StackMap
Subscribe

arkon vs onyx

Self-hosted enterprise knowledge hub + MCP server: an LLM pipeline compiles SOPs and docs into a traceable, human-reviewed wiki, then serves it to AI clients scoped by department and role. — versus — Self-hosted context layer and AI chat for teams: indexes 50+ workplace apps with permissions into a hybrid index, then serves agentic RAG, deep research, custom agents and an MCP server.

The curated verdict

Both are self-hosted enterprise knowledge hubs exposed to agents over MCP; arkon compiles SOPs/docs into a curated hub, Onyx indexes raw app data with source permissions.

arkononyx
Stars1.5k33k
Forks3084.8k
LanguagePythonPython
LicenseNOASSERTIONNOASSERTION
Last activity5 months agotoday
Topicsragrag, agents
Curated connections55

arkon — the curator's take

The MRP pipeline is the differentiator: instead of chunk-and-index, documents are compiled into merged, source-traceable wiki pages behind a plan-review gate — knowledge management, not just retrieval — with department-scoped serving over one MCP endpoint. When NOT: the license is NOASSERTION, a real blocker for the enterprises it targets — clarify before adoption; ★1.2k young, and the compile-everything approach costs LLM tokens where a plain vector store costs none.

onyx — the curator's take

Use it when you want one permission-aware index over Slack, Drive, Confluence and friends that both humans (chat, Slack bot, Chrome extension) and coding agents (MCP) can query — the pre-built index beats agents fanning out across dozens of MCP servers on latency and tokens. Standard mode is a heavy multi-container deploy with connector sync jobs; skip it for a single doc collection or when you don't want to own an ingest pipeline.