182 tool takes since 2026-08-19
A pipeline that generates vertical short videos using LLMs, Whisper transcription, highlight detection, and automated editing.
An open-source tool that rewrites AI-generated text into more human-sounding output using a multilingual LLM-powered pipeline.
A free course covering AI engineering topics from machine learning and neural networks to LLMs, RAG, AI agents, and AI system design.
A Mac utility that saves and restores per-project window layouts, each accessible by a single shortcut.
Uses Jev to tune GPT-6 reasoning effort per Codex task, reducing token usage without manual configuration.
Separate AI models for brand analysis, typography, and symbol design feed a composition engine that outputs real logo lockups with clear-space rules.
Every pick in the Wire gets the same treatment: read, verified, and given a written verdict.
A starter kit for animating hand-painted cartoons with Claude, bundling p5.js, p5.brush, a character, and 31 acted emotions.
JevHarness lets LLMs author task-specific eval harnesses, with optional full-trajectory reward reflection and GEPA evolutionary refinement.
A database of user-agent strings for 100+ browsers on 100+ operating systems, updated every 5 minutes via GitHub Actions.
Repo holding the source code behind an AI-generated music video built with Claude Opus 5.5, themed around p(doom).
A menu-bar app that routes multiple AI coding agents to any model backend from one place.
A JavaScript agent that generates a 30-second vertical film with drawn visuals and score from a given topic.
Every pick in the Wire gets the same treatment: read, verified, and given a written verdict.
One-prompt Claude Code skill that generates a looping animated 3D icon with real transparency.
Converts local LLMs into Jev-style structured decision models via prefill alone—no token-by-token decoding, supports text and images.
An MCP connector that gives AI agents access to Typesafe AI's jev model and open-weight models like Laya.
A 0.6B decision model for AI agents that takes unstructured state and structured questions and returns probability distributions in one ~50ms forward pass.
An educational visual inference experiment for Apple Silicon using shared context and direct candidate scoring.
Per-turn routing layer for Codex that selects model, thinking depth, and speed mode for each turn.
Every pick in the Wire gets the same treatment: read, verified, and given a written verdict.
Browser automation split between Jev (clicks) and Codex (reasoning/verification), claiming 5–10x faster operations; built at EZCollegeApp.
Open, local alternative to Jev: routes typed LLM decisions without generating a single token.
A motion-graphics project showing a finished ad alongside its black-and-white draft frames, with frame-accurate MP4 export.
jev-router picks the cheapest Claude Code model per task, reducing costs without manual model selection.
Vulkan reimplementation of NVIDIA's DLSS 5 Neural Rendering that targets bit-exact parity with the original closed-source network.
Wraps TypeSafe's Jev model as MCP tools for fast, cheap, typed judgments in agent pipelines.