Open-source Plano routes LLM calls by prompt intent, no agent code changes, cutting bills 2x
Roger_M_Taylor · x · 2026-09-12
Plano (7k stars on GitHub, by katanemo) is an open-source AI-native proxy server for agentic apps offering smart LLM routing, observability, orchestration and guardrails.
The trick: point your client's baseurl at Plano's local endpoint and it routes by prompt intent without touching agent code — e.g. "write a binary search" goes to claude-sonnet-4.5, while "Capital of France?" goes to gpt-4o-mini, so trivial tasks hit cheap models. The planoai obs command gives a live view of every routing decision, model picked and route taken.
A cited case reports cutting an Hermes Agent bill 2x with this "cheapest capable model" layer — the same approach Coinbase reportedly uses.
More from coding & agent
- Claude Built a Bow-and-Arrow Deathmatch Game, and Its Author Won the 1v1 — invocation02 · 2026-09-12
- 'Staff' once meant your own walking stick — AI agents should be loyal to you, not your company — granawkins · 2026-09-12
- Building a Multilingual RAG Document Assistant with FastAPI, FAISS and Ollama — imABDRAOUF · 2026-09-12
- Teknium's Agent Philosophy: One Agent, One Skill, Each Hermes Agent Does One Thing — Teknium · 2026-09-12
- Pi, a minimal self-customizing coding agent harness, sparks OMP comparison debate — HankYeomans · 2026-09-12
- Seroter Daily Reading #865: cyber model arena, post-git storage, billion-token savings — rseroter · 2026-09-12