Zervanor — 智能體員工隊伍

連接器目錄化身为智能體員工。

每個通過認證的連接器都會自動投影為 AI 智能體可以調用的 Tool 技能。因此,驅動一鍵範本的相同原生包也驅動著一個受監管的智能體員工隊伍——規劃中涵蓋運行在單一執行期上的 4 層架構 40 個智能體

Live通用智能體執行期外殼
26已建構的第一方智能體
Live智能體控制台 (配置 · 檢查工具 · 執行目標)
404 層架構下的智能體目錄目標數量

執行期、首批兩個智能體、BYOK 大模型和管理控制台今日已上線。底層的第 2 至 4 層為順次開發計劃,尚未交付。

First-party agents

Ready-to-run agents hosted on the Zervanor runtime. Each runs as an isolated pod in the same runtime as your workflows.

AI Assistant

ai-agent
Live

Conversational AI assistant with connector-backed tools. Built on the Generic Agentic Runtime shell (ADR-038): understands goals in natural language, uses available connector tools to take real action

operations ai 1 capabilities Details →

Content Agent

content-agent
Live

Content operations agent: drafting, editorial calendar, and social scheduling across CMS and publishing tools. Built on the Generic Agentic Runtime shell (ADR-038).

operations ai 1 capabilities Details →

Data Agent

data-agent
Live

Autonomous data and analytics agent. Queries databases and BI tools, transforms raw results into readable reports, identifies trends and anomalies, and delivers summaries via email or Slack. Read-only

operations ai 1 capabilities Details →

DevOps Agent

devops-agent
Live

Autonomous DevOps and infrastructure agent. Monitors deployments, triages incidents, coordinates on-call via PagerDuty, checks GitHub PR status, and automates routine ops tasks — across GitHub, Kubern

operations ai 1 capabilities Details →

E-commerce Agent

ecommerce-agent
Live

E-commerce operations agent: order management, inventory tracking, and fulfillment across store platforms. Built on the Generic Agentic Runtime shell (ADR-038).

operations ai 1 capabilities Details →

Education Agent

education-agent
Live

Education operations agent: student progress tracking and feedback across LMS and scheduling tools. Built on the Generic Agentic Runtime shell (ADR-038).

operations ai 1 capabilities Details →

Executor Agent

executor-agent
Live

Multi-step automation archetype: reliably executes a defined multi-step procedure end to end, idempotently. Built on the Generic Agentic Runtime shell (ADR-038).

operations ai 1 capabilities Details →

Finance Agent

finance-agent
Live

Finance operations agent: invoicing, AP/AR, expense approvals, and reconciliation across accounting and payment tools. Built on the Generic Agentic Runtime shell (ADR-038).

operations ai 1 capabilities Details →

generic-agent

generic-agent
Live

Generic Agentic Runtime shell (ADR-038). One configurable runtime: a new agent product is this shell + a manifest (system prompt + tool bindings), not a new codebase. ReAct planning loop over AG-02 co

operations ai 1 capabilities Details →

HR Agent

hr-agent
Live

HR operations agent: employee onboarding, policy Q&A, and time-off handling across HRIS and chat tools. Built on the Generic Agentic Runtime shell (ADR-038).

operations ai 1 capabilities Details →

Legal Agent

legal-agent
Live

Legal review agent: contract clause review and risk flagging — read-only, escalates to counsel. Built on the Generic Agentic Runtime shell (ADR-038).

operations ai 1 capabilities Details →

Marketing Agent

marketing-agent
Live

Marketing analytics agent: campaign performance analysis, segmentation, and reporting across ad and email tools. Built on the Generic Agentic Runtime shell (ADR-038).

operations ai 1 capabilities Details →

Monitor Agent

monitor-agent
Live

Threshold-alerting archetype: evaluates a metric or condition against a threshold and reports status or raises an alert. Built on the Generic Agentic Runtime shell (ADR-038).

operations ai 1 capabilities Details →

Planner Agent

planner-agent
Live

Domain-agnostic multi-phase task orchestrator: decomposes a complex goal into ordered phases and drives each with real tools. Built on the Generic Agentic Runtime shell (ADR-038).

operations ai 1 capabilities Details →

Project Manager Agent

pm-agent
Live

Project management agent: sprint planning, standup summaries, and backlog grooming across issue trackers. Built on the Generic Agentic Runtime shell (ADR-038).

operations ai 1 capabilities Details →

Real Estate Agent

realestate-agent
Live

Real estate operations agent: listing management, lead qualification, and showing scheduling across CRM tools. Built on the Generic Agentic Runtime shell (ADR-038).

operations ai 1 capabilities Details →

Recruiting Agent

recruiting-agent
Live

Recruiting agent: CV screening, candidate ranking, and interview scheduling across ATS and calendar tools. Built on the Generic Agentic Runtime shell (ADR-038).

operations ai 1 capabilities Details →

Research Agent

research-agent
Live

Autonomous research specialist. Given a research goal, gathers information from connected sources (web, documents, APIs), synthesizes findings, and returns a structured research report. Read-only tool

operations ai 1 capabilities Details →

Responder Agent

responder-agent
Live

Context-aware Q&A archetype: answers questions grounded in retrieved data and tool calls, with citations. Built on the Generic Agentic Runtime shell (ADR-038).

operations ai 1 capabilities Details →

Sales Agent

sales-agent
Live

Autonomous sales operations agent. Manages CRM pipelines, enriches prospect data, drafts outreach, tracks deal activity, and surfaces revenue insights — across HubSpot, Salesforce, email, and calendar

operations ai 1 capabilities Details →

Security Agent

security-agent
Live

Security operations agent: threat-alert triage and audit-log review — read-only, escalates incidents. Built on the Generic Agentic Runtime shell (ADR-038).

operations ai 1 capabilities Details →

Slack AI Agent

slack-agent
Live

Conversational AI over Slack (Socket Mode) powered by the Generic Agentic Runtime shell (ADR-038, PH-AG-03C). Every inbound DM or @mention drives a ReAct planning loop that can use connector tools to

operations provider 2 capabilities Details →

Support Agent

support-agent
Live

Autonomous customer support agent. Triages incoming tickets, routes to the right queue, drafts responses from knowledge base, escalates when needed, and keeps Slack updated — across Zendesk, Freshdesk

operations ai 1 capabilities Details →

Uptime Watcher

uptime-watcher
Live

L3 Ambient Watcher: on a schedule, evaluates endpoint/service uptime against a threshold and raises an ALERT verdict when degraded, cascading to a role agent. Built on the Generic Agentic Runtime shel

operations ai 1 capabilities Details →

WhatsApp AI Agent

whatsapp-agent-v2
Live

Conversational AI over WhatsApp powered by the Generic Agentic Runtime shell (ADR-038). Replaces command rules with LLM intelligence: every inbound message drives a ReAct planning loop that can use co

operations provider 2 capabilities Details →

whatsapp-agent

whatsapp-agent
Live

WhatsApp provider agent built with Zervanor Agent SDK

operations provider 2 capabilities Details →

創建新智能體只需配置清單,無需新建代碼庫。

統一的通用智能體執行期外殼(ADR-038)負責運行每一個智能體。打造新功能只需配置 agent.manifest.json——定義系統提示詞、規劃模式、記憶模式和精選工具綁定,然後通過 zervanor push 部署。無需編寫定制代碼,無需新建倉庫。

  • ReAct 規劃閉環——思考 → 行動 → 觀察,在啟動時從連接器目錄自動載入工具。
  • 自帶模型——目前通過提供商/base-url 抽象層支援 OpenAI / Gemini,平台永遠不會硬編碼綁定單一廠商。
  • 治理完備——租戶物理隔離、精選工具白名單,以及為智能體量身定制的人工協同(HITL)審批策略。
{
  "id": "support-agent",
  "agentic": {
    "system_prompt": "You triage support tickets…",
    "planning_mode": "react",
    "memory_mode": "session",
    "tool_sources": ["zendesk", "slack"],
    "tool_policy": { "require_confirmation": true }
  }
}
全新 — 執行階段與模型

在平台上執行——或在你自己的裝置上。

同一個代理程式既能在受管雲端執行,也能在你自己的機器上執行,透過路由組合雲端與本機模型,並可透過聊天介面存取。

雲端或你的裝置

同一個代理程式(一個 manifest、一個 SDK)可在受管雲端 Pod 中執行,或透過 Zervanor Desktop 應用程式在你的機器上執行。它向外連線,因此能在防火牆後運作。

智慧模型路由

將雲端、平台與本機模型統一到一個目錄,背後是具名路由器與自動容錯移轉。為每個代理程式選擇模型;需要時在本機執行推論。

對話(Conversations)

一個持久、依模型路由的聊天,可將你的連接器與代理程式作為工具呼叫——在變更任何內容之前都有確認步驟。

目前為桌面執行階段主機;行動主機已在路線圖中。

統一的執行期。完整的智能體團隊。