Awesome Jev / Decision Tools

Decision Tools

Standalone decision helpers, schema validators, probability decoders, and utilities.

Back to All Projects12 reviewed repositories
jev-playground repository icon by Little-Planet-Labs

Little-Planet-Labs

jev-playground

1
Decision ToolsMITTypeScript

A web playground for entering state and decision questions, then inspecting Jev answers and probability distributions.

What Jev does here

Submits multiple Noul, Choice, and Score questions in one request.

Lets users try questions and answer options before writing application code.

#typed-decisions#evaluation-benchmarks
2 evidence links
Inspect details
jev-predict-skill repository icon by DanielKillenberger

DanielKillenberger

jev-predict-skill

1
Decision ToolsMITHTML

An Agent skill recipe that predicts another skill’s closed-set outcome from its rules and evidence.

What Jev does here

Jev first assesses whether a closed decision is possible, then selects among the target skill’s outcomes.

Includes API-call and response-check examples; it predicts the outcome without executing the target skill.

#mcp-integrations#typed-decisions
2 evidence links
Inspect details
jevify repository icon by altryne

altryne

jevify

3
Decision ToolsMITPython

An Agent Skill for finding suitable Jev decision points and designing questions and comparison experiments.

What Jev does here

Designs Noul, Choice, and Score question packs for an application, with a script for API-backed case runs.

Connects integration ideas, question design, and evaluation methods.

#mcp-integrations#evaluation-benchmarks#typed-decisions
2 evidence links
Inspect details
1
Decision ToolsMITJavaScript

A chat-style Jev demo whose answers are selected from predefined or custom options rather than generated prose.

What Jev does here

Maps answer styles to Choice options and selects chat titles from fragments of the question.

Shows answer options and probabilities in a chat UI with customizable answer sets.

#voice-conversation#typed-decisions
2 evidence links
Inspect details
hermes-jev repository icon by keeltrace

keeltrace

hermes-jev

4
Decision ToolsMITPython

An asynchronous Jev companion for Hermes Agent covering relevance, completion, recovery and optional admission decisions.

What Jev does here

Jev evaluates bounded questions in the background while Hermes retains reasoning and execution responsibilities.

Records decision provenance and supports configuration that avoids blocking ordinary execution.

#mcp-integrations#evaluation-benchmarks#typed-decisions
2 evidence links
Inspect details
killmyidea repository icon by monteduro

monteduro

killmyidea

17
Decision ToolsMITTypeScript

A startup-idea evaluation demo assigning KILL, FIX or SHIP labels from Jev scores.

What Jev does here

Jev answers scoring, category and clarity questions; local weights and gates calculate the final label.

Shows a structured assessment process, not market validation, a success forecast or investment advice.

#domain-workflows#typed-decisions
34 evidence links
Inspect details
jev-commit repository icon by valentynkit

valentynkit

jev-commit

0
Decision ToolsMITTypeScript

A commit-msg hook that scores the message against the staged diff with one Jev request of five Nouls and warns by default. Default blocking is a local regex belt on high-precision added-line hits; the secret_shaped Noul blocks only with --strict.

What Jev does here

Five Noul questions in one request: checkable message, hunk match, debug leftovers, unmentioned work, and credential-shaped added lines. Default blocking is the regex belt; secret_shaped participates only under --strict.

Turns commit-message review into thresholded probabilities instead of prose; API failures still allow the commit.

#typed-decisions#classification-ranking
2 evidence links
Inspect details
jev-belay repository icon by valentynkit

valentynkit

jev-belay

1
Decision ToolsMITTypeScript

A Claude Code Stop hook that reads the turn transcript locally and calls Jev only when files changed and no check has passed, blocking an unverified “done”.

What Jev does here

Four questions: whether the closing message claims done, claims checks passed, whether verification applies, and a complete / partial / blocked / other choice.

Skips the model when a check already passed; every error path lets the turn end.

#typed-decisions#classification-ranking
3 evidence links
Inspect details
jev.nvim repository icon by valentynkit

valentynkit

jev.nvim

0
Decision ToolsMITTypeScript

A Neovim plugin that asks a plain-language question of every function in the buffer and lists every Jev hit in quickfix, ranked by probability.

What Jev does here

Scores each Treesitter function against the user question, splitting across requests if the buffer does not fit. Every hit is listed in quickfix; only hits at or above the threshold get buffer marks.

Finds cross-language shapes that grep misses, and lands the ranked hits in the existing quickfix loop.

#typed-decisions#classification-ranking
3 evidence links
Inspect details
jev-skip repository icon by valentynkit

valentynkit

jev-skip

1
Decision ToolsMITTypeScript

A browser extension that classifies YouTube caption segments with Jev, splitting requests when the segment or token budget is exceeded, paints five categories on the seek bar, and auto-skips those painted slices over the threshold.

What Jev does here

One Choice per caption segment among content, sponsor, intro, outro, self_promo, recap, and other. Painted categories sponsor, self_promo, intro, outro, and recap skip when probability is at or above the threshold; content and other never skip.

Works on videos nobody has labeled yet; with no captions it does nothing.

#typed-decisions#classification-ranking
2 evidence links
Inspect details
Decision ToolsMITTypeScript

Pokemon Red on PyBoy where Python owns the route and the arithmetic, and Jev chooses only among legal actions at actual branches.

What Jev does here

A Choice over legal actions at each branch; battle turns also ask Noul faints_this_turn and should_flee; failures take the code default.

The model only picks among code-proven legal moves; a failed call never loosens the script.

#typed-decisions#classification-ranking
2 evidence links
Inspect details
0
Decision ToolsMITTypeScript

Interactive three-level AI interrogation game powered by TypeSafe Jev; write responses and pass plea, logic, and paradox verdicts to earn release.

What Jev does here

For each level, Jev evaluates release probability plus plea, logic, and paradox signals, then selects a persuasion tactic and scores persuasiveness.

Turns structured Jev judgments into playable feedback, pass thresholds, and leaderboard results that show how arguments affect release probability.

#typed-decisions#games-simulation
2 evidence links
Inspect details

Explore Other Architecture Categories

Explore Jev Decision Workflows