正在打开每日关注
正在打开每日关注
用自动组建、协作执行与经验沉淀,构建可持续成长的个人 AI 公司。
Introducing OpenOPC, an open-source framework for building your own AI-native company. Key features of OpenOPC: 🏗️ Self-Built OpenOPC automatically instantiates role-specific AI employees and organizes them into a fully structured, task-ready company — no manual setup required. ⚙️ Self-Run It orchestrates seamless multi-agent collaboration through structured task assignment, intelligent handoffs, peer reviews, and closed-loop execution cycles. 🌱 Self-Grown Every task run is captured as reusable organizational knowledge, enabling your AI company to continuously learn, adapt, and improve over time. Fully Open Sourced: https://t.co/sj1LlUuyOS
是什么 OpenOPC 是 HKUDS 的 MIT 开源 Python 框架,目标是把用户目标转成可运行的 AI-native company;同时提供 Task Mode 单 Agent 工作区和 Company Mode 多角色组织,入口覆盖 CLI 与 React + Phaser Office UI。仓库目前有 1,576 stars,创建于 2026-07-01,最近提交于 2026-08-29。
核心设计 Self-Built 根据目标生成组织图与汇报关系,在复用既有员工与招募新员工间选择;Self-Run 用工作项状态机驱动 execute、delegate、review、integrate、rework 五类动作,依赖 DAG 决定并行与等待,阻塞可转交,越权问题升级给人类;Self-Grown 将反馈归因到实际负责角色,把轨迹提炼成个人经验和共享 playbook。
关键洞察 它的核心不是多一个聊天入口,而是把角色、责任、状态、审查和组织记忆连成闭环,适合跨职能、长链路交付。kanban 与 office 视图进一步把组织和执行进度变成可观测状态。
边界与风险 README 仍明确保留人工升级、审批和外部 agent 配置,自动化并非无监督运行;使用需 Python 3.10+、LLM key,并验证各类 agent 集成。关注度不能代替对可靠性、成本和安全性的生产验证。