Show HN: Enju – humans, AI agents, and compute as peers on one workflow graph

Category: devtools

Tags: workflow-engine, dag, human-in-the-loop, ai-agents, git-based

Score: 8.0/10 (Innovation: 9, Technical: 8, Documentation: 8, Utility: 7)

Enju is a workflow system that treats humans, AI agents, and deterministic compute as interchangeable peers on a live DAG, enabling iterative collaboration with built-in audit trails via git. Its novel design—placing human review and voting as first-class graph nodes with output-neutral coordination—makes it particularly interesting for complex, multi-step workflows requiring human-in-the-loop validation.

Target audience: backend devs, data engineers, devops

Repository: https://github.com/tamerh/enju · Go · MIT

View on Hacker News