Agent costs get hard to control when you only govern one model call at a time.
This is a dev post classified by Jev as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
Agent costs get hard to control when you only govern one model call at a time. TokenOps is an open-source Python project for setting and enforcing a token budget across a whole AI-agent run. It helps you keep multi-step workflows within a shared spend limit by applying governance before each model call, instead of only reporting the cost after execution. Key features: • Run-scoped budgets – set one budget for the full agent workflow, not a single request • Pre-call enforcement – check the available budget before each model call and halt a run when it is exhausted • Shared control plane – l
Posted by Dan Kornas (99.1k followers) 1 h ago · 3 likes · 571 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- Your coding agent can make THIS now. — @superalesha
- I recorded a 41-minute tutorial on how I use Astra to create insane three.js websites in… — @MengTo
- @tugawane_ — @tugawane_
- Qwen-Image-2.1 from @Alibaba_Qwen has day-0 support in vLLM-Omni. 🎉 — @vllm_project
- A customer writes, "I was charged twice. Please refund me or I’m cancelling." Software… — @agenticgirl
- MiniCPM-o 4.5 meets real-time voice agents. — @OpenBMB
- Publishing a short video is easy. Catching compliance risks before it goes live is harder. — @DanKornas
- 🎉 To no one's surprise, Jev support just landed in TanStack AI via `decide()`, our new… — @tan_stack
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 15.4k posts from 4.9k X accounts over the last 21 days, 1.7k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-20 14:45 UTC. Full method.