# embabel/embabel-agent

Agent framework for the JVM. Pronounced Em-BAY-bel /ɛmˈbeɪbəl/

Repository: https://github.com/embabel/embabel-agent
Canonical: https://ross.abutalabs.com/products/embabel-agent
Homepage: https://hub.embabel.com
Language: Kotlin
License: Apache-2.0
License Family: permissive
Topics: agentic-ai, generative-ai, java, kotlin, spring, agents, aiagentframework, agent, ai, ai-agents, genai, llms, multi-agents, multi-agents-orchestration, multi-agents-system
Last push: 2026-08-24T18:27:23+00:00

## Health v2 (maintenance only)
Score: 86/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 99, longevity 36
- inputs: {"age_days": 510, "days_push": 9, "days_rel": 9, "gap_med": 17.0, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4386, forks 429 (observed 2026-08-28T04:08:47.138457+00:00)

## What it is
Embabel Agent is an agentic AI framework for the JVM, written in Kotlin with first-class Java and Spring Boot support. It provides typed, goal-oriented agent orchestration, LLM integration, human-in-the-loop flows, and automatic exposure of agents as MCP servers.

## Use cases
- build production AI agents on the JVM
- orchestrate multi-agent workflows in Java or Kotlin
- expose LLM agents as MCP tools for Claude Desktop or VS Code
- extract typed objects from LLM prompts
- build human-in-the-loop agent applications with Spring Boot
- replace Python agent prototypes with type-safe JVM code

## When to choose
- you are building LLM-powered agents in Java or Kotlin
- you want Spring Boot integration and enterprise-grade type safety
- you need MCP server publishing of agent goals
- you are moving agentic AI from Python experiments to production

## When to avoid
- your stack is Python-centric and you prefer LangChain or Pydantic AI
- you need a lightweight script rather than a full framework
- you do not use the JVM at all

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, mcp, rag, prompt-engineering, chatbot
- domain: artificial-intelligence, large-language-models, developer-tools, backend
- platform: jvm, self-hosted
- tags: agentic-ai, multi-agent-orchestration, spring-boot, mcp-server, genai, type-safe-prompts, ai-agents, spring, docker

## Member repositories
- embabel/embabel-agent (main) score 86

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:47.138457+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:21:14.550061+00:00, confidence not recorded.
  - readme: https://github.com/embabel/embabel-agent (fetched 2026-08-28T04:08:47.138457+00:00, sha d0be44ee6a63)
  - homepage: https://hub.embabel.com (fetched 2026-08-29T09:09:18.365099+00:00, sha b8e6db59a009)
  - site_page: https://hub.embabel.com/getting-started/quickstart (fetched 2026-08-29T09:09:18.367597+00:00, sha 23171d6f1d4a)
  - site_page: https://hub.embabel.com/getting-started (fetched 2026-08-29T09:09:18.369276+00:00, sha abe9f90794e2)
  - site_page: https://hub.embabel.com/reference/integrations (fetched 2026-08-29T09:09:18.371565+00:00, sha 0dcfde111345)
- Data as of 2026-08-30T08:39:29.467469+00:00.