Viewing profile — amavashev

True website is not for you and in the age for AI is not even for people. Its for AI agents reading your website and deciding what to do with it: recommend it, skip it, integrate w…

The no proxy approach makes sense for LLMs calls. The gap is non LLM calls. Often times damage is done by non LLM calls -- tool calls like sending email, add records, files, placin…

Agree, you need to your own code review, although as AI gets better, this problem will most likely be solved.

The core argument here is that autonomous agents will need a economic envelope enforced before execution not after. This means agents must follow this flow: reserve, use, commit or…

technical breakdown: https://dev.to/amavashev/i-burned-153-in-30-minutes-with-an-...

Demo (no API key needed): https://github.com/runcycles/cycles-runaway-demo

Rate limits control velocity. They say nothing about what an agent is allowed to do next. An agent can pass every rate-limit check and still delete 400 records, send 200 emails, or…

I'm the author. A few design decisions worth explaining: The model downgrade is the most useful feature for daily use — when budget drops below a threshold, the plugin silently swa…

OpenClaw agents can loop, pick expensive models, and burn budget before anyone notices. This plugin stops that. Install: openclaw plugins install @runcycles/openclaw-budget-guard A…

[dead]

I built this after reading too many incident reports of agent loops spending $200 in 4 minutes because a quality threshold was never met. The pattern is always the same: an agent r…

Per-key isolation + model locking is a solid baseline — especially for multi-tool stacks where one shared key hides everything. One thing we’ve noticed though: spend caps stop dama…

Drift correlating more with constraint tension than raw step count matches what we’ve observed. Your external gate instinct is right, but the gate has to be structurally external, …