Agentic-Org 是 AI Skill Hub 本期精选Agent工作流之一。综合评分 7.5 分,整体质量较高。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。
Agentic-Org是开源AI工作流平台,提供企业级AI代理协调功能。
Agentic-Org 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
Agentic-Org是开源AI工作流平台,提供企业级AI代理协调功能。
Agentic-Org 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:pip 安装(推荐)
pip install agentic-org
# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install agentic-org
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/mishrasanjeev/agentic-org
cd agentic-org
pip install -e .
# 验证安装
python -c "import agentic_org; print('安装成功')"
# 命令行使用
agentic-org --help
# 基本用法
agentic-org input_file -o output_file
# Python 代码中调用
import agentic_org
# 示例
result = agentic_org.process("input")
print(result)
# agentic-org 配置文件示例(config.yml) app: name: "agentic-org" debug: false log_level: "INFO" # 运行时指定配置文件 agentic-org --config config.yml # 或通过环境变量配置 export AGENTIC_ORG_API_KEY="your-key" export AGENTIC_ORG_OUTPUT_DIR="./output"
AI Virtual Employee Platform — LangGraph agents, 1000+ integrations (via Composio), native connectors and tools. Agents call real APIs (Jira, HubSpot, GitHub, GSTN, Tally, Banking AA) — not just generate text. Voice agents, RAG knowledge base, smart LLM routing, industry packs, PII redaction, browser RPA, CFO/CMO dashboards, ABM dashboard, NL Query (Cmd+K), multi-company support, scheduled reports, A/B testing, email drip engine, web push HITL, Python/TypeScript SDKs, MCP server, human-in-the-loop governance, no-code builder.
Live counts for agents, connectors, tools, and product version come from GET /api/v1/product-facts. Anywhere a count appears in the UI it is fetched from that endpoint — do not hand-edit numbers in docs or pages; they will drift.
Live: https://agenticorg.ai | App: https://app.agenticorg.ai | Playground: https://agenticorg.ai/playground
---
pip install -r requirements.txt # Core platform (required) pip install -r requirements-v4.txt # v4 features (optional) pip install -r requirements-dev.txt # Dev tools (optional)
Describe business processes in plain English (e.g., "Automate invoice approval when amount > 5L") and the system generates the complete workflow definition. Preview before deploying.
AgenticOrg provides three requirements files for different deployment scenarios:
| File | Packages | Purpose | Required? |
|---|---|---|---|
requirements.txt | 45 pinned | Core platform (API, agents, workflows, connectors, auth) | **Yes** |
requirements-v4.txt | 4 | v4 features: Composio 1000+ tools, RouteLLM smart routing, Presidio PII redaction | Optional (graceful degradation) |
requirements-dev.txt | 11 | Development: pytest, ruff, mypy, bandit, pre-commit | For contributors only |
All versions in requirements.txt are pinned to exact production-tested versions (2026-04-06).
docker compose --profile ragflow up -d # Knowledge Base (RAGFlow)
docker compose --profile voice up -d # Voice Agents (LiveKit)
docker compose --profile airgap up -d # Local LLM (Ollama, CPU)
docker compose --profile airgap-gpu up -d # Local LLM (vLLM, GPU)
```bash docker compose up -d
bash scripts/deploy_cloud_run.sh --yes
bash scripts/deploy_cloud_run.sh --sha <commit-sha> --skip-build --with-migrations --yes
python -m pytest tests/unit/test_oacp_c6x4_durable_cache_repository.py tests/unit/test_oacp_c6x5_cache_maintenance.py tests/unit/test_deploy_cloud_run_script.py tests/regression/test_security_audit_20260613_dependency_gates.py -q
| Role | Password | |
|---|---|---|
| CEO | ceo@agenticorg.local | ceo123! |
| CFO | cfo@agenticorg.local | cfo123! |
| CHRO | chro@agenticorg.local | chro123! |
| CMO | cmo@agenticorg.local | cmo123! |
| COO | coo@agenticorg.local | coo123! |
| Auditor | auditor@agenticorg.local | audit123! |
---
COMPOSIO_API_KEY — 1000+ tool integrations (optional)
AGENTICORG_LLM_ROUTING — auto | tier1 | tier2 | tier3 | disabled
AGENTICORG_LLM_MODE — cloud | local | auto
AGENTICORG_PII_REDACTION_MODE — before_llm | logs_only | disabled
RAGFLOW_API_URL — RAGFlow instance URL for knowledge base
RAGFLOW_API_KEY — RAGFlow API key
LIVEKIT_URL — LiveKit server URL for voice agents
LIVEKIT_API_KEY — LiveKit API key
LIVEKIT_API_SECRET — LiveKit API secret
STRIPE_SECRET_KEY — Stripe billing key (hosted tier)
STRIPE_WEBHOOK_SECRET — Stripe webhook signing secret
Natural language search across all your business data: - Cmd+K Search Bar — global shortcut opens search from any page - Slide-out Chat Panel — full conversational interface with agent attribution - Agent Attribution — every answer shows which agent(s) provided the data - Example Queries: "What's my cash position?", "Show me AP aging over 90 days", "How did Google Ads perform last week?", "What's our DSO this quarter?"
Finance (11): Oracle Fusion, SAP, Tally (XML/TDL + bridge), GSTN (Adaequare 2-step + DSC), Stripe, QuickBooks, Zoho Books, Banking AA (RBI consent), Income Tax India, Pine Labs (Plural), NetSuite HR (8): Darwinbox, Okta, Greenhouse, LinkedIn Talent, DocuSign, Keka, Zoom, EPFO Marketing (19): Salesforce, HubSpot, Google Ads, LinkedIn Ads, Meta Ads, Ahrefs, Mixpanel, Buffer, Brandwatch, GA4, MoEngage, WordPress, Twitter/X, YouTube, Mailchimp, Semrush, Bombora, G2, TrustRadius Ops (7): Jira, ServiceNow, Zendesk, PagerDuty, Confluence, Sanctions API, MCA Portal Comms (9): Slack, GitHub, Gmail, SendGrid, GCS, Google Calendar, Twilio, WhatsApp, LangSmith
Every connector uses real API endpoints from official documentation. Zero stubs. The Tally connector uses native XML/TDL protocol with a bridge agent for on-premise instances. Banking AA follows RBI-compliant consent flow. GSTN uses Adaequare's 2-step authentication with DSC signing for filing.
uvicorn api.main:app --host 0.0.0.0 --port 8000 --reload
```
Base URL: https://app.agenticorg.ai/api/v1
| Method | Path | Auth | Description |
|---|---|---|---|
| GET | /health/liveness | No | Health check |
| POST | /auth/signup | No | Create account |
| POST | /auth/login | No | Get JWT token |
| POST | /auth/google | No | Google OAuth |
| POST | /auth/forgot-password | No | Request password reset email |
| POST | /auth/reset-password | No | Reset password with token |
| POST | /demo-request | No | Demo form → lead + sales agent |
| GET | /agents | JWT | List agents (RBAC filtered) |
| POST | /agents | JWT | Create agent (tools auto-populated by type/domain) |
| POST | /agents/generate | JWT | Generate launchable agent config from plain English |
| POST | /agents/{id}/run | JWT | Execute agent |
| PATCH | /agents/{id} | JWT | Update (prompt lock on active) |
| GET | /agents/org-tree | JWT | Org chart tree (department hierarchy) |
| POST | /agents/import-csv | JWT | Bulk import agents via CSV |
| POST | /agents/{id}/clone | JWT | Clone with persona |
| POST | /agents/{id}/promote | JWT | Shadow → Active (shadow limit enforcement) |
| GET | /agents/{id}/prompt-history | JWT | Prompt audit trail |
| GET | /prompt-templates | JWT | List templates |
| POST | /prompt-templates | JWT | Create template |
| GET | /sales/pipeline | JWT | Sales pipeline |
| POST | /sales/pipeline/process-lead | JWT | Trigger sales agent |
| POST | /sales/process-inbox | JWT | Process Gmail replies |
| GET | /sales/metrics | JWT | Weekly digest data |
| GET | /workflows | JWT | List workflows |
| POST | /workflows/generate | JWT | Generate workflow definition from plain English |
| GET | /workflows/templates | JWT | List workflow templates |
| POST | /workflows | JWT | Create workflow |
| POST | /workflows/{id}/run | JWT | Start workflow run |
| GET | /workflows/runs/{id} | JWT | Get workflow run status and steps |
| GET | /approvals | JWT | HITL approval queue |
| GET | /audit | JWT | Audit log |
| GET | /kpis/cfo | JWT | CFO dashboard KPIs |
| GET | /kpis/cmo | JWT | CMO dashboard KPIs |
| POST | /chat/query | JWT | NL Query (natural language question) |
| GET | /chat/history | JWT | Chat history for current user |
| POST | /knowledge/search | JWT | Search tenant knowledge base |
| GET | /companies | JWT | List companies (multi-company) |
| POST | /companies | JWT | Create company entity |
| PATCH | /companies/{id} | JWT | Update company entity |
| GET | /report-schedules | JWT | List scheduled reports |
| POST | /report-schedules | JWT | Create scheduled report |
| PATCH | /report-schedules/{id} | JWT | Update scheduled report |
| POST | /report-schedules/{id}/run-now | JWT | Trigger immediate report run |
| DELETE | /report-schedules/{id} | JWT | Delete scheduled report |
| GET | /connectors | JWT | List native connectors (count from /product-facts) |
| GET | /connectors/registry | JWT | Connector registry (all registered connectors + tool counts) |
| GET | /connectors/{id}/health | JWT | Connector health check |
| GET | /connectors/{id} | JWT | Connector details |
| PUT | /connectors/{id} | JWT | Update connector config |
| POST | /org/api-keys | Admin | Generate API key (ao_sk_ prefix) |
| GET | /org/api-keys | Admin | List API keys |
| DELETE | /org/api-keys/{id} | Admin | Revoke API key |
| GET | /a2a/agent-card | No | A2A agent discovery card |
| GET | /a2a/agents | No | A2A launchable agent catalog |
| POST | /a2a/tasks | JWT/Grantex | Execute A2A task |
| GET | /mcp/tools | No | List MCP tools (see /api/v1/product-facts.tool_count) |
| POST | /mcp/call | JWT/Grantex | Call MCP tool |
| POST | /sop/upload | JWT | Upload and parse SOP document |
| POST | /sop/parse-text | JWT | Parse SOP text |
| POST | /sop/deploy | JWT | Deploy parsed SOP as agent |
| POST | /agents/{id}/delegate | JWT | Grantex delegation setup |
pip install agenticorg is the canonical Python install path for both the SDK and the direct agenticorg CLI. Use the CLI from shell-capable assistants and developer environments such as Claude Code, Codex, Gemini CLI, VS Code tasks/terminals, CI jobs, and customer runbooks. Use the MCP server when the client supports Model Context Protocol and should call AgenticOrg as tools.
pip install agenticorg
from agenticorg import AgenticOrg
client = AgenticOrg(api_key="ao_sk_your_key_here")
result = client.agents.run("ap_processor", inputs={"invoice_id": "INV-001"})
agents = client.agents.list()
commerce = client.agents.run(
"commerce_sales_agent",
action="buyer_discovery_preview",
inputs={"merchant_id": "merchant_demo", "query": "Show laptops under Rs 50000"},
)
draft_agent = client.agents.generate("Create a contract intelligence agent using Confluence and Jira")
kb = client.knowledge.search("vendor renewal policy", top_k=3)
workflow_draft = client.workflows.generate("Review vendor renewal risk using KB and Jira, then notify vendor_manager")
workflow = client.workflows.create(name="Renewal Risk Review", definition=workflow_draft["workflow"], domain="ops")
run = client.workflows.run(workflow["id"], payload={"vendor_id": "V-100"})
sop = client.sop.parse_text("When invoice > 5L, require CFO approval")
card = client.a2a.agent_card()
npm install agenticorg-sdk
import { AgenticOrg } from "agenticorg-sdk";
const client = new AgenticOrg({ apiKey: "ao_sk_your_key_here" });
const result = await client.agents.run("ap_processor", { inputs: { invoice_id: "INV-001" } });
const commerce = await client.agents.run("commerce_sales_agent", {
action: "buyer_discovery_preview",
inputs: { merchant_id: "merchant_demo", query: "Show laptops under Rs 50000" },
});
const draftAgent = await client.agents.generate("Create a contract intelligence agent using Confluence and Jira");
const kb = await client.knowledge.search("vendor renewal policy", { topK: 3 });
const workflowDraft = await client.workflows.generate("Review vendor renewal risk using KB and Jira, then notify vendor_manager");
const agents = await client.agents.list();
API keys provide programmatic access for SDKs, CLI, and MCP integrations.
ao_sk_ prefix (e.g., ao_sk_a1b2c3...)POST /api/v1/org/api-keysagenticorg:admin scopeDELETE /api/v1/org/api-keys/{id}---
python tests/test_production_connectors.py ```
| Suite | Tests | What It Covers |
|---|---|---|
| Backend (pytest) | See CI | Unit, security, connector harness (every native connector × exposed tools), synthetic data, regression, integration, voice, RAG, RPA, packs |
| Frontend (vitest) | **93** | Component tests, hooks, utilities |
| Playwright E2E | **17 spec files** | Full browser flows: login, onboarding, agents, workflows, approvals, landing, SOP, dashboards, ABM, drip, A/B, push |
| CI E2E | Enabled | Runs against production on every merge to main |
---
Production-ready workflow templates that combine multiple agents: <div class="rdm-tbl-wrap"><table class="rdm-tbl"><thead><tr><th>Template</th><th>Domain</th><th>Description</th></tr></thead><tbody><tr><td>invoice_to_pay_v3</td><td>Finance</td><td>PDF parse --> GSTIN --> 3-way match --> payment execution</td></tr><tr><td>month_end_close</td><td>Finance</td><td>Trial balance --> adjustments --> reconciliation --> close</td></tr><tr><td>daily_treasury</td><td>Finance</td><td>Cash position --> sweep --> forecast --> report</td></tr><tr><td>tax_calendar</td><td>Finance</td><td>Deadline tracking --> filing prep --> DSC signing</td></tr><tr><td>campaign_launch</td><td>Marketing</td><td>Brief --> content --> review --> publish --> monitor</td></tr><tr><td>content_pipeline</td><td>Marketing</td><td>Ideation --> draft --> SEO --> approval --> publish</td></tr><tr><td>lead_nurture</td><td>Marketing</td><td>Scoring --> segmentation --> drip --> wait_for_event --> handoff to sales</td></tr><tr><td>weekly_marketing_report</td><td>Marketing</td><td>Collect metrics --> build report --> deliver</td></tr><tr><td>email_drip_sequence</td><td>Marketing</td><td>Behavior-triggered email sequences (open/click/time delays)</td></tr><tr><td>ab_test_campaign</td><td>Marketing</td><td>Create variants --> run test --> auto-winner selection --> CMO override --> send winner</td></tr><tr><td>abm_campaign</td><td>Marketing</td><td>CSV upload targets --> intent scoring (Bombora/G2/TrustRadius) --> personalized outreach</td></tr><tr><td>incident_response</td><td>Ops</td><td>Triage --> Jira ticket --> assign --> monitor --> resolve</td></tr><tr><td>lead_to_revenue</td><td>Sales</td><td>Qualify --> outreach --> follow-up --> close</td></tr><tr><td>weekly_devops_health</td><td>Ops</td><td>GitHub + Jira metrics --> health score --> report</td></tr></tbody></table></div>
The /integration-workflow page provides a visual guide for connecting external systems, with SDK/CLI quickstart examples and protocol documentation.
---
AgenticOrg 是一个领先的 AI Virtual Employee Platform(AI 虚拟员工平台)。它基于 LangGraph 构建智能 Agent,通过 Composio 集成了超过 1000 种外部工具,使其不仅能生成文本,更能直接调用 Jira、HubSpot、GitHub、Tally 及 Banking AA 等真实 API 执行任务。平台支持 Voice agents、RAG 知识库、智能 LLM routing 以及 PII 脱敏等企业级功能,并提供 CFO/CMO 专用仪表盘,支持多公司管理与自动化任���调度,是构建企业级 Agentic 工作流的核心基础设施。
核心功能涵盖了从自动化流程到企业级合规的全方位能力。平台支持通过自然语言构建 NL Workflow,实现业务流程的自动化;内置 RAG 知识库与智能 LLM routing,确保响应的准确性与成本优化;具备强大的 PII redaction(隐私脱敏)能力,保障数据安全。此外,平台还提供浏览器 RPA、语音 Agent 以及针对财务与营销场景定制的专业 Dashboard,能够通过 NL Query 实现对业务数据的自然语言交互。
在开始部署前,请确保您的开发环境已安装 Python 3.11+(已在 3.12 和 3.13 版本上完成测试)、Node.js 20+ 以及 Docker。项目提供了多个 requirements.txt 文件以满足不同需求:`requirements.txt` 用于安装核心平台(包含 API、agents、connectors 等必备组件);`requirements-v4.txt` 用于启用 v4 高级特性(如 Composio 工具集、RouteLLM 路由及 Presidio PII 脱敏);`requirements-dev.txt` 则用于开发环境配置。
安装过程分为 Python 依赖安装与 Docker 服务部署两部分。首先,根据需求使用 pip 安装对应的 requirements 文件。对于需要知识库(RAGFlow)、语音 Agent(LiveKit)或本地 LLM(Ollama/vLLM)的场景,建议使用 Docker Compose 进行部署。例如,通过 `docker compose --profile ragflow up -d` 启动知识库服务,或使用 `airgap` 配置模式实现本地化部署,确保在不同网络环境下都能灵活运行。
平台提供了直观的 NL Workflow Builder,用户只需使用纯英文描述业务逻辑(例如:“当金额大于 5L 时自动审批发票”),系统即可自动生成完整的 Workflow 定义,并在部署前支持预览。对于数据查询,用户可以通过全局快捷键 Cmd+K 唤起 NL Query 界面,通过对话式交互获取业务数据,且每个回答都会通过 Agent Attribution 明确标注数据来源,确保结果的可追溯性。
项目通过环境变量进行精细化配置。关键参数包括:`COMPOSIO_API_KEY` 用于连接 1000+ 外部工具;`AGENTICORG_LLM_ROUTING` 用于控制智能路由模式(如 auto, tier1 等);`AGENTICORG_LLM_MODE` 决定使用 Cloud 还是 Local 模型;`AGENTICORG_PII_REDACTION_MODE` 用于设置隐私脱敏策略。此外,针对 RAGFlow 和 LiveKit 等外部服务,需配置相应的 API URL 与 Key 以实现无缝集成。
AgenticOrg 提供了强大的 NL Query 接口,支持通过自然语言对所有业务数据进行搜索。用户可以通过全局快捷键 Cmd+K 快速打开搜索栏,或使用侧边栏聊天面板进行深度对话。系统具备完善的 Agent Attribution 机制,能够清晰展示每条信息的提供者。同时,平台内置了丰富的 Native Enterprise Connectors,涵盖了 Finance(如 Oracle, SAP, Tally, Stripe)与 Marketing(如 Salesforce)等领域的真实 API 端点。
平台内置了 15 个生产级 Workflow Templates,涵盖了复杂的业务场景。例如,Finance 领域的 `invoice_to_pay_v3` 模板可以实现从 PDF 解析、GSTIN 校验到 3-way match 及最终支付执行的全自动化流程;`month_end_close` 模板则用于处理月度结账中的试算平衡与调整任务。此外,通过 `/integration-workflow` 页面,用户可以获得可视化的外部系统连接指南及 SDK/CLI 快速入门示例。
Agentic-Org是一个开源的AI工作流平台,提供了企业级的AI代理协调功能,但其星数较少,可能需要进一步优化。
该工具使用 NOASSERTION 协议,商用场景请仔细阅读协议条款,必要时咨询法律意见。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
📄 NOASSERTION — 请查阅原始协议条款了解具体使用限制。
经综合评估,Agentic-Org 在Agent工作流赛道中表现稳健,质量良好。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | agentic-org |
| 原始描述 | 开源AI工作流:Agentic-Org is an open-source, enterprise-grade AI agent orchestration platform.。⭐7 · Python |
| Topics | workflowpython |
| GitHub | https://github.com/mishrasanjeev/agentic-org |
| License | NOASSERTION |
| 语言 | Python |
收录时间:2026-05-17 · 更新时间:2026-05-30 · License:NOASSERTION · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端