I run a 'radar' that finds free LLM endpoints and auto-adopts the good ones — behind a five-part gate so it can't adopt junk

A developer built model-radar, an open-source tool that automatically discovers free LLM endpoints and adopts qualifying models into an agent stack, but only after they pass a fixed five-stage deterministic gate. The gate tests agent-critical behaviors such as tool-calling, full-prompt retention, and stability on real tasks, rejecting any candidate that fails a single stage to prevent silent failures from cheaper models.

Free LLM endpoints appear and vanish constantly — a provider opens a generous tier, a new open model shows up on someone's gateway, a promo runs for a month. Chasing them by hand is a losing game. So I built a small radar model-radar https://github.com/casareanderson/model-radar that watches for free models and, when one is genuinely good enough, adopts it automatically into my agent stack — but only after it clears a gate strict enough that it has never once adopted something that embarrassed me. The auto-adoption is the flashy bit. The gate is the bit worth your time, because "just use the free model" is advice that will quietly wreck an agent pipeline. The appeal is obvious: a lot of agent work — summarise, triage, draft, classify — doesn't need a frontier model, and paying frontier prices for it is silly. A free tier that's "good enough" for the boring 90% is real money saved. The catch is that "free model" and "works in an agent" are almost unrelated properties. A model can score beautifully on a leaderboard and be useless for agentic work , because agent work needs things benchmarks don't measure: So a radar that adopted models on quality scores would be a machine for introducing silent failures. The whole design problem is: how do you let a process adopt something automatically without letting it adopt something bad? The radar can find candidates freely. It can promote one only by passing every stage of a fixed, deterministic gate — and if any stage fails, it's rejected, full stop. No score, no averaging, no "it's mostly fine." The gate checks, in order, things a leaderboard never will: Only a model that clears all five gets adopted. Everything is measured on real tasks and written down , so adoption is a reproducible decision I can audit later, The principle underneath is the same one my whole estate runs on: let the automated part gather and propose freely; let it act only through a gate that a bad candidate cannot argue its way past. A guardrail written as a suggestion in a prompt is decoration. A guardrail written as a pass/fail function is a wall. The failure I designed the whole thing to avoid is the one that gets everyone else: a cheaper model quietly swapped in that looks like it's working — emits calls, returns fluent text — while ignoring tool results or truncating context, producing confident garbage that no error ever flags. The gate exists specifically to catch the model that fails silently , because that's the only kind of failure that survives long enough to hurt you. model-radar is on GitHub https://github.com/casareanderson/model-radar . Even if you never auto-adopt anything, the transferable idea is the gate: before you route real work to a free model, test it on the thing agents actually need — can it tool-call and use the result, does it keep your whole prompt, is it stable — and make that test a hard pass/fail, not a score. Cheap intelligence is worth Notes from someone who wanted a coffee-a-month agent bill and refused to pay for it in silent failures, so built a radar that adopts free models automatically and a gate strict enough to trust it. 🤖 Drafted with AI assistance from my own homelab notes, logs and repos, then reviewed and edited before publishing.