# jd-opensource/joyagent-jdgenie

开源的端到端产品级通用智能体

Repository: https://github.com/jd-opensource/joyagent-jdgenie
Canonical: https://ross.abutalabs.com/products/joyagent-jdgenie
Language: Java
License: Apache-2.0
License Family: permissive
Last push: 2026-02-12T06:33:00+00:00

## Health v2 (maintenance only)
Score: 42/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 67, release rhythm 16, longevity 29
- inputs: {"age_days": 413, "days_push": 202, "days_rel": 350, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 11879, forks 1661 (observed 2026-08-28T04:10:50.372985+00:00)

## What it is
JoyAgent-JDGenie is an open-source, end-to-end, production-grade general-purpose multi-agent product built in Java. It directly answers user queries or completes tasks (e.g., generating web or PPT reports) and allows custom sub-agents or tools to be mounted onto the framework.

## Use cases
- build a multi-agent AI assistant without writing code from scratch
- generate analysis reports or PPT presentations from a natural language query
- self-host a general-purpose agent product instead of an SDK or framework
- mount custom sub-agents or tools for new business scenarios
- run intelligent Q&A over multimodal unstructured documents with RAG
- query and diagnose structured tabular enterprise data with a DataAgent

## When to choose
- you want a ready-to-use, out-of-the-box agent product rather than a low-level SDK
- you need a lightweight multi-agent system with no dependency on a specific cloud LLM platform
- you want strong benchmark-validated general agent performance (GAIA leaderboard)

## When to avoid
- you only need a minimal agent library to embed in an existing Python application
- your stack is Python-centric and you prefer frameworks like LangChain or AutoGen
- you need deep customization of the agent engine internals and prefer a smaller framework

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, rag, llm-inference, chatbot, web-framework
- domain: large-language-models, artificial-intelligence, data-science
- platform: self-hosted, cross-platform
- tags: multi-agent, end-to-end-product, java, report-generation, ppt-generation, data-agent, gaia-benchmark, open-source-agent, ai-agents, retrieval-augmented-generation, web-server

## Member repositories
- jd-opensource/joyagent-jdgenie (main) score 42

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:50.372985+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 2026-08-29T17:15:14.459874+00:00, confidence not recorded.
  - readme: https://github.com/jd-opensource/joyagent-jdgenie (fetched 2026-08-28T04:10:50.372985+00:00, sha 5900eaa36c2b)
- Data as of 2026-08-30T08:39:29.467469+00:00.