Aquila is Franz Bettag's open-source Elixir library that orchestrates the OpenAI Responses and Chat Completions APIs, with tool-context callbacks, streaming sinks for processes and LiveView, and deterministic record/replay for tests.
Production LLM integrations in Elixir/Phoenix need a shared abstraction for the Responses and Chat Completions APIs, tool calls with their own context, streaming into processes and LiveView, and reproducible tests without live API calls.
Author and maintainer of the library.
Responses and Chat Completions orchestration with tool-context callbacks.
Streaming sinks for Elixir processes and Phoenix LiveView.
Record/replay cassettes enable reproducible tests without live API calls, complemented by telemetry for observability.
The record/replay cassettes are reproducible reliability and correctness checks, not performance benchmarks. No measured customer latency or cost-savings data exists.
examples/support_assistant runs a complete tool and streaming workflow offline. Verification on 5 September 2026: 432 library tests passed, 15 live tests excluded, 82.6% coverage, plus three passing application-example tests. This is a demonstration application.
Tool calls, tests and streaming are only part of a rollout. Before launch, teams need quality criteria, permissions, cost controls and a recovery path. A readiness review identifies the missing steps; a model comparison tests the choice against your tasks.
