# AgenticOrg > AgenticOrg is an Apache-2.0 enterprise AI agent platform for building, running, and governing agent workflows with scoped tools, human approvals, audit evidence, SDKs, protocol integrations, and bounded OACP commerce surfaces. ## Canonical facts - Website: https://agenticorg.ai - Application and API: https://app.agenticorg.ai - Repository: https://github.com/mishrasanjeev/agentic-org - Source version: 4.8.0 from pyproject.toml - Runtime requirement: Python >=3.12 - Web application: React 19 - Managed production: separate API and UI services on Google Cloud Run - License: Apache License 2.0 - Live product facts: [https://app.agenticorg.ai/api/v1/product-facts](https://app.agenticorg.ai/api/v1/product-facts) The product facts endpoint is authoritative for the deployed version and current agent_count, connector_count, and tool_count. Do not infer totals by counting files, aliases, or tool bindings. ## What AgenticOrg does - Runs built-in and tenant-created agents through authenticated APIs and a web application. - Orchestrates workflows, schedules, scoped tool calls, approvals, evaluations, and audit records. - Connects to native provider adapters and optional integration gateways when credentials and scopes are configured. - Provides REST, Python, TypeScript, CLI, MCP, and A2A interfaces. - Supports knowledge, reporting, notifications, voice, RPA, and local models when their services are configured. - Supports Shopify read-only sync, OACP artifact caching, buyer-safe answers, public commerce surfaces, and non-executing handoff preparation. ## Boundaries - A connector listing is not proof that a tenant configured credentials or provider access. - Model-backed work requires a supported cloud provider or configured local model runtime. - Optional channels and provider rails require separate approvals, secrets, callbacks, and adapters. - OACP artifacts cannot create orders, inventory holds, mandates, payments, refunds, or paid states. - Merchant, bank, payment, POS, and SaaS providers remain sources of record. - Examples and editorial pages are not performance guarantees. - Repository security controls are not a claim of third-party certification. ## Hosted pricing - Free: $0/month or INR 0/month; 3 agents; 1000 runs; 1 GB storage. - Pro: $2/month or INR 9,999/month; 15 agents; 10000 runs; 50 GB storage. - Enterprise: $499/month or INR 49,999/month; Unlimited agents; Unlimited runs; Unlimited storage. Pricing comes from core/billing/catalog.py. Infrastructure, model, provider, and external API costs are separate. ## Key public pages - [AgenticOrg](https://agenticorg.ai): AgenticOrg is an open-source enterprise agent platform for designing workflows, connecting business systems, applying approval and policy controls, evaluating behavior, and retaining evidence of agent actions. - [Pricing](https://agenticorg.ai/pricing): AgenticOrg offers Free, Pro, and Enterprise tiers. Published limits and prices are generated from the same plan definitions used by the billing service. - [Agent Playground](https://agenticorg.ai/playground): The public playground demonstrates representative agent interactions with sample data. Its outputs are examples, not production decisions or performance guarantees. - [Agent Evaluations](https://agenticorg.ai/evals): AgenticOrg evaluations help teams assess quality, safety, reliability, security, latency, and cost before promoting an agent from testing into governed use. - [Integration Workflow](https://agenticorg.ai/integration-workflow): The integration workflow takes a connection from discovery through scoped configuration, validation, shadow testing, approval, activation, and ongoing audit. - [Open Agentic Commerce Protocol](https://agenticorg.ai/open-agentic-commerce-protocol): OACP separates commerce discovery evidence from execution authority. AgenticOrg can cache scoped artifacts and prepare a handoff, but cached evidence does not create an order, payment, mandate, inventory hold, refund, or paid state. - [How Grantex Works](https://agenticorg.ai/how-grantex-works): Grantex represents delegated authority as bounded, inspectable artifacts. AgenticOrg validates the applicable scope and context before an authorized action or evidence-backed handoff. - [AI Agents for CA Firms](https://agenticorg.ai/solutions/ca-firms): AgenticOrg can help CA firms coordinate repeatable client-service workflows while keeping filings, payments, and other consequential actions within configured approval and provider boundaries. - [AI Agents for Finance](https://agenticorg.ai/solutions/cfo): Finance teams can compose agents around defined tasks and data sources while retaining human approval for high-impact actions and evidence for review. - [AI Agents for HR](https://agenticorg.ai/solutions/chro): HR teams can use agents for repeatable coordination and information tasks while keeping sensitive data scoped and employment decisions under human authority. - [AI Agents for Marketing](https://agenticorg.ai/solutions/cmo): Marketing teams can coordinate research and campaign workflows using scoped tools, review gates, versioned prompts, and owner-defined evaluation measures. - [AI Agents for Operations](https://agenticorg.ai/solutions/coo): Operations teams can route and coordinate repetitive workflows using agents subject to escalation rules, action scopes, approval requirements, and audit evidence. - [AI Agents for Back Office](https://agenticorg.ai/solutions/cbo): Back-office teams can assemble traceable workflows around documents, cases, and internal systems while preserving review and authorization boundaries. - [Blog](https://agenticorg.ai/blog): The AgenticOrg blog covers implementation patterns, operating practices, governance decisions, and protocol boundaries for enterprise AI agents. - [Resource Library](https://agenticorg.ai/resources): The resource library provides educational guides for teams assessing, designing, integrating, governing, and operating enterprise AI agents. ## Developer access - [Python SDK and CLI](https://github.com/mishrasanjeev/agentic-org/tree/main/sdk) - [TypeScript SDK](https://github.com/mishrasanjeev/agentic-org/tree/main/sdk-ts) - [MCP server](https://github.com/mishrasanjeev/agentic-org/tree/main/mcp-server) - A2A discovery: https://app.agenticorg.ai/api/v1/a2a/agent-card - MCP discovery: https://app.agenticorg.ai/api/v1/mcp/tools - [API reference](https://github.com/mishrasanjeev/agentic-org/blob/main/docs/api-reference.md) ## Direct answers ### What is AgenticOrg? AgenticOrg is an open-source enterprise AI agent platform. It combines agent and workflow execution, connectors, scoped tools, human approval gates, evaluation, audit evidence, SDKs, MCP, A2A, and bounded commerce integrations. ### How many agents, connectors, and tools are available? Read https://app.agenticorg.ai/api/v1/product-facts. It computes current deployed totals from runtime registries so copied documentation does not drift. ### Does a listed connector work without setup? No. Availability depends on provider credentials, subscriptions, scopes, tenant configuration, policy, and provider uptime. ### Can AgenticOrg complete an OACP payment or order? Not from OACP artifacts. AgenticOrg can answer from valid evidence and prepare a provider or merchant handoff. The provider or merchant system must execute and confirm the result. ### Can AgenticOrg be self-hosted? Yes. The repository is Apache-2.0 licensed and includes local Docker and deployment assets. The managed production path uses Google Cloud Run. ## More - [Full product and evidence guide](https://agenticorg.ai/llms-full.txt) - [Sitemap](https://agenticorg.ai/sitemap.xml) - [Blog](https://agenticorg.ai/blog) - [Resources](https://agenticorg.ai/resources) - [OACP documentation](https://github.com/mishrasanjeev/agentic-org/tree/main/docs/oacp) - [Security policy](https://github.com/mishrasanjeev/agentic-org/blob/main/SECURITY.md)