JevMade

Sign in

Explore the Jev ecosystem.

Learn, build, and play with Jev — from deep technical guides to creative experiments.

Make & explore

Experiments.

See what builders made with Jev. Games, tools, repositories, articles, and more — traced to their sources.

Featured experiment Jev experiments by Nader Dabit
Recorded frame from Jev experiments
Explore 2,140 entries
The directory03 / 03 · Experiments

Find something worth exploring.Experiments

Every category, from games and tools to repositories and writeups, traced to a primary source.

Real-time research powered by Firecrawl

Same ideas.
Different paths.

This is the full registry, not just the featured picks. Figures like speed, cost, and stars are maker-reported or captured snapshots, not JevMade measurements.

2140 experiments · showing 421–480

riff

by scale-venture-partners · Python

A fast prose linter with Ruff-style rule codes and Jev-backed semantic checks.

Source screenshot of riff
SOURCE SCREENSHOTEXPAND ↗
from the source # riff.tomlselect = ["RIF", "CLR", "JEV"] # omit to use every default-on ruleignore = ["JEV002"] # drop reasoning-leak (noisy on reflective writ...extend-select = ["JEV401"] # turn on a default-off rule (passive voice)jev = true # set false to skip semantic rules
choicenoul ★ 5 Agent tooling
Explore experiment →

jev-guard

by leepokai · JavaScript

Jev Guard checks coding-agent tool calls and returns an allow, ask, or deny decision based on risk and session context.

Source screenshot of jev-guard
SOURCE SCREENSHOTEXPAND ↗
from the source npm i -g jev-guardjev-guard key "…" # TypeSafe key from console.typesafe.ai, or a vck_…...jev-guard install claude|codex|copilot|gemini|cursor|pi|opencode # writes hooks into t...jev-guard check Bash '{"command":"rm -rf ~/"}'# DENY jev-guard blocked this call (risk 3.0/3, approval p=0.98, confidence 0.99): Bash...
choicescorenoul ★ 5 Agent tooling
Explore experiment →

jev-lm

by y0usaf · TypeScript

A word-level language model that drafts with n-grams and asks Jev to check chunks of the result.

Source screenshot of jev-lm
SOURCE SCREENSHOTEXPAND ↗
from the source jev-lm probe "the little dog was" --top 5jev-lm verify "the capital of france is" "paris" "london"jev-lm gen "the little dog" --words 18 --tracejev-lm gen "she went to the door" --draft --tracejev-lm eval --file data/heldout_en.txt --positions 60
choicescorenoul ★ 5 Benchmarks & research
Explore experiment →

typesafe-local

by aabolfazl · Python

typesafe-local asks a local MLX model typed questions and returns calibrated probabilities without generating or parsing prose.

Source screenshot of typesafe-local
SOURCE SCREENSHOTEXPAND ↗
from the source { "model": "mlx-community/Qwen3-1.7B-bf16", "answers": { "refund_requested": {"type": "noul", "noul": 1.0, "raw_mass": 1.0}, "department": {"type": "choice", "choice": "billing",
choicescorenoul ★ 5 Benchmarks & research
Explore experiment →

FindSFSymbols

by tornikegomareli · Swift

Describe the icon you need and watch matching SF Symbols rise out of a physics-driven pile.

Recorded frame of FindSFSymbols
ACTUAL RECORDING12 SEC ↗
from the source questions["s\(index)"] = [ "type": "noul", "instructions": "A person searches an icon library with the text in `query`. " + "Is the icon described at `icons.s\(index)` a good result for that search?", "criteria": [
noul ★ 5 Apps & data pipelines
Explore experiment →

JevOnly

by buluoray · Python

A browser agent with no general-purpose language model: Jev chooses bounded actions, targets and values from each page snapshot.

Recorded frame of JevOnly
ACTUAL RECORDING12 SEC ↗
from the source API_HOST = "api.typesafe.ai"API_PATH = "/v1/systemone"def jev(state, questions, tag): body = json.dumps({"state": state, "model": MODEL, "questions": questions}, ensure_a... headers = {"Authorization": f"Bearer {key}", "Content-Type": "application/json", "Co...
choicenoul ★ 5 Browser & computer use
Explore experiment →

clean-code-review

by frostney · TypeScript

Jev checks a pull request against Clean Code principles; Luna turns the findings into a written review.

Source screenshot of clean-code-review
SOURCE SCREENSHOTEXPAND ↗
from the source browser ──── judge turn ────▶ eve session ──▶ Jev, one call per file (parallel) ◀── 34 answers/file ── typesafe-ai/jev via AI Gatewaybrowser ──── summarize turn ─▶ eve session ──▶ Luna, one call per 6 files + 1 overall ◀── streamed review ── openai/gpt-5.6-luna-fast via AI Gateway
— ★ 4 Agent tooling
Explore experiment →

Jev, briefly

A decision model, not a chatbot.

A chat model generates text token by token and hopes you parse it. Jev never generates a word. Your code sends the state of the world plus typed questions; Jev returns every answer in one parallel pass — typed values with calibrated probabilities and a confidence score your code can trust. About 70–500 ms end to end, $0.042 per million input tokens, output free. Trained with what TypeSafe calls Reinforcement Learning for Calibrated Decisions.

choice Pick one of these.

You define the options. Jev returns the chosen option, a probability for every option, and a confidence. The workhorse of routing, agents, and games — the answer space is always legal, so there is nothing to parse and nothing to hallucinate.

score Rate this on a rubric.

You describe ordered levels — say trivial / normal / critical. Jev returns the level, the probability of each, and a confidence. Scores turn fuzzy judgment (“how severe is this log line?”) into a number-free decision your code can branch on.

noul Is this statement true?

You assert a statement; Jev returns the probability that it is true — a noul. Moderation, verification, guardrails, “does this diff actually fix the bug?”: one question, one calibrated probability.

Official material lives at typesafe.ai and docs.typesafe.ai. JevMade is an independent community registry — not affiliated with or endorsed by TypeSafe AI.

Recurring lessons

Patterns that keep showing up.

One decision per tick

Games, drones, trading bots, and browser agents all converge on the same loop: serialize the state, ask one decisive question, act, repeat. Jev’s latency makes the loop feel instant — the model lives inside the control loop, not outside it.

Confidence as a gate

The answer says what; the confidence says whether to act. The most reliable entries threshold on confidence to route edge cases to a slower model or a human — automation with an honest escape hatch.

Shrink the choice space in code

Makers rarely ask Jev to pick from everything. Local tactics prune 225 gomoku moves to ~40; DOM filters turn a page into an element table; code narrows options, Jev judges within them.

Jev judges, LLMs talk

A recurring split: Jev makes every decision cheaply and instantly, and a small LLM is only invoked when a human-facing string must actually be written. Decision and generation are separate budgets.

Made something with Jev?

Send the link — repo, live demo, post, or video — plus a line on what it does and which primitives it uses. Every entry is verified against its primary source before it ships.

Submit your experiment

Sign in first so we can reply to you. Submissions are reviewed, not published automatically.

Keep this for later

Sign in to bookmark experiments, guides and videos, and keep notes only you can see.

Continue to sign in

We’ll bring you back to this listing.