Open-source workflow engine for AI agents. An agent calls Realm over MCP, or realm agent drives a model from the CLI. Steps run in order, agent answers are checked against the schema a step declares, human gates pause the run until answered, and each finished step is recorded.
An opinionated agentic development layer for OpenCode — spec-first when it matters, review-driven execution, portable model roles, safer tools, and long-run safety.
A team of specialized AI agents covering the complete software development flow — from requirements discovery to deploy. One responsibility per agent, specs as source of truth, no shortcuts.
A small, nestable agent-loop job primitive: loop(body→until→review) composed with dag, pluggable engines, agent-judge gates, budget + run records. TypeScript.