Tools & apps

I built a CI tool this week that reads every pull request and says whether it is AI slop. It flags speculative abstractions, tests that only assert on mocks, swallowed errors,…

- Jev is a fundamentally different kind of evaluator. It returns typed answers directly instead of generating text like an LLM judge. - Jev was dramatically more consistent on…

The project combines TypeSafe Jev, GitHub Copilot CLI over the Agent Client Protocol (ACP), and a native VS Code chat participant. Together, they create a diagnostic layer for…

Eric Kang Posted on Sep 20 # Agents Make Three Decisions All Day: 18 JEV Use Cases and When Not to Use It A production agent makes the same three kinds of calls all day: pick one…

jomatsu

github.com

↗

Pairs local Zod shape validation with Jev semantic validation.

saibimajdi

github.com

↗

.NET SDK for Jev.

zhirschtritt

github.com

↗

Idiomatic Go SDK for the TypeSafe API.

krzyzanowskim

github.com

↗

SwiftPM client whose behaviour follows the official JavaScript SDK.

m0rphtail

github.com

↗

Security alert triage as a Unix filter: JSONL alerts in, typed decisions out.

sharziki

github.com

↗

Typed semantic decisions for Unix pipelines and CI.

kunobi-ninja

github.com

↗

Rust client, published on crates.io.

AboveColin

github.com

↗

Async Python client for typed Jev questions and probabilities.

valentynkit

github.com

↗

Neovim plugin that splits the buffer into functions with Treesitter, scores each against a plain-language question with Jev, and ranks answers by probability in the quickfix…

mrnugget

github.com

↗

Ranks existing zsh history entries for inline completion; accepting a suggestion does not execute it.

dannote

github.com

↗

Elixir/OTP client designed around GenServer replies and pattern matching.

Alurith

github.com

↗

Read-only Go CLI that checks files against rules such as unclear responsibility or weak error handling with Jev, locally or in CI.

pithings

github.com

↗

Small type-safe client for asking Jev questions about datasets.

shitianfang

github.com

↗

Experimental gate where Jev decides whether a timer or incoming event is worth resuming a sleeping agent's LLM; code skips only when Jev is confident and always wakes on user…

noelzappy

github.com

↗

Runs seven checks on every LLM response in one Jev call, as AI SDK middleware or an OpenAI-compatible proxy.

TanStack

github.com

↗

`@tanstack/ai-typesafe` adapter exposing typed Boolean, Choice, and Score decisions through TanStack AI's `decide()` API.

HarnessRouter

github.com

↗

Turns a decision model into an agent loop: it compiles the environment's finite action space into typed questions, gates each step by confidence, and records the trace.

supercorp-ai

github.com

↗

Scores source files so coding agents can prioritize code-quality work.

devagrawal09

github.com

↗

Bounded Jev workflows for coding agents (formerly jev-code).

lukstei

github.com

↗

Rule-based text grader that uses Jev scores and line-by-line flags to audit documents against custom rulesets and guide an AI agent to auto-fix violations.

obie

github.com

↗

Ruby client with standard-library transport for TypeSafe and OpenRouter decision endpoints.

0xPlaygrounds

github.com

↗

Rust `rig-typesafeai` crate with typed Choice, Score, and Noul queries, response validation, examples, and fixtures.

pydantic

github.com

↗

TypeSafe model provider that derives Jev questions from Pydantic output types and supports typed routing and fallback workflows.

irfndi

github.com

↗

Liquidity-provision agent for Meteora DLMM.

DevMortimer

github.com

↗

Pi extension that judges rule compliance, risky actions, stuck loops, and completion claims; enforcement depends on the hook and policy.

joelhooks

github.com

↗

Pi extension that prunes stale tool history and leaves summary compaction to Pi when pruning is insufficient.

lakeday-org

github.com

↗

Semantic code linter that evaluates code units against configurable Jev questions.

wobsoriano

github.com

↗

Oxlint rules written as plain-English questions about a function, call, JSX element or file, reported when the yes-probability clears your cutoff.

aaronshaf

github.com

↗

Keeps an OpenCode parent model fixed and uses Jev difficulty judgments to delegate harder turns to temporary subagents.

Nanako0129

github.com

↗

Claude Code skills that wait for CodeRabbit, Copilot or Codex to finish reviewing a pull request, then judge whether the verdict actually permits a merge.

BerriAI

github.com

↗

Jev-backed complexity routing and an optional relevance guardrail for compacting tool results before they return to an agent.

langchain-ai

github.com

↗

JavaScript/TypeScript classifier Runnable and middleware for bounded routing and tool-call checks.

langchain-ai

github.com

↗

Python `TypeSafeClassifier` Runnable with batched typed questions plus model-routing and risky-tool middleware.

runta-dev

github.com

↗

A general-purpose agent loop where Jev picks the next move and Jot runs it.

PanAchy

github.com

↗

Plugins for coding agents, starting with one that auto-approves shell permission requests it judges harmless and passes everything uncertain to the normal flow.

cocktailpeanut

github.com

↗

Symbolic-music studio where Jev chooses plans, instruments, and bar patterns, and code renders editable music and MIDI.