# nduckmink/arkon

Arkon: Enterprise AI Knowledge Hub & MCP Server. Self-hosted knowledge base for teams to manage RAG contexts, access policies, and AI skills. Connect Claude and other LLMs via Model Context Protocol (MCP) for automated, secure organizational knowledge integration.

Repository: https://github.com/nduckmink/arkon
Canonical: https://ross.abutalabs.com/products/arkon
Language: Python
License: NOASSERTION
License Family: other
Topics: enterprise-ai, knowledge-base-embeddings, knowledge-based-systems, knowledge-bases, llm-wiki-personal-knowledge-base, mcp, mcp-server, model-context-protocol, organizational-knowledge, rag, self-hosted, wiki
Last push: 2026-06-03T18:41:48+00:00

## Health v2 (maintenance only)
Score: 70/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 85, release rhythm 86, longevity 8
- inputs: {"age_days": 125, "days_push": 91, "days_rel": 93, "gap_med": 0.0, "n_releases_24m": 13}
- flags: young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1244, forks 269 (observed 2026-08-28T04:04:06.729016+00:00)

## What it is
Arkon is a self-hosted enterprise knowledge hub that compiles organizational documents into a structured, traceable wiki and serves it to LLMs via a Model Context Protocol (MCP) server. It includes an LLM-driven document compilation pipeline, a wiki browser with semantic search and knowledge graph, and role/department-scoped access policies.

## Use cases
- self-host a knowledge base that Claude can query via MCP
- compile SOPs and internal docs into an AI-accessible wiki
- give employees role-scoped RAG context instead of copy-pasting into chatbots
- build a searchable internal knowledge graph with pgvector
- manage access policies for organizational AI context
- review and approve AI-generated wiki page updates before publishing

## When to choose
- you need a centralized, permission-scoped MCP knowledge server for an organization
- you want traceable, human-reviewed wiki compilation rather than raw vector chunking
- you prefer self-hosting your team's AI knowledge layer

## When to avoid
- you need a permissively licensed library to embed in your own product (PolyForm Internal Use license)
- you just want a simple vector store without wiki compilation or review workflows
- you need a fully managed SaaS solution

## Facets
- artifact type: application
- maturity: active
- function: rag, mcp, search-engine, vector-database, documentation, auth, chatbot
- domain: large-language-models, self-hosted, erp
- platform: self-hosted, python
- tags: mcp-server, knowledge-wiki, enterprise-knowledge-base, pgvector, knowledge-graph, access-policies, retrieval-augmented-generation, knowledge-management, ai-agents, docker, web-server

## Member repositories
- nduckmink/arkon (main) score 70

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:06.729016+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 2026-08-30T05:08:15.975917+00:00, confidence not recorded.
  - readme: https://github.com/nduckmink/arkon (fetched 2026-08-28T04:04:06.729016+00:00, sha d72d4d727019)
- Data as of 2026-08-30T08:39:29.467469+00:00.