Entries 49 to 83 of 83, in the hub's default order. The introduction is on page 1.
Showing 49 to 83 of 83
CLI that lints UI code, copy, and agent instructions for AI slop on every commit. Local rules handle the measurable checks; the judgement calls go to Jev as yes/no questions that come back as probabilities, and a set of rules can fail the run.
Labels GitHub pull requests using Jev's typed decisions, sizing changes by conceptual scope rather than lines changed.
A local-first test selector that asks one semantic relevance judgment per test to decide which e2e tests a code change can safely skip, failing open to the full suite on low confidence. Judge is pluggable between classifier.dev, Jev over HTTP, or self-hosted Laya via ONNX Runtime. Ships a bundled GitHub Action.
Lets a person or coding agent ask a plain-English question across a repository. Hunch sends each in-scope chunk to Jev and returns scored source locations, without needing to guess which words the code uses.
A Codex plugin that asks Jev which bulky tool results a session still needs, then replaces the rest with a bounded head and a one-line note, so long sessions don't resend stale output on every turn.
Checks an OpenAPI spec for breaking changes hidden in its prose, combining deterministic schema checks with Jev's semantic review.
An MCP server that hands small coding-agent decisions, such as which file to edit or whether a diff breaks tests, to Jev instead of spending reasoning tokens on them. Works with Cursor, Windsurf and Claude Code.
A local desktop and CLI coding agent where Jev selects the next tool from the user's request and recorded execution results, while DeepSeek or a local model supplies the arguments.
Agent skill that sends closed coding-agent judgments to Jev and acts on the probabilities. Jev answers yes/no, choice and score questions in about 250 ms, so the agent interrupts the user only when a person must decide, and stops before a command that could destroy data or leak secrets.
Stop hook that keeps a coding agent from finishing early. You write completion rules in plain language, and every time the agent is about to stop, Jev scores the stop against each rule in 0.7 seconds and sends it back to work if a rule is violated. Works with Claude Code and Codex.
Claude Code mod that routes decisions to Jev: it ranks installed skills against each prompt and answers the agent's own this-or-that questions when confidence is high enough, otherwise falling back to asking the user.
An automatic extension for the Pi coding agent that has Jev score older tool outputs and stops resending the ones no longer needed, while keeping the original session messages intact.
An MCP server and agent skill for using Jev from a coding agent at design time: question linting, batch evaluation, threshold calibration and taxonomy exploration.
A personal skill router for Claude Code that uses Jev to decide which of your installed skills a session needs, built after the author found they only reached for five of about 90 installed skills.
A Codex CLI plugin that uses Jev to score which of a project's skills are relevant to a prompt, passes the matches to Codex, and shows selection history on a local dashboard.
Semantic code search for coding agents built on Jev, packaged as a CLI and MCP server, with results reported on SWE-bench Lite.
Agent skill that hunts for fuzzy semantic judgment in a system and turns it into small Choice, Score and Noul questions, deciding where the Jev boundary belongs, what state each question sees and which ones can run together. Meant to be installed alongside TypeSafe's official skill.
Has Jev select a native Codex tool call before the coding model runs, so Codex executes it through its own tool runtime and approvals while the coding model handles reasoning and edits.
Learns a repository's decision norms from its history, then uses Jev to adversarially judge past decisions against those norms, through five Unix-style primitives: seed, expand, judge, verify, report.
A PreToolUse hook for Claude Code that scores every tool call against a YAML policy you own and allows or denies it in about 100ms, with no LLM call in the loop. Runs on Jev today, with local models planned next, and publishes a calibration table.
A coding-agent CLI that splits work between a decision model, Jev by default or self-hosted Laya, which only picks the next tool and scores progress and risk, and an OpenAI-compatible LLM that fills in the tool arguments.
Turns a set of coding-agent skills into oxlint rules, using Jev to do the classification.
A configurable GitHub Action that reviews directory submissions and classifies pull requests using only Jev: typed yes/no checks plus one category choice, with code applying the policy and posting one PR comment.
Multiplayer triage dashboard for public GitHub repositories, where a System One model answers a fixed set of typed questions per issue: what kind, how severe, how urgent, whether it duplicates another, and what a maintainer should do next. People correct the answers, corrections are shown back on later runs, and nothing is written back to GitHub.
A Jev-based model-routing experiment for Codex tasks that the author now recommends against adopting: in a Pokedex benchmark, the Jev-routed team cost almost as much as running the top model alone and missed the time limit, while the single-model run finished and passed all checks. Code and results are public as a negative benchmark.
A Rust CLI that reads completed Claude Code and Codex sessions, scores them with Jev, and suggests specific changes to your agent instructions, skills and tools based on where work went well or got stuck.
Four Claude Code hooks that use Jev for cheap, calibrated judgment calls inside the agent loop: a danger gate that blocks destructive tool calls, a failure notice, a completion check, and a scope check.
A video demo shows Jev returning 14 typed probability checks per pull request diff, such as hardcoded secrets and SQL injection, which code turns into a block, review, or merge verdict. Checks scoring between 0.35 and 0.65 confidence are escalated to a human or a larger model.
Paolo Rosson (@redp314)OpenFourteen checks for every pull request (X) on x.com357k viewsCost per PR $0.00007vs Opus, 1k PRs 7c vs $14.50
A video demo feeds Jev 3 million session-replay events. In 40 seconds it watched 3,247 sessions, caught 132 rage clicks, 116 dead clicks and 95 JavaScript errors, and opened 213 draft pull requests to fix them, for $2.17 in total.
Taras (@tarasshyn)OpenSession replay to bug fixes (X) on x.com101k views3M events 40s, $2.17
A video demo of jev-review, an experimental local-first MCP plugin that scores a coding agent's work against quality metrics; the agent calls Jev, gets scored, makes improvements, and repeats the loop.
An experimental linter for Postgres Row Level Security policies, built with Jev. It sends nine judgments about a submitted policy and table schema in a single request to check whether access controls actually restrict users to their own data, not just that RLS is turned on.
Paste a public GitHub pull request. DiffJury fetches the dossier and Jev returns a risk verdict, safe to merge or needs review, with no essay.
Raihan Khan (@raihankhan_rk)9.3k viewsOpenDiffJury: Jev decides if this PR is risky or not on diffjury.up.railway.app
Open source harness layer for coding agents that added Jev as an opt-in System One decision layer, used for typed tool gates, decision packs, and rubric checks while coding models still write the code.
Auto mode preset for the DeepSeek Harness coding agent, hosted on a self-run GitLab. At every end prompt, Jev decides whether the agent's open questions can be answered without the human, so full-access runs stay guided by a typed decision.
Official docs for the TypeSafe agent skill, which gives a coding agent context on the three question types, architectural patterns and evaluation practice. Installs via Claude Code plugin, npx skills, or manual copy.
Nothing matches those filters
Clear a filter to widen the search, or send us the thing you were looking for.
