OpenViSTAI · Agents · Blockchain · Crypto
Menu
Agent Frameworks

Enterpriseagentframework

Enterpriseagentframework is an MIT-licensed, Java-oriented framework for building and running AI agents that connect to existing enterprise applications and use registered business capabilities to query data, fill forms and execute tasks.

Independent OpenViST project profile, based on linked sources.

Enterpriseagentframework — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when AI needs to operate within an existing enterprise application and the integration must preserve the application’s identity, permissions, APIs and business rules. It is also suited to teams planning a staged process from system scanning and AI-assisted implementation to capability publishing and business acceptance.

Who it is for

  • Enterprise development teams maintaining Java business systems.
  • Organisations modernising OA, ERP, CRM, eHR, procurement, ticketing or contract applications.
  • Developers who need agent actions to use existing identities, permissions and business rules.

Documented uses

  • Add natural-language data querying to an existing business system.
  • Prepare enterprise forms from user instructions.
  • Execute operational tasks in OA, ERP, CRM or procurement systems.
  • Register Java methods and APIs as governed agent capabilities.
  • Assemble reusable capabilities into authorised workflows.
Before you choose

Requirements & limits

The repository is publicly accessible and identified with an MIT licence. The documented runtime platforms are server and self-hosted environments.

  • Java is the documented primary language, with JDK 8-compatible SDK and Spring Boot 2 Starter support.
  • Backend Capabilities or business APIs perform real data queries and writes; page actions handle navigation and form interaction.
  • The framework keeps existing application identity, permissions and business rules in the execution path.
  • Write, submission and approval actions require user confirmation.
  • The documented lifecycle includes scanning, developer review, AI Coding implementation, publishing and business acceptance.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Register Java business capabilities for enterprise agents

Expose selected Java business methods as governed capabilities that can be reviewed and used by agents or workflows.

Before you start

  • An existing Java enterprise application.
  • JDK 8-compatible SDK support.
  • Spring Boot 2 Starter support.
  • Business methods or Spring MVC interfaces suitable for capability registration.

Steps

  1. Add the SDK and Spring Boot 2 Starter to the Java application.

  2. Annotate business methods as ReachAI capabilities, including the capability name, description, domain, module, side-effect level and required roles.

  3. Declare required parameters for the business method.

  4. Allow the Starter to scan the annotated methods and Spring MVC interfaces and report the project, instance and capability information.

  5. Review the resulting capability snapshot and apply or ignore the detected changes before placing the capability in the catalog.

Expected outcome

The selected Java methods or interfaces are represented as reviewable capabilities that can support agent and workflow execution.

Guide limitations

  • The guide documents registration and review, not a complete production deployment or successful business transaction.
  • Actual data access and writes still depend on the underlying business service or API.
  • Write operations require user confirmation according to the project documentation.
Evidence and transparency

Sources & review

Source record details
Source availability
Active
Sources checked
3 October 2026
Original website title
w8123/EnterpriseAgentFramework · Official homepage title · retained in its source language

Related options

Dify — The repository describes Dify as an AI application, Agent and Workflow orchestration platform, while Enterpriseagentframework focuses on adapting existing enterprise systems.

Explore project →

OpenClaw — The repository describes OpenClaw as a personal-agent approach for connecting tools and services, while Enterpriseagentframework targets multi-user enterprise systems and controlle