StackMap
Subscribe

MaxKB vs onyx

Open-source enterprise agent platform: RAG pipelines (upload or crawl docs), a visual workflow engine with MCP tool-use, and zero-code embedding into existing business systems. — 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 agent+RAG platforms; MaxKB centres on uploaded/crawled knowledge bases and a visual workflow engine, Onyx on permission-synced connectors across 50+ live workplace apps.

MaxKBonyx
Stars23k33k
Forks3.2k4.8k
LanguagePythonPython
LicenseGPL-3.0NOASSERTION
Last activitytodaytoday
Topicsagents, ragrag, agents
Curated connections85

MaxKB — the curator's take

The self-hosted answer to 'we need an internal AI assistant this quarter': upload or crawl your docs, get a RAG-grounded Q&A agent with a real workflow engine and MCP tool-use, then embed it into existing systems without code. Model-agnostic including fully private deployments. Battle-tested at 22k stars, mostly in enterprise support/knowledge-base roles. NOT a developer framework — you orchestrate in its UI, not your codebase (LangGraph territory); GPL-3.0 matters if you redistribute; and the project's center of gravity is the Chinese enterprise ecosystem — English docs and community trail the code.

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.