RubyLLM retries POSTs that Faraday would not, and honors Retry-After with no upper bound. A 429 can park a Rails request for as long as the provider says.
RubyLLM is a model client with Rails generators. Langchainrb is retrieval plumbing. Pick by whether you query your own documents, not by provider count.
Add LLM chat to Rails with RubyLLM: one API for OpenAI, Claude, and Ollama, acts_as_chat persistence, tool calling, streaming into Turbo, and real trade-offs.
LLM responses stream for 30 seconds while a Rails thread waits. The arithmetic of Puma threads vs open SSE streams, and when Falcon's fibers earn the switch.
Our production multi-agent LLM pipeline in Rails: eight RubyLLM agents on a 21-line base class, a 16-line loop, and the deploy that starved the database pool.
What a green Rails suite actually asserts when the thing under test is a hosted model: VCR matches on method and URI only, and the model can be retired.
CVE-2026-66066 lets an unauthenticated upload read server files via Active Storage. Patching Rails is not enough - libvips must go to 8.13 and secrets rotate.
Rails 7.1 got no patch for CVE-2026-66066, a CVSSv4 9.5 pre-auth RCE. How to find every app of yours on a dead branch and pick between four realistic exits.
Reading this because something is going wrong?
A free code audit gives you a written assessment of your codebase in plain English.
