# apecloud/ApeRAG

ApeRAG: Production-ready GraphRAG with multi-modal indexing, AI agents, MCP support, and scalable K8s deployment

Repository: https://github.com/apecloud/ApeRAG
Canonical: https://ross.abutalabs.com/products/aperag
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agents, graphrag, knowledge-graph, mcp, context-engineering
Last push: 2026-05-02T05:01:36+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 80, release rhythm 8, longevity 83
- inputs: {"age_days": 1170, "days_push": 123, "days_rel": 524, "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 1306, forks 146 (observed 2026-08-28T04:04:18.904957+00:00)

## What it is
ApeRAG is a production-ready RAG platform combining Graph RAG, vector search, and full-text search with AI agents and MCP support. It offers multimodal document indexing, knowledge graph construction, and scalable Kubernetes deployment.

## Use cases
- build a knowledge graph from my documents
- self-host a RAG platform with hybrid search
- expose my knowledge base to AI assistants via MCP
- chat with my documents using graph and vector retrieval
- deploy a production RAG service on Kubernetes
- parse and index multimodal documents for AI search

## When to choose
- you need GraphRAG with knowledge graph construction out of the box
- you want hybrid retrieval combining vector, full-text, and graph search
- you need MCP integration so AI assistants can query your knowledge base
- you want a self-hosted, Kubernetes-scalable RAG platform

## When to avoid
- you only need a lightweight embedding library to embed in your own app
- you want a fully managed cloud RAG service with zero ops
- your hardware cannot meet the 2-core/4GB minimum requirements

## Facets
- artifact type: service
- maturity: active
- function: rag, search-engine, vector-database, agent-framework, mcp, chatbot, nlp, llm-inference
- domain: large-language-models, self-hosted
- platform: python, self-hosted, cloud
- tags: graphrag, knowledge-graph, hybrid-search, multimodal, context-engineering, mcp-server, production-ready, retrieval-augmented-generation, ai-agents, search, natural-language-processing, docker, kubernetes, web-server

## Member repositories
- apecloud/ApeRAG (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:18.904957+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 2026-08-30T04:50:57.176363+00:00, confidence not recorded.
  - readme: https://github.com/apecloud/ApeRAG (fetched 2026-08-28T04:04:18.904957+00:00, sha a3d34f753450)
- Data as of 2026-08-30T08:39:29.467469+00:00.