Skip to content

Spendbrake

SpendBrake turns a budget plus a plan into one of three calls — continue, downgrade_model or stop — and renders the cost against value as a dashboard, with the decision made by TypeSafe Jev.

Stars
0
Language
TypeScript
Published by
Community
Author
ndolinschi
Last verified
Oct 2026

ndolinschi/spendbrake

User repository on GitHub

View on GitHub

Agent budget brake — continue / downgrade_model / stop via TypeSafe Jev

Forks
0
Last pushed
Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.Homepage

About this project

Budget + plan → continue / downgrademodel / stop — cost×value dashboard powered by TypeSafe Jev.

Quoted from the project's README. Read the full README.

Highlights

  • The output space is fixed at three values: continue, downgrade_model, stop.
  • Inputs are a budget and a plan, and the decision is made by TypeSafe Jev.
  • The reasoning is presented as a cost-against-value dashboard, per the README.

Watch out

The three labels are named but never defined: there is no threshold, no unit of value, no currency assumption, and no statement of what happens on the continue path or how downgrade_model is applied — whether it is advice, a setting change or an action taken. No persistence, spend tracking over time, alerting or integration is documented, and no failure modes for the model are given. Treat the dashboard as an illustration of the decision shape rather than as cost control. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

2GitHub stars
Next.js spectator demo in which two independent Jev agents drive separate Snake browsers through same-origin iframes, clicking indexed direction buttons only, with each board state streamed to a server-only endpoint that returns the chosen target.
Jev Demos & Experiments#community#jevbest#catalog-import
2GitHub stars
An agent tool and MCP call gate: paste a planned call plus its context and it returns allow, ask_human or deny with risk scores derived from a TypeSafe Jev decision call.
Jev Demos & Experiments#community#jevbest#catalog-import
2GitHub stars
An MCP stdio proxy in front of the official Playwright MCP server that triages page state, masks prompt injection, trims oversized page dumps by goal and risk-gates actions, exposing the same tools and schemas.
Jev Demos & Experiments#community#jevbest#catalog-import
0GitHub stars
Paste a trace of an agent step, get one of four dispositions back: ok, retry, escalate or stop. Aimed at agent builders putting a supervision step around an agent loop, with the judging powered by TypeSafe Jev and a two-command setup.
Jev Demos & Experiments#community#jevbest#catalog-import
0GitHub stars
McpMatch takes a free-text user goal and matches it against a catalog of MCP servers or capabilities using TypeSafe Jev, with a two-stage path for large catalogs. Runs with npm i and npm run dev.
Jev Demos & Experiments#community#jevbest#catalog-import
0GitHub stars
SwarmRouter picks which agent or skill should handle a task and returns a confidence with the pick, drawn as a visual swarm map, with the choice made by TypeSafe Jev. Five handler types are named in the README.
Jev Demos & Experiments#community#jevbest#catalog-import

From the Jev guides

Original write-ups on what this entry is for.

A game tick is a state plus a legal action list. How Clash Royale, Minecraft, and the earlier Mario, Pokémon, StarCraft, and drone loops ask Jev one step at a time.
Jev Demos & Experiments#gaming#agents#control
Read article
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai