2022
Leave a message by @aschenmo in #2023
Add tip from 开源新手 to memorial wall by @WenrongDu in #2026
⭐️ Add MCP Server Install hint and fix tool test display by @Phinease in #2033
✨ Adapt MCP protocal to different program language #416 by @YehongPan in #1990
✨ The model ultimately renders an image from the S3 bucket. by @Zhi-a in #2005
⭐️ Add upgrade script by @loveTsong in #1989
♻️ All models should use nexent.core.model instead of smolagent #1971 by @YehongPan in #2027
fix: scrolling flicker on agent creation by @loveTsong in #2039
🐛Bugfix: When the list of agents is empty, the column width will shrink by @xuyaqist in #2045
✨ Docs: Add instructions for debugging with locally built latest images by @loveTsong in #2051
🐛Bugfix: tool config test page inconsistency by @loveTsong in #2050
🐛Bugfix: Eliminate flicker when switching knowledge base overview by @loveTsong in #2046
🐛 fix when asking the agent to write code, code does not appear code box by @Phinease in #2052
Bugfix: adding memory box at the front of the list, improving user experience by @xuyaqist in #2054
✨ Agent copy feature by @SimengBian in #2044
🐛Bugfix: Set the agent configuration page outer scrollbar to be hidden and the inner scrollbar to be displayed by @xuyaqist in #2060
✨ Now document process has a progress bar by @Jasonxia007 in #2011
♻️ Move the logic of renaming the duplicate agents to frontend by @WMC001 in #2053
⭐️ Agent Author by @Phinease in #2061
♻️ Revise the sql name prefix to v1.7.8 by @Jasonxia007 in #2064
🐛 Bugfix: Agents with no duplicate names will also display the renaming steps #2069 by @WMC001 in #2073
📝 Update Docs by @Phinease in #2075
Release/v1.7.8 by @WMC001 in #2078

New Contributors

@Came11ious made their first contribution in #2007
@Papaver01 made their first contribution in #2020
@aschenmo made their first contribution in #2022
@WenrongDu made their first contribution in #2026

Full Changelog: v1.7.7.1...v1.7.8

Contributors

loveTsong, SimengBian, and 10 other contributors

Assets 2

05 Dec 11:31

SimengBian

v1.7.7.1

f1f02b6

v1.7.7.1

🚀 Nexent：开源智能体平台 / Nexent: Open Source Intelligent Agent Platform

我们很高兴地宣布Nexent v1.7.7.1正式发布！🎉
Nexent 是一个开源智能体平台，能够将流程的自然语言转化为完整的多模态智能体 —— 无需编排，无需复杂拖拉拽。基于 MCP 工具生态，Nexent 提供强大的模型集成、数据处理、知识库管理、零代码智能体开发能力。我们的目标很简单：将数据、模型和工具整合到一个智能中心中，使日常工作流程更智能、更互联。

We are excited to announce that Nexent v1.7.7.1 is released! 🎉
Nexent is an open-source agent platform that turns process-level natural language into complete multimodal agents — no diagrams, no wiring. Built on the MCP tool ecosystem, Nexent provides model integration, data processing, knowledge-base management, and zero-code agent development. Our goal is simple: to bring data, models, and tools together in one smart hub, making daily workflows smarter and more connected.

🔔 本周核心BUG修复 / This Week's Key Bug Fixes

1️⃣ 模型配置保存问题：修复了单一新增的LLM模型无法自动保存的问题

LLM Config Not Saved Automatically: Fixed issue where a single added LLM model wouldn't be saved automatically

2️⃣ 部署失败导致终端关闭：修复了部署因端口占用而失败会导致终端意外关闭的问题

Deployment Failure Causes Terminal to Close: Fixed issue where the deployment failure due to ports occupied would cause the terminal to close

3️⃣ 删除MCP服务器后对话框残留：修复了删除MCP服务器后确认对话框仍然残留显示的问题

Delete Dialog Remains After Deleting MCP Server: Fixed issue where the delete dialog box remained displayed after deleting the MCP server

4️⃣ DataMate数据源文件无法下载：修复了无法下载DataMate数据源文件的问题

Cannot Download DataMate Data Source Files: Fixed issue where users were unable to download Datamate data source files

5️⃣ 其他BUG修复：修复了其他9个BUG，持续提升系统稳定性和用户体验

Other bug fixes: Fixed 9 other bugs, continuously improving system stability and user experience

What's Changed

🐛 Bugfix: single added LLM model won't be saved automatically by @Jasonxia007 in #1934
🐛 Front-end development and optimization of market interface display by @WMC001 in #1931
📝 Update multimodal tool description by @Zhi-a in #1930
info aaa - 2025-11-28 by @joket11 in #1911
📝 Update agent import description by @YehongPan in #1938
⭐️ Agent Market Backend Adapt by @Phinease in #1948
🐛 Update url of agent market by @WMC001 in #1950
⭐️ ModelEngine Models Interrogation by @Phinease in #1949
Update opensource-memorial-wall.md by @hanyuan5888-beep in #1940
Add thank you note for Nexent in memorial wall by @G-oeX in #1943
Add gratitude entry for Nexent in memorial wall by @G-oeX in #1944
Add message of gratitude for nexent platform by @luna2025-collab in #1954
Add user testimonials to memorial wall documentation by @peri1506 in #1946
Update opensource-memorial-wall.md by @kissmekm in #1956
Add new entry to open source memorial wall by @sbwrn in #1960
Update opensource-memorial-wall.md by @huqinyuan in #1961
Add messages of support for nexent platform by @sbwrn in #1962
🐛 fix Status inconsistent in Agent Space by @Phinease in #1963
⭐️ Support image version tag by @loveTsong in #1968
🐛 no expected error should show on UI by @Phinease in #1964
🐛 Fix the title generate of deep thinking model. #1947 by @YehongPan in #1970
🐛 fix deployment failure will cause the terminal to close by @Phinease in #1974
✨ Add DataMate knowledge retrieval tool by @Zhi-a in #1969
Add user comment for NEXENT event participation by @Deng-peiying in #1965
Fix formatting in open source memorial wall by @2231924086 in #1981
Add gratitude note for Nexent in memorial wall by @KIMI-QIMO in #1980
Update opensource-memorial-wall.md by @jinhb2012-afk in #1987
📝 Multimodal sdk document by @Zhi-a in #1993
🐛UI Improvement by @xuyaqist in #1972
✨ 1. Knowledge base tracing results support downloading. 2. File download requests are made to the backend interface, instead of directly accessing Minio. by @Zhi-a in #1975
🐛 Fix the pending of agent duplicate name handling. by @YehongPan in #1978
♻️ The agent import performance improvement #1905 by @WMC001 in #1991
🐛 Bugfix: The doc website link cannot be accessed #2000 by @WMC001 in #2014
📝 Multimodal document issue fixes by @Zhi-a in #2012
⭐️ Add Future features to side navigation and UI Improvement by @Phinease in #2004
🐛 Bugfix: "deleting the MCP server, the delete dialog box remains displayed" by @xuyaqist in #2013
[release] 🐛 Bugfix: Build frontend arm image failed by @WMC001 in #2019
[release] ♻️ Upgrade the version of next.js to 15.5.7 by @WMC001 in #2031
🐛 Fixing the inability to download datamate data source files by @Zhi-a in #2029
Release/v1.7.7.1 by @WMC001 in #2015

New Contributors

@joket11 made their first contribution in #1911
@hanyuan5888-beep made their first contribution in #1940
@G-oeX made their first contribution in #1943
@luna2025-collab made their first contribution in #1954
@peri1506 made their first contribution in #1946
@kissmekm made their first contribution in #1956
@sbwrn made their first contribution in #1960
@huqinyuan made their first contribution in #1961
@loveTsong made their first contribution in #1968
@Deng-peiying made their first contribution in #1965
@2231924086 made their first contribution in #1981
@KIMI-QIMO made their first contribution in #1980
@jinhb2012-afk made their first contribution in #1987

Full Changelog: v1.7.7...v1.7.7.1

Contributors

loveTsong, xuyaqist, and 17 other contributors

Assets 2

29 Nov 11:48

SimengBian

v1.7.7

09da4ba

v1.7.7

🚀 Nexent：开源智能体平台 / Nexent: Open Source Intelligent Agent Platform

我们很高兴地宣布Nexent v1.7.7正式发布！🎉
Nexent 是一个开源智能体平台，能够将流程的自然语言转化为完整的多模态智能体 —— 无需编排，无需复杂拖拉拽。基于 MCP 工具生态，Nexent 提供强大的模型集成、数据处理、知识库管理、零代码智能体开发能力。我们的目标很简单：将数据、模型和工具整合到一个智能中心中，使日常工作流程更智能、更互联。

We are excited to announce that Nexent v1.7.7 is released! 🎉
Nexent is an open-source agent platform that turns process-level natural language into complete multimodal agents — no diagrams, no wiring. Built on the MCP tool ecosystem, Nexent provides model integration, data processing, knowledge-base management, and zero-code agent development. Our goal is simple: to bring data, models, and tools together in one smart hub, making daily workflows smarter and more connected.

🔔 核心功能更新 / Key Enhancements

1️⃣ 智能体市场 / Agent Marketplace

我们正式推出智能体市场，未来将陆续上架各类实用与有趣的智能体，供用户轻松下载与使用。诚邀广大开发者与用户共同参与内容共建，打造更丰富的智能体生态。

We are excited to launch the Agent Marketplace, where a variety of useful and engaging agents will be made available for download and use. We welcome developers and users to join us in building a vibrant agent ecosystem together.

2️⃣ 多模态数据SDK / Multimodal Data SDK

全新多模态数据SDK现已提供，支持图像、文本、文件等多类数据在工具与智能体间高效流转，为复杂任务处理提供底层能力支撑。

The new Multimodal Data SDK is now available, enabling efficient data flow—including images, text, and files—between tools and agents, empowering more sophisticated task handling.

3️⃣ 多模态工具 / Multimodal Tools

新增多模态理解工具，支持对上传的文件及图片进行内容识别与分析。在创建智能体时启用此工具，即可在对话过程中上传并处理文件或图像内容。

Introducing the Multimodal Comprehension Tool, which supports content recognition and analysis of uploaded files and images. Enable this tool during agent creation to process files or images within conversations.

4️⃣ 知识库检索测试 / Knowledge Base Retrieval Testing

新增知识库检索测试模块，支持通过模拟查询检验检索效果，帮助您快速定位并优化知识库配置问题。

A new Knowledge Base Retrieval Testing feature allows you to validate search effectiveness through test queries, making it easier to identify and resolve configuration issues.

5️⃣ 知识库文本块管理 / Knowledge Base Text Chunk Management

新增知识库文本块编辑、新增及删除功能，您可以灵活调整文本块内容，进一步提升知识检索的准确性与效果。

You can now edit, add, or delete text chunks in your knowledge base, giving you greater control over content organization and improving retrieval performance.

6️⃣ BUG 修复 / Bug Fixes

本次更新还修复了其他7个已知问题，持续提升系统稳定性与用户体验。

This release also addresses 7 other known issues, further enhancing system stability and user experience.

🧭 特性预览 / Feature Preview

更健全的用户管理机制 / Enhanced User Management Mechanism

即将推出更完善的用户权限与安全管理功能，助力团队协作更安全、更高效。

Upcoming improvements in user management will deliver more robust permission controls and security features for smoother team collaboration.

更丰富的智能体市场 / Expanded Agent Marketplace

我们将持续引入更多优质智能体，覆盖更广泛的场景与需求。

We will continue to enrich the marketplace with high-quality agents designed for diverse scenarios and user needs.

支持MCP服务一键部署及接入 / One-Click MCP Service Deployment & Integration

我们将支持MCP服务的一键部署与快速接入，进一步降低开发与集成门槛。

Soon, you'll be able to deploy and integrate MCP services with just one click, streamlining development and integration processes.

What's Changed

🐛 Bugfix: agent tools save or load parameters failed by @Jasonxia007 in #1779
📝 Update user-guide docs to fit new features by @SimengBian in #1783
🐛 Bugfix: After redeployment, the contents of files in Minio were cleared by @WMC001 in #1839
✨ Now documents and chunks support semantic search by @Jasonxia007 in #1849
📝 Add doc to illustrate MCP server development by @SimengBian in #1857
📝 Update sceenshots and illustrate tool test run in docs by @SimengBian in #1884
🐛 Add renderings of failed image and video loading #1872 by @WMC001 in #1873
✨ Now supports add/delete/edit chunks by @Jasonxia007 in #1880
✨ Agent duplicate name handling logic improvement #1622 by @YehongPan in #1861
✨ image to text tool by @Zhi-a in #1836
✨ file to text tool by @Zhi-a in #1848
📝 Update app version and format the memorial wall by @WMC001 in #1897
🐛 Bugfix: When creating a new Agent, the user is not prompted to save it before debugging by @Jasonxia007 in #1898
✨ Multi modal agent. Pass the URL of the multimodal file as the query to the agent. by @Zhi-a in #1860
⭐️ Agent Market phase 1 by @Phinease in #1904
⭐️ Agent Market phase 2 by @Phinease in #1917
🐛 Repairing Multimodal Tools Cannot Export by @Zhi-a in #1916
🐛 Repairing Multimodal Tools Cannot Export by @Zhi-a in #1919
⭐️ Agent Market phase 2 by @Phinease in #1927
📝 Update multimodal tool description by @Zhi-a in #1929
[release] 🐛 Front-end development and optimization of market interface display by @WMC001 in #1932
🐛 Bugfix: single added LLM model won't be saved automatically by @Jasonxia007 in #1935
Release/v1.7.7 by @WMC001 in #1936

New Contributors

@Lin-Wang-QHU made their first contribution in #1784
@AgainsTurb made their first contribution in #1786
@fujin6399-bit made their first contribution in #1821
@DUTBenjamin made their first contribution in #1827
@dean-stack made their first contribution in #1828
@adasibi made their first contribution in #1829
@charleswang-de made their first contribution in #1830
@AuroraHashcat made their first contribution in #1832
@williamllk-ai made their first contribution in #1833
@lostlight530 made their first contribution in #1838
@dantingli1 made their first contribution in #1840
@wuhu-wjd made their first contribution in #1842
@czh1316 made their first contribution in #1844
@jackliu631 made their first contribution in #1854
@gs80140 made their first contribution in #1864
@wwaawwaaee made their first contribution in #1875
@sharkkk123-1 made their first contribution in #1877
@Lillian00700 made their first contribution in #1881
@NOSNNN made their first contribution in #1885
@Chenpi-Sakura made their first contribution in #1886
@yy-cy made their first contribution in #1887
@AstreoX made their first contribution in #1888
@jiajialuo027-droid made their first contribution in #1890
@Phoebe246824 made their first contribution in #1892
@wei-cell12 made their first contribution in #1895

Full Changelog: v1.7.6...v1.7.7

Contributors

gs80140, SimengBian, and 29 other contributors

Assets 2

21 Nov 12:15

SimengBian

v1.7.6

e27d265

v1.7.6

🚀 Nexent：开源智能体平台 / Nexent: Open Source Intelligent Agent Platform

我们很高兴地宣布Nexent v1.7.6正式发布！🎉
Nexent 是一个开源智能体平台，能够将流程的自然语言转化为完整的多模态智能体 —— 无需编排，无需复杂拖拉拽。基于 MCP 工具生态，Nexent 提供强大的模型集成、数据处理、知识库管理、零代码智能体开发能力。我们的目标很简单：将数据、模型和工具整合到一个智能中心中，使日常工作流程更智能、更互联。

We are excited to announce that Nexent v1.7.6 is released! 🎉
Nexent is an open-source agent platform that turns process-level natural language into complete multimodal agents — no diagrams, no wiring. Built on the MCP tool ecosystem, Nexent provides model integration, data processing, knowledge-base management, and zero-code agent development. Our goal is simple: to bring data, models, and tools together in one smart hub, making daily workflows smarter and more connected.

🔔 核心功能更新 / Key Enhancements

1️⃣ 新增全局导航栏 / Global Navigation Bar

我们在页面左侧新增了清晰易用的导航栏，优化了用户的操作路径，支持快速跳转至各个核心模块，显著提升使用效率与操作便捷性。

We have introduced a user-friendly global navigation bar on the left side of the page, streamlining user workflows and enabling quick access to key modules, significantly improving overall usability and navigation efficiency.

2️⃣ 智能体空间上线 / Agent Space Launch

全新推出“智能体空间”页面，用户可在此以直观的卡片形式浏览所有智能体，查看详细配置信息，并执行删除、导出等管理操作，帮助用户更好地组织与管理智能体资源。

We are excited to launch the new "Agent Space" page, where users can browse all agents in an intuitive card-based layout, view detailed configurations, and perform management actions such as deletion and export, enabling better organization and control over agent resources.

3️⃣ 视频播放支持 / Video Playback Support

前端现已支持视频内容的嵌入与播放，用户可对视频进行播放、暂停等交互操作，进一步丰富了内容展示形式与用户体验。

The frontend now supports video embedding and playback, allowing users to interact with video content through play and pause controls, enriching content presentation and enhancing the overall user experience.

4️⃣ 后端容器架构优化 / Backend Container Architecture Optimization

我们将后端容器拆分为编辑态与运行态两种模式，有效提升系统资源利用率和任务处理能力，显著增强多任务并发性能。

We have split the backend container into separate editing and runtime modes, optimizing system resource utilization and task processing capabilities, thereby significantly improving performance under concurrent workloads.

5️⃣ 知识库切块预览 / Knowledge Base Chunk Preview

新增知识库内容切块预览功能，用户可直观查看知识库中被分段处理后的详细内容，便于理解和校验知识的结构与完整性。

We've added a knowledge base chunk preview feature, allowing users to visually inspect the segmented content within their knowledge bases, making it easier to understand and verify the structure and integrity of stored knowledge.

6️⃣ BUG 修复 / Bug Fixes

本次更新还修复了其他9个已知问题，持续提升系统稳定性与用户体验。

This release also addresses 9 other known issues, further enhancing system stability and user experience.

🧭 特性预览 / Feature Preview

智能体市场即将上线 / Agent Marketplace Coming Soon

我们即将推出智能体市场，为用户提供丰富多样的实用与趣味智能体，支持一键下载与部署，拓展智能体应用场景。

We will soon launch the Agent Marketplace, offering a variety of practical and entertaining agents for users to download and deploy with one click, expanding the possibilities of agent applications.

多模态 SDK 开发 / Multimodal SDK in Development

我们正在开发全新的多模态 SDK，以支持图像、音频等多模态数据在智能体间的无缝、高效流转，赋能更复杂的跨模态交互场景。

A new Multimodal SDK is currently in development, designed to facilitate seamless and efficient transmission of multimodal data (such as images and audio) between agents, enabling more sophisticated cross-modal interaction scenarios.

What's Changed

🐛 Bugfix: ray initialize failed by @Jasonxia007 in #1704
🐛 Bugfix: ray initialize failed by @Jasonxia007 in #1705
Release/v1.7.5.3 hotfix by @WMC001 in #1709
⭐️ Agent Space by @Phinease in #1712
⭐️ Navigation system by @Phinease in #1723
⭐️ Add pages to Navigation by @Phinease in #1724
⭐️ Navigation SPA mode by @Phinease in #1725
⭐️ Navigation SPA mode to chat by @Phinease in #1726
🐛 Bugfix: Agent import does not import max steps of agent run #1582 by @WMC001 in #1718
🐛 Fix chat sidebar and main area scroll height by @Phinease in #1729
✨Agent runtime isolation Step1: Service decomposition based on Docker #606 by @YehongPan in #1672
✨ Multi-modal data sdk by @Zhi-a in #1717
✨Agent configuration page logic optimization #1711 by @YehongPan in #1730
♻️ Refactor: refactor elasticsearch core to vectordb core by @Jasonxia007 in #1728
✨Agent runtime isolation Step1: Service decomposition based on Docker #606 by @YehongPan in #1735
Add new testimonial for qinjavermo by @jingjing-ai520 in #1731
✨ Add video rendering for the chat page, name searching when batching add models, and optimize the display effect of the final answer by @WMC001 in #1737
🐛 Bugfix: The intelligent generation agent cannot recognize the selected tool by @Jasonxia007 in #1746
✨ Now knowledgebase page supports chunk preview and chunk download by @Jasonxia007 in #1736
🐛 Fixed the incompatibility issue of env.example utf8-bom on Linux. by @Zhi-a in #1749
🐛 Changes to app settings on the configuration page need to be saved in real time by @WMC001 in #1751
⭐️ Comming soon pages by @Phinease in #1766
🐛 Bugfix: knowledgebase search tools cannot initialize correctly by @Jasonxia007 in #1773
Update app version v1.7.6 by @WMC001 in #1767
Add info tip for chengyudan by @chengyudan in #1756
🐛 When the knowledge base is automatically summarized, other interfaces will be pended. #1684 #1755 by @YehongPan in #1771
Release/v1.7.6 by @WMC001 in #1775
🐛 Bugfix: agent tools save or load parameters failed by @Jasonxia007 in #1780
Release/v1.7.6 by @WMC001 in #1781

New Contributors

@18June96 made their first contribution in #1675
@happyzhanghengyu0 made their first contribution in #1677
@LockerCN made their first contribution in #1694
@xlp888 made their first contribution in #1700
@duanchuangju666 made their first contribution in #1681
@dym040615 made their first contribution in #1701
@kno-do made their first contribution in #1713
@jingjing-ai520 made their first contribution in #1731
@lvxiaohai99 made their first contribution in #1738
@chengyudan made their first contribution in #1743
@992638310-glitch made their first contribution in #1752
@china-king-hs made their first contribution in #1757

Full Changelog: v1.7.5.3...v1.7.6

Contributors

lvxiaohai99, Jasonxia007, and 15 other contributors

Assets 2

17 Nov 07:02

WMC001

v1.7.5.3-hotfix

d666c6c

v1.7.5.3-hotfix

🔔 热修复 / Hotfix

1️⃣ Ray 进程初始化失败修复 / Ray Process Initialization Failure Fix

修复了本地环境中 Ray 进程启动时因配置加载异常导致的初始化失败问题

Fixed the initialization failure of Ray processes in the local environment caused by abnormal configuration loading.

Assets 2

15 Nov 07:11

SimengBian

v1.7.5.3

9c165e6

v1.7.5.3

🚀 Nexent：开源智能体平台 / Nexent: Open Source Intelligent Agent Platform

我们很高兴地宣布Nexent v1.7.5.3正式发布！🎉
Nexent 是一个开源智能体平台，能够将流程的自然语言转化为完整的多模态智能体 —— 无需编排，无需复杂拖拉拽。基于 MCP 工具生态，Nexent 提供强大的模型集成、数据处理、知识库管理、零代码智能体开发能力。我们的目标很简单：将数据、模型和工具整合到一个智能中心中，使日常工作流程更智能、更互联。

We are excited to announce that Nexent v1.7.5.3 is released! 🎉
Nexent is an open-source agent platform that turns process-level natural language into complete multimodal agents — no diagrams, no wiring. Built on the MCP tool ecosystem, Nexent provides model integration, data processing, knowledge-base management, and zero-code agent development. Our goal is simple: to bring data, models, and tools together in one smart hub, making daily workflows smarter and more connected.

🔔 本周核心BUG修复 / This Week's Key Bug Fixes

1️⃣ 知识库总结失败：修复了知识库总结失败的问题

Knowledge Base Summary Failure: Fixed issue where knowledge base summary failed

2️⃣ 聊天框状态切换问题：修复了聊天框状态应切换为"已读"的问题

Chat Box Status Switch Issue: Fixed issue where Dialog status should switch to "read"

3️⃣ 页面显示和跳转逻辑：修复了轻量版中页面显示逻辑和完整版中页面跳转逻辑

Page Display/Jump Logic: Fixed page display logic in speed mode and page jump logic in full mode

4️⃣ 登录窗口关闭问题：修复了登录窗口无法关闭的问题

5️⃣ 其他BUG修复：修复了其他5个BUG，持续提升系统稳定性和用户体验

Other bug fixes: Fixed 5 other bugs, continuously improving system stability and user experience

What's Changed

🐛 Fixed an issue where batch modification of the maximum token count was not synchronized in a single model setting. #1575 by @YehongPan in #1590
🐛 When a user swipes and taps the chat box, the Dialog status should switch to "read". #1388 by @YehongPan in #1591
🐛 Knowledge base summary failed. #1619 by @porkpink in #1620
🐛 Page display logic fix in speed mode and page jump logic fix in full mode by @WMC001 in #1627
🐛 In the MCP configuration, connectivity is verified, and after a tool is deleted or added (or its status changes), the tool list and agent list are refreshed synchronously. #1345 by @YehongPan in #1633
✨[Request] Abstract Storage SDK by @Zhi-a in #1628
Add user feedback on automatic agent creation feature by @JQTXZS2 in #1645
Revert "✨[Request] Abstract Storage SDK" by @Phinease in #1668
✨ Now user can save or discard changes in agent config page by @Jasonxia007 in #1654
🐛 Even when there is no historical login token, the login prompt needs to pop up #1476 by @WMC001 in #1648
Add tip section for new open source contributors by @0501-maomao in #1655
Add tip from jeery1 about Huawei ICT event by @Jeery1 in #1656
✨[Request] Abstract Storage SDK #1219 by @Zhi-a in #1651
🐛 Bugfix: login window cannot be closed #1476 by @WMC001 in #1679
🐛 Agents with abnormal status should also be allowed to operate #1683 by @WMC001 in #1687
🐛 Bugfix: generate button in Agent config page returns error: Empty agent ID in creation mode by @Jasonxia007 in #1689
♻️ Imporvement: nexent-data-process now takes less memory, elasticsearch takes more available memory by @Jasonxia007 in #1691

New Contributors

@Jackie-LIONS made their first contribution in #1579
@lzypython made their first contribution in #1585
@xiaochenIpter made their first contribution in #1596
@pxqn-xing made their first contribution in #1598
@qiyan111 made their first contribution in #1611
@axp007 made their first contribution in #1615
@qianmoyaq made their first contribution in #1639
@muxinmoment made their first contribution in #1641
@JQTXZS2 made their first contribution in #1645
@yifeiqiao made their first contribution in #1650
@andznrule made their first contribution in #1652
@0501-maomao made their first contribution in #1655
@Jeery1 made their first contribution in #1656
@Ren-chao02 made their first contribution in #1657
@hly7774 made their first contribution in #1658
@wilson-hash made their first contribution in #1659
@KevinLeeNJ made their first contribution in #1663
@chengliuxiang2002 made their first contribution in #1670

Full Changelog: v1.7.5.2...v1.7.5.3

Contributors

Jasonxia007, Phinease, and 22 other contributors

Assets 2

11 Nov 01:36

SimengBian

v1.7.5.2

747761f

v1.7.5.2

🚀 Nexent：开源智能体平台 / Nexent: Open Source Intelligent Agent Platform

我们很高兴地宣布Nexent v1.7.5.2正式发布！🎉
Nexent 是一个开源智能体平台，能够将流程的自然语言转化为完整的多模态智能体 —— 无需编排，无需复杂拖拉拽。基于 MCP 工具生态，Nexent 提供强大的模型集成、数据处理、知识库管理、零代码智能体开发能力。我们的目标很简单：将数据、模型和工具整合到一个智能中心中，使日常工作流程更智能、更互联。

We are excited to announce that Nexent v1.7.5.2 is released! 🎉
Nexent is an open-source agent platform that turns process-level natural language into complete multimodal agents — no diagrams, no wiring. Built on the MCP tool ecosystem, Nexent provides model integration, data processing, knowledge-base management, and zero-code agent development. Our goal is simple: to bring data, models, and tools together in one smart hub, making daily workflows smarter and more connected.

🔔 本周核心BUG修复 / This Week's Key Bug Fixes

1️⃣ 批量添加模型失败：修复了因缺少分块大小参数导致批量添加模型失败的问题

Batch Model Adding Failure: Fixed issue where batch adding model failed due to missing expected chunk size parameter

2️⃣ Markdown意外换行：修复了最终答案中Markdown意外换行的问题

Unexpected Line Break in Markdown: Fixed issue where unexpected Markdown line break appears in final answer

3️⃣ 模型连接失败时的提示错误：修复了在中文环境下模型连接失败时显示英文错误信息的问题

Wrong Error Message When Model Connection Failed: Fixed issue where English error message shows up under Chinese environment when model connection fails

4️⃣ 同名Agent状态修复：修复了同名Agent均可运行的问题；现在当存在同名Agent时，系统会将其标记为不可用并提醒用户修改名称。

Duplicate Agent Name Status Repair: Fixed issue where multiple agents with the same name could all run; now duplicate-named agents will be marked as unusable and guide the user to modify the name.

5️⃣ 其他BUG修复：修复了其他9个BUG，持续提升系统稳定性和用户体验

Other bug fixes: Fixed 9 other bugs, continuously improving system stability and user experience

What's Changed

🐛 [Bug] Fixed the issue where the Agent prompt text description overwrote the button. by @Zhi-a in #1500
🐛 [Improvement] When creating an Agent, the information items of the created agent should be clear by @Zhi-a in #1508
🐛 [Bug] English error message shows up under chinese language when model is not connected #1502 by @Mermaid97 in #1543
✨ Now user can adjust the chunking size when adding or editing the embedding model by @Jasonxia007 in #1512
🎨 Tool test run results formatting #1399 by @porkpink in #1556
🐛 [Bug] Translation unavailable when generating agent without business description by @Zhi-a in #1557
🐛 [Bug] An agent with the same name should be displayed as unusable. by @Zhi-a in #1560
🐛 Fix unexpected line break on markdown display of final answer #1475 by @YehongPan in #1563
🐛 [Bug] Remove unnecessary floating tooltip. by @Zhi-a in #1564
🐛 Button text in agent tools modal are not centered. #1506 by @porkpink in #1565
🐛 Fix the issue where the frontend still throws an exception after successfully batch modifying the model configuration #1439 by @YehongPan in #1567
🐛 Repair English error message shows up under chinese language when model is not connected by @Mermaid97 in #1513
🎨 [Improvement] When uploading the same document multiple times, the knowledge base summary will classify them into multiple categories. by @Mermaid97 in #1551
🐛 Generating title error when using tokenpony deepseek-r1 #1339 by @porkpink in #1570
🐛 When not logged in, access to the backend interface is not allowed #1476 by @WMC001 in #1571
🐛 Bugfix: bacth create model failed due to missing expected chunk size by @Jasonxia007 in #1573
🐛 Bugfix: bacth create model failed due to missing expected chunk size by @Jasonxia007 in #1574
[release] 📝 Update APP version by @WMC001 in #1584
Release/v1.7.5.2 by @WMC001 in #1613