The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
README.md	2026-09-16	19.2 kB	0
v2.6.0 source code.tar.gz	2026-09-16	62.6 MB	0
v2.6.0 source code.zip	2026-09-16	64.1 MB	0
Totals: 3 Items		126.7 MB	0

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

我们很高兴地宣布Nexent v2.6.0 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 v2.6.0 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.

新功能 / New Features

重构模型管理页面：统一模型编辑对话框，新增模型容量自动推荐（内置 LiteLLM 模型目录、离线可用）、自定义参数校验与推理参数配置。 / Revamped the model management page: unified model edit dialog, automatic model capacity suggestions (bundled LiteLLM catalog, works offline), custom parameter validation, and inference parameter configuration.
新增完整会话线程（Thread）管理能力，覆盖创建、切换与并发控制，并配套遥测指标。 / Added full conversation thread management, covering creation, switching, and concurrency control, with telemetry support.
上线外部记忆体系：智能体可在最终回答后自动提取记忆，支持外部记忆提供方检索（top_k、超时可配置），并提供 AIDP Memory 插件与插件热加载。 / Introduced the external memory system: agents automatically extract memories after final answers, with configurable external provider search (top_k, timeout), an AIDP Memory plugin, and hot-reloadable plugins.
优化 Agent 创建体验：NL2Agent 生成流程与落地卡片打磨，新增 NL2Agent 优化建议，提示词同步升级。 / Improved the agent creation experience: polished NL2Agent generation flow and landing cards, with new NL2Agent optimization suggestions and upgraded prompts.
检索引用交互升级：回答中的引用支持统一悬浮卡片与点击定位高亮。 / Upgraded retrieval citations: references in answers now support unified hover cards with click-to-focus highlighting.
重构统一标签（Label）系统，支持标签库权限、资源打标与筛选，并为多版本 Agent 提供协作版本标签。 / Refactored the unified label system with tag library permissions, resource tagging, and filtering, plus collaborative version labels for multi-version agents.
支持模型优先级排序，可按优先级为智能体选择模型。 / Added model priority sorting so agents can select models by priority.
沙箱适配 Anthropic Skills，可直接运行 Anthropic 技能格式。 / Adapted the sandbox to run Anthropic skills natively.
S3 上传/下载工具支持用户自定义配置。 / The upload_to_s3 and download_from_s3 tools now support user configuration.
日志支持落盘为文件，便于排查与归档；服务启动时自动恢复中断的后台任务。 / Logs are now written to disk as files for easier troubleshooting, and interrupted background tasks are automatically recovered on service startup.

Bug 修复 / Bug Fixes

完成上下文预算契约迁移，增加有界压缩与真实溢出恢复，长对话不再丢失上下文。 / Completed the context budget contract migration with bounded compaction and real overflow recovery, preventing context loss in long conversations.
修复会话链路多处问题：返回后恢复会话、线程切换保留智能体、会话标题使用会话模型生成、正确渲染执行代码与对比模式下的历史保留。 / Fixed several conversation-flow issues: conversation restore after returning, agent retention across thread switches, session-model-based title generation, correct execution-code rendering, and history retention in compare mode.
修复多模态网关适配器缓存键缺陷，模型配置变更后不再使用过期适配器。 / Fixed the multimodal gateway adapter cache keying defect so model configuration changes no longer serve stale adapters.
修复模型健康管理问题：部分绑定模型健康检查失败时智能体仍可用，健康检查改为内联图标入口，embedding 连通性探测通过的 base_url 正确持久化，被删除模型给出明确提示。 / Fixed model health management: agents stay available when some bound models fail health checks, the health check moved to an inline icon, the embedding base_url validated by probing is persisted correctly, and deleted models now show clear notices.
修复知识库问题：删除中的知识文件/知识库处理、AIDP 知识库保存与会话向量模型提示、搜索范围提示准确性，以及损坏数据跳过处理。 / Fixed knowledge-base issues: in-flight knowledge file and knowledge base deletion, AIDP knowledge base saving and session vector model prompts, accurate search scope notices, and corrupted data skipping.
修复评估模块的页签统计过期与流式关键字重复问题。 / Fixed stale tab totals and duplicate stream keywords in the evaluation module.
修复多租户存储配额、复制智能体名称冲突及旧版 Docker 沙箱容器启动失败等问题。 / Fixed tenant storage quota restoration, copied agent name conflicts, and sandbox container startup failures on older Docker versions.

文档与部署变化 / Docs & Deployment Changes

新增 nexent-infrastructure Helm Chart（Elasticsearch、PostgreSQL、Redis、MinIO）并配置健康探针；项目配置支持在 Docker 与 Kubernetes 部署间持久化，并修复 K8s 离线部署的镜像加载、共享存储 PV 渲染与离线技能资产问题。 / Added the nexent-infrastructure Helm chart (Elasticsearch, PostgreSQL, Redis, MinIO) with health probes; project configuration now persists across Docker and Kubernetes deployments, with fixes for K8s offline image loading, shared-storage PV rendering, and offline skill assets.
数据库初始化改为幂等，统一标签迁移整合为 v2.5.2 版本化脚本，新增 v2.6.0 推理参数等增量迁移。 / Made database bootstrap idempotent, consolidated unified tag migrations into the versioned v2.5.2 script, and added incremental migrations including v2.6.0 inference parameters.
完善中英文文档体系（Mermaid 图表、侧边栏本地搜索），新增智能体评估用户指南与第三方资源集成文档，并更新自动化测试与离线包构建流水线。 / Improved the bilingual documentation system (Mermaid diagrams, sidebar local search), added the agent evaluation user guide and third-party resource integration docs, and updated the automated testing and offline package build pipelines.