[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72160":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":25,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":39,"readmeContent":40,"aiSummary":41,"trendingCount":16,"starSnapshotCount":16,"syncStatus":42,"lastSyncTime":43,"discoverSource":44},72160,"nexent","ModelEngine-Group\u002Fnexent","ModelEngine-Group","Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skills, memory, and orchestration with built-in constraints, feedback loops, and control planes.","https:\u002F\u002Fnexent.tech",null,"Python",4988,634,218,222,0,61,184,545,183,110.41,"MIT License",false,"main",true,[27,28,29,30,31,32,33,34,35,36,37,38],"agent","agentic-ai","agentic-framework","agentic-rag","agentic-workflow","ai","harness","harness-engineering","llm","mcp","multi-agent","rag","2026-06-12 04:01:03","![Nexent Banner](.\u002Fassets\u002FNexentBanner.png)\n\n[![Website](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FWebsite-blue?logo=icloud&logoColor=white)](https:\u002F\u002Fnexent.tech)\n[![English](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FEnglish-README-blue?logo=github)](README.md)\n[![中文](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F中文-README-green?logo=github)](README_CN.md)\n[![Documentation](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDocumentation-CN\u002FEN-red?logo=googledocs&logoColor=%23ECD53F)](https:\u002F\u002Fmodelengine-group.github.io\u002Fnexent)\n[![Docker Pulls](https:\u002F\u002Fimg.shields.io\u002Fdocker\u002Fpulls\u002Fnexent\u002Fnexent?logo=docker&label=DockerPull)](https:\u002F\u002Fhub.docker.com\u002Frepositories\u002Fnexent)\n[![Codecov (with branch)](https:\u002F\u002Fimg.shields.io\u002Fcodecov\u002Fc\u002Fgithub\u002FModelEngine-Group\u002Fnexent\u002Fdevelop?logo=codecov&color=green)](https:\u002F\u002Fcodecov.io\u002Fgh\u002FModelEngine-Group\u002Fnexent)\n\nNexent is a zero-code platform for auto-generating production-grade AI agents, built on **Harness Engineering** principles. It provides unified tools, skills, memory, and orchestration with built-in constraints, feedback loops, and control planes — no orchestration, no complex drag-and-drop required, using pure language to develop any agent you want.\n\n> One prompt. Endless reach.\n\n\u003Cvideo controls width=\"100%\" style=\"max-width: 800px;\">\n  \u003Csource src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fdb6b7f5a-9ee8-4327-ae6f-c5af896126b4\" type=\"video\u002Fmp4\" \u002F>\n  \u003Cp>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fdb6b7f5a-9ee8-4327-ae6f-c5af896126b4\">Watch the demo video\u003C\u002Fa>\u003C\u002Fp>\n\u003C\u002Fvideo>\n\n# 🚀 Get Started Now\n\n> ⭐ Before you get started, please star us on [GitHub](https:\u002F\u002Fgithub.com\u002FModelEngine-Group\u002Fnexent) — your support drives us forward!\n\n## Option 1: Try Our Official Demo\n\nNo installation required — jump right in with our **[online demo environment](http:\u002F\u002F60.204.251.153:3000\u002Fen)** to experience Nexent's capabilities instantly.\n\n## Option 2: Deploy on Your Own\n\nIf you need to run Nexent locally or in your private infrastructure, we offer two deployment options:\n\n### System Requirements\n\n| Resource | Docker | Kubernetes |\n|----------|--------|-------------|\n| **CPU** | 4 cores (min) \u002F 8 cores (rec.) | 4 cores (min) \u002F 8 cores (rec.) |\n| **Memory** | 8 GiB (min) \u002F 16 GiB (rec.) | 16 GiB (min) \u002F 64 GiB (rec.) |\n| **Disk** | 40 GiB (min) \u002F 100 GiB (rec.) | 100 GiB (min) \u002F 200 GiB (rec.) |\n| **Architecture** | x86_64 \u002F ARM64 | x86_64 \u002F ARM64 |\n| **Software** | Docker 24+, Docker Compose v2+ | Kubernetes 1.24+, Helm 3+ |\n\n> **Note:** Recommended configurations ensure optimal performance in production environments.\n\n### Docker Deployment (Recommended for Individuals\u002FSmall Teams)\n\nQuick and straightforward for most users. Prerequisites: Docker 24+ and Docker Compose v2+:\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FModelEngine-Group\u002Fnexent.git\ncd nexent\u002Fdocker\ncp .env.example .env\nbash deploy.sh\n```\n\nFor detailed deployment instructions, see [Docker Installation](https:\u002F\u002Fmodelengine-group.github.io\u002Fnexent\u002Fen\u002Fquick-start\u002Finstallation.html).\n\n### Kubernetes Deployment (For Enterprise Production)\n\nIdeal for enterprise scenarios requiring high availability and elastic scaling. Prerequisites: Kubernetes 1.24+ and Helm 3+:\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FModelEngine-Group\u002Fnexent.git\ncd nexent\u002Fk8s\u002Fhelm\n.\u002Fdeploy-helm.sh apply\n```\n\nFor detailed deployment instructions, see [Kubernetes Installation](https:\u002F\u002Fmodelengine-group.github.io\u002Fnexent\u002Fen\u002Fquick-start\u002Fkubernetes-installation.html).\n\n# ✨ Core Features\n\nNexent provides a comprehensive feature set for building powerful AI agents:\n\n| Feature | Description |\n|---------|-------------|\n| **⚙️ Multi-Model Integration** | OpenAI-compatible with any provider, full LLM\u002FEmbedding\u002FVLM\u002FSTT\u002FTTS coverage, supports domestic model switching |\n| **🤖 Zero-Code Agent Generation** | Describe requirements in natural language, generate executable agents instantly, what you think is what you get |\n| **🤝 A2A Agent Collaboration** | Agent-to-Agent protocol enables seamless multi-agent cooperation and distributed workflows |\n| **🧠 Layered Memory Mechanism** | Two-tier memory (user-level + user-agent-level) for persistent context across conversations |\n| **📝 Progressive Skill Disclosure** | Dynamically loads Skill into context, maximizing context window efficiency |\n| **🗄️ Personal-Grade Knowledge Base** | Real-time import and intelligent retrieval for 20+ document formats, auto summaries, fine-grained access control |\n| **🔧 MCP Tool Ecosystem** | Plug-and-play extension system with custom development and third-party MCP service support |\n| **🌐 Internet Knowledge Integration** | Multi-source search blending real-time information with private data |\n| **🔍 Knowledge-Level Traceability** | Precise citations and source verification, full transparency for every fact |\n| **🎭 Multimodal Interaction** | Voice, text, images, files — comprehensive natural dialogue |\n| **🔢 Agent Version Management** | Version iteration and history rollback, safe and controllable |\n| **🏪 Agent Marketplace** | Official and community curated agents, one-click install and use |\n| **👥 Multi-Tenancy & RBAC** | Multi-tenant isolation, role-based access control, fine-grained resource management |\n\n# 🤝 Join Our Community\n\n> *If you want to go fast, go alone; if you want to go far, go together.*\n\nWe have released **Nexent v2.0**! A comprehensive upgrade from v1.0, featuring A2A protocol support, progressive Skill disclosure, layered memory mechanism, user management with multi-tenancy, agent version management, agent marketplace, and more.\n\n- **🗺️ Check our [Feature Map](https:\u002F\u002Fgithub.com\u002Forgs\u002FModelEngine-Group\u002Fprojects\u002F6)** to explore current and upcoming features.\n- **🔍 Try the current build** and leave ideas or bugs in the [Issues](https:\u002F\u002Fgithub.com\u002FModelEngine-Group\u002Fnexent\u002Fissues) tab.\n\n> *Rome wasn't built in a day.*\n\nIf our vision speaks to you, jump in via the **[Contribution Guide](https:\u002F\u002Fmodelengine-group.github.io\u002Fnexent\u002Fen\u002Fcontributing)** and shape Nexent with us.\n\nEarly contributors won't go unnoticed: from special badges and swag to other tangible rewards, we're committed to thanking the pioneers who help bring Nexent to life.\n\nMost of all, we need visibility. Star ⭐ and watch the repo, share it with friends, and help more developers discover Nexent — your click brings new hands to the project and keeps the momentum growing.\n\n# 📖 What's Next\n\nReady to dive deeper? Here are the main documentation entry points:\n\n- **[Quick Start](https:\u002F\u002Fmodelengine-group.github.io\u002Fnexent\u002Fen\u002Fquick-start\u002Finstallation.html)** — System requirements and deployment guide\n- **[Core Features](https:\u002F\u002Fmodelengine-group.github.io\u002Fnexent\u002Fen\u002Fgetting-started\u002Ffeatures.html)** — Comprehensive feature documentation\n- **[User Guide](https:\u002F\u002Fmodelengine-group.github.io\u002Fnexent\u002Fen\u002Fuser-guide\u002Fhome-page.html)** — Agent development and usage\n- **[Developer Guide](https:\u002F\u002Fmodelengine-group.github.io\u002Fnexent\u002Fen\u002Fdeveloper-guide\u002Foverview)** — Build from source and customization\n- **[FAQ](https:\u002F\u002Fmodelengine-group.github.io\u002Fnexent\u002Fen\u002Fquick-start\u002Ffaq.html)** — Common questions and troubleshooting\n\n# 📄 License\n\nNexent is licensed under the [MIT License](LICENSE).\n","Nexent 是一个零代码平台，用于自动生成生产级别的AI代理，基于Harness Engineering原则构建。它提供了统一的工具、技能、记忆和编排功能，并内置了约束、反馈循环和控制平面，无需复杂的拖放操作，仅通过纯语言即可开发所需的任何代理。该项目使用Python编写，具备强大的自动化生成能力和灵活的部署选项，支持Docker和Kubernetes部署，适用于需要快速构建和管理智能代理的各种场景，如企业级应用、个人项目或小型团队协作。MIT许可证下开源，社区活跃，拥有4443个星标和586次分支。",2,"2026-06-11 03:40:37","high_star"]