Vilano Runtime – a durable runtime for building agent systems
BEAM kernel with deterministic replay solves agent state durability problems.

Uses Elixir OTP to orchestrate Python agents with 3.77 KB memory overhead.
AI infrastructure engineers building scalable agent swarms
LangGraph · AutoGen · Erlport
BEAM kernel with deterministic replay solves agent state durability problems.
Multi-session agents with inter-session context passing, but huge feature list hides unclear priorities.
Ray and Prefect alternative claiming single-codebase distribution without the boilerplate.
It makes a smart, practical bet: let existing Python functions become agent-ready tools by turning type hints into structured tool schemas with validation and HTTP endpoints, so you don't rewrite logic to expose it to agents. The included PolyClaw agent and discovery/orchestration features sound useful for multi-service workflows, but the space is crowded (LangChain/AutoGPT/etc.), so what matters next is demos showing robust orchestration, failure handling, and provider integrations.
BEAM-based agent runtime with git-backed recovery and auditable safety gates.
Quoracle forces you to stop trusting one model and instead runs every decision through an explicit consensus pipeline, with per-model conversation history persisted to Postgres and a LiveView dashboard for realtime inspection. Agents can spawn children recursively and communicate via messages, which makes it a neat sandbox for studying emergent behaviors or building robust multi-model workflows — heavy, opinionated, and clearly aimed at folks who want to experiment rather than ship a lightweight chatbot.