bytechef vs MaxKB
Open-source platform unifying AI agent orchestration with classic workflow automation — visual builder, 200+ integration components, self-hosted via Docker. Apache 2.0 + EE split. — versus — 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.
Both are self-hosted no-code enterprise agent platforms with different centers of gravity: MaxKB starts from the knowledge base and RAG, ByteChef from integrations and workflow automation.
| bytechef | MaxKB | |
|---|---|---|
| Stars | 910 | 22k |
| Forks | 157 | 3.0k |
| Language | Java | Python |
| License | NOASSERTION | GPL-3.0 |
| Last activity | yesterday | today |
| Topics | agents, orchestration | agents, rag |
| Curated connections | 3 | 3 |
bytechef — the curator's take
The bet: agent autonomy and deterministic workflow automation belong in ONE platform, not two — let precise integration flows hand work to agents and vice versa. If your team already thinks in n8n/Zapier terms and wants agents in the same canvas, this is the natural home. NOT proven at scale yet (~900 stars, young community for a platform this ambitious), and mind the Apache-2.0 + Enterprise Edition split — check which features live behind the EE line before betting the roadmap.
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.