Pure, deterministic scheduler core for the Areev agent runtime: graph walk with re-entry generations, journal keys, budgets, and the sans-IO step function. No…
Out-of-box LLM provider backends for Areev and Areev Loop: OpenAI-compatible, Anthropic, and Ollama adapters over a small blocking HTTP client, implementing…
The Areev agent runtime driver: executes OMS Workflow grains over the deterministic scheduler core, journaling every effect as content-addressed grains —…
Areev substrate adapter for the Areev Loop engine: implements areev_loop::OmsSubstrate over AreevFacade so `areev loop` runs against real .mg/Turso memory…
MCP gateway and Model Context Protocol proxy: connect unlimited MCP servers, tools and REST APIs to an AI client at a fixed context cost, with on-demand tool…
OpenLatch runtime enforcement node — the capture-and-enforce adapter that evaluates every covered action against a coding agent's Autonomy Zone before it runs