ZGI Open-Source Agent Runtime Platform Unifies Multi-Model Management, Enterprise Knowledge, and Workflow Execution
English summary
ZGI has shared its open-source Agent Runtime platform designed to run AI agents in production. The platform provides unified management of multiple models including GPT, Claude, DeepSeek, and Qwen, along with enterprise knowledge base integration. It features visual workflow composition with conditional logic, tool calls, and human approval, as well as reusable Skills for file generation and data queries. Every execution is traceable with node-level inputs, outputs, errors, and token usage. ZGI can be deployed via Docker on private infrastructure, and source code is available on GitHub and Gitee. A developer trial event offers 10,000 tokens for approximately 50 basic tasks.
Chinese summary
ZGI 公开了其开源 Agent 运行时平台，旨在将 AI Agent 真正投入生产运行。该平台统一管理 GPT、Claude、DeepSeek、Qwen 等多个模型，并集成企业知识库。通过可视化工作流可组合条件判断、工具调用和人工审核，可复用 Skills 用于文件生成、报告和计算等。每次运行均可追溯节点输入输出、错误和 Token 消耗。支持 Docker 部署到自有服务器，源代码已在 GitHub 和 Gitee 开放。即将上线的开发者体验活动提供 10,000 Token 额度，可用于约 50 次基础任务。
Key points
ZGI is an open-source Agent Runtime that unifies model, knowledge, workflow, and governance management in one workspace.
ZGI 是一款开源 Agent 运行时，在同一工作空间中整合模型、知识、工作流与运行治理。
It supports multiple LLMs (GPT, Claude, DeepSeek, Qwen), visual workflows, reusable Skills, and Docker deployment.
支持多种大模型、可视化工作流、可复用 Skills 和 Docker 部署。
Execution traces include input/output per node, errors, and token consumption for debugging.
运行追踪包含节点级输入输出、错误和 Token 消耗，便于调试。
Source code is on GitHub and Gitee; a registration trial provides 10,000 tokens for testing.
源代码托管于 GitHub 和 Gitee；新用户注册可获 10,000 Token 体验额度。