spendbrake
Tiny demo that asks Jev whether an agent should continue, downgrade its model, or stop, given budget and plan.
Overview
SpendBrake is a minimal demo described in a two-line README: given a budget and a plan, it asks TypeSafe Jev to choose continue, downgrade_model or stop, and shows a cost-versus-value dashboard.
The README contains only an install command, so the state fields, thresholds and how spend is measured are not documented. It illustrates using a typed choice as a budget brake on an agent run.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Given the budget and plan, should the agent continue, downgrade its model, or stop? | continue · downgrade_model · stop |
How it works
- Track spend against budget and plan
- Ask Jev the three-way choice
- Continue, switch to a cheaper model or stop
Strengths
- Simple budget control pattern
Caveats
- Minimal README with no details
- Demo only; no licence stated
Getting started
npm i && npm run devAt a glance
- Type
- Demo
- Status
- prototype
- Language
- TypeScript
- Runtime
- Node web app
- Has code
- yes
Use cases and integrations
How curated lists describe it
Agent budget brake — continue / downgrade_model / stop via TypeSafe Jev.
hellogumbo/awesome-jev
Frequently asked questions
What does Jev decide?
Whether an agent should continue, downgrade its model or stop.
Is there documentation?
Only a two-line README.
How do I run it?
npm i && npm run dev.
Related projects
Multi-agent orchestration layer for Claude Code with opt-in Jev hooks for fast judgment points, decision caching and egress controls.
PluginproductionTypeScriptRuns Claude Code on Opus 5.5 with Jev re-picking reasoning effort after every tool batch, via per-message effort so the cache survives.
ProxybetaTypeScriptOpenClaw plugin and CLI that turn a plain-language condition into a scheduled trigger, waking the model only when Jev says it is true.
PluginbetaTypeScriptDeepSeek Harness plugin for budgeted, read-only GPT 'teacher' consults; Jev may only suggest when a consult is worthwhile.
ProjectprototypeJavaScriptGate that asks Jev whether a timer or event is worth resuming a sleeping agent's LLM, skipping only when confidently not.
BenchmarkprototypeTypeScriptnpm library that rate-limits, spend-caps, caches and redacts every Jev request made in a loop.
LibrarybetaJavaScript