Read & learn
Written guides.
Understand Jev, one idea at a time. Walkthroughs, recipes, and writeups — our notes first, the original next.
Learn, build, and play with Jev — from deep technical guides to creative experiments.
Read & learn
Understand Jev, one idea at a time. Walkthroughs, recipes, and writeups — our notes first, the original next.
Watch & learn
See an idea take shape. Tutorials, demos, and deep dives, organized by topic and credited to their creators.
Make & explore
See what builders made with Jev. Games, tools, repositories, articles, and more — traced to their sources.

Every category, from games and tools to repositories and writeups, traced to a primary source.
Real-time research powered bySame 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.
388 experiments · showing 181–240
Reviews pull-request changes against the practical refactoring rules in Five Lines of Code.
Reads batches of web pages and keeps the passages that best support a research question or planned claim.
Builds a smaller Codex handoff packet by selecting useful evidence verbatim instead of summarizing it.
Cuts long command output down before a coding agent reads it, while keeping selected lines exactly as written.
Temporarily hides older, low-value Pi messages from future requests without deleting them from the session.
Keeps OpenCode on a lightweight cache-friendly parent model until Jev decides a turn deserves a stronger child agent.
Five small gates help coding agents triage failures, stop doomed work, route models, verify steps and choose reasoning effort.
Uses typed Jev judgments to classify relationships between Hermes skills and plan conservative archive operations.
Routes an agent request to a small set of skills by asking Jev which descriptions match.
Uses Jev to select developer tools while leaving code generation and edits to Codex.
A Mnemosyne-compatible memory layer uses Jev to rank evidence and prefetch relevant memories for Hermes agents.
siftr gives coding agents Jev-ranked semantic search, focused file reads, and bounded list selection through a CLI and MCP server.
ActionGate reviews an agent's proposed tool call before allowing it, blocking it or asking for human approval.
Choose Claude Code's effort level from the prompt before the larger model starts work.
Give a coding assistant tools to find relevant source lines, check a claim against a file, rank options and sort records with Jev.
An MCP server for semantic code search and diff checks in Antigravity, Cursor, and Claude Code.
A PowerShell tool that asks Jev to review coding-agent conversations and answer focused questions about them.
An MCP server that brings Jev judgments into Cursor, Codex, and other MCP clients.
An agent skill that uses Jev to predict another skill's next closed decision without running it.
A capability router that matches each coding prompt with installed skills, MCP servers, agents, and commands.
A stop hook that keeps coding agents working until plain-language completion rules are satisfied.
Ask Jev to review code or answer a question from inside Oh My Pi.
Sort through repository issues with help from Jev, while Zero keeps the repository data in sync.
Inspect and operate an SO-101 robot workbench where Jev can choose bounded joint movements.
Lets agents gather audit context while Jev assigns severity, confidence and routing judgments for code-owned policy.
Remove stale read-only Pi tool exchanges while preserving every retained piece of evidence byte for byte.
Filter ripgrep passages for a Codex task without losing the ability to reveal hidden results or nearby code.
Find files and line ranges relevant to a coding task with a searchable map of your source code.
Lets a Flutter integration test state its goal, then chooses registered UI actions until that goal is met or attempts run out.
Applies a YAML policy to Claude Code tool calls, using Jev scores to allow, deny, or review each action.
Ranks Clay people-search results with Jev probabilities for role fit and current operating-founder status.
Composes Unix-style tools that seed, expand, judge, verify, and report code defects while preserving evidence chains.
Routes each agent turn’s effort, tools, skill, and model tier from one bounded Jev request behind a hard deadline.
Turns an agent skill into project-specific Oxlint checks, using AST rules for structure and Jev for contextual judgement.
Adds a zero-dependency CLI and coding-agent skill for batching narrow yes/no, choice, and score judgements.
A command-line referee judges supplied evidence with Jev, compares choices in both option orders and keeps local decision receipts.
Give Jev a list of game moves to choose from, and check what happens after each move.
Give Codex smaller pieces of code to read, with a list of everything the filter left out.
Write review rules in Markdown and ask Jev whether changed lines violate them; code attaches findings to those lines.
Put Jev between an agent and its tool collection so the agent sees a smaller, task-specific menu.
jevcrawl is an open-source web crawler and scraper for AI assistants, using a small decision model to score links and passages so agents receive exact source excerpts rather than entire sites.
HiRoute is a local routing engine that evaluates each new agent turn to direct tasks across different AI models based on complexity and stage.
KiroGraph adds optional decision-model checks for memory relationships, contradictory wiki pages and custom authentication wrappers in a code knowledge graph.
Find C# symbols in VS Code by describing them in English; Jev translates the request and a local code-analysis server finds matches.
Build a tool-using assistant with a writing model and Jev checkpoints that suggest when to reconsider a result, change or answer.
Route user messages, retrieved text and tool output toward allow, review or block using Jev risk signals and a local policy.
A local proxy and dashboard that keeps Jev answers alongside the question versions, usage estimates and review labels that produced them.
Let a coding agent fix a GitHub issue, with tests and AI reviewers checking its work before it proceeds.
An experiment in checking an agent's work before handing it to another agent, with Jev helping review the evidence.
A CLI and GitHub Action that combines deterministic rules with Jev to assess the risk of code changes.
A configurable Go CLI that uses Jev to route prompts between models.
An experimental Hermes plugin for planning model routes within budget and capability constraints.
A Grok skill that combines Jev probabilities with prior beliefs to choose the next action in a builder-agent loop.
An automated pull-request reviewer with Jev-based approval thresholds and escalation to trusted owners.
A Jev-powered permission gate for the omp coding agent.
A Pi extension that sends agents back to work when Jev determines they stopped before completing the task.
A Pi coding coprocessor that uses Jev gates to review changes from the initial baseline and record an append-only activity trail.
Ask Jev to choose, score or answer yes-or-no questions without leaving a Pi coding session.
A Pi extension that exposes five tools for narrow Jev judgments while leaving thresholds and actions in application code.
A standard-library Python gateway that checks prompts for risk and routes safe requests to a suitable model.
Jev, briefly
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.
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.
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.
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
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.
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.
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.
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.
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 experimentSign in first so we can reply to you. Submissions are reviewed, not published automatically.