Entries 145 to 192 of 430, in the hub's default order. The introduction is on page 1.
Showing 145 to 192 of 430
A mobile end to end testing library built on the AI SDK and agent-device, now supporting Jev alongside other models. In one test run Jev finished in 29 seconds for $0.003, versus 37 seconds and $0.07 for Haiku 4.5.
Robert Soriano (@wobsoriano)Opentouchpress on github.com28 starsJev run 29s, $0.003Haiku 4.5 run 37s, $0.07
An independent, evidence-based map of where Jev's calibrated-decision claim holds up and where it breaks down, built from real API-call receipts rather than a leaderboard.
A command-line tool for Jev: ask yes/no, multiple-choice or rubric questions about any text and get calibrated probabilities back as shell exit codes, JSON, or MCP tools.
Local context-pruning proxy for Claude Code and Codex. Jev judges which conversation history is still needed above a configurable size gate, and Yoshi applies the validated omissions before forwarding to Anthropic or OpenAI; the author calls it a proof of concept headed into CompozyOS.
A DuckDB extension that returns Jev's typed answers as native SQL types, so a query can call Jev directly.
Harness that lets Jev control the original StarCraft shareware through synthetic keyboard and mouse input, recording action probabilities for each decision.
Data recipe and scripts to fine-tune a Jev-style classifier on Qwen3.5 4B from 37,840 examples for about $17. Together also serves the result, Tev1-4B-experimental, at $0.042 per million input tokens, and a step-by-step tutorial is on X.
Together AI (@togethercompute)OpenTev1 (Together AI): Jev-like classifier on Qwen3.5 4B on github.com23 starsTraining cost $17Serving price $0.042/M in
Serves typed-decision models, including Laya or your own, behind a Jev-compatible API on NVIDIA GPUs or Apple Silicon, with coding-agent integrations.
Auto mode for the Pi coding agent, which has no permission system of its own. A deterministic layer handles hard denies and your allow and deny patterns, then Jev judges the bash, write and edit calls it escalates and fails closed when it cannot decide. Thresholds come from recorded real-API calibration.
Unofficial study reproducing Jev-style parallel constrained decoding on stock 1.5B-8B models on an Apple Silicon laptop. Prefills context once, broadcasts the KV cache across one batch row per schema field and evaluates all fields in a single forward pass.
A CLI that scans a codebase's source, config, build and CI files with Jev for hidden or data-stealing behavior, pointing to suspicious files and lines as a second opinion before running unfamiliar code.
Python MCP server exposing Jev as classify, score, check, match and screen tools, with a confidence value on every answer. Ships registration steps for Claude Code, Codex and Cursor that keep the API key out of tool arguments.
A skills framework for AI coding agents that adds Jev-based gates and vetting to the workflow.
An asynchronous Jev integration for Hermes Agent that supervises turn admission, tool-call gating and context curation in the background, using up to sixteen typed choice, score and noul questions per call.
Snake auto-played by Jev: one Choice per game tick, with legal moves and board facts computed in code before the call.
Agent-ergonomic CLI for Jev with pick, rate, check, rank, triage and guard subcommands, meant for agents offloading snap judgments from the shell.
Community playground for Jev with around 110 use cases, games, dilemmas and model challenges. Supports editable prompts, A/B comparisons, conversation routing, document field extraction and code-policy inspection in a Next.js interface. Hosted at jev.works.
A Rails-native wrapper around TypeSafe's Jev API that puts typed, calibrated decisions directly in a Rails app's control flow.
TypeSafe structured-output provider for RubyLLM 2, wiring Jev into the RubyLLM provider interface.
Gives an agent one tool to find the documented commands it needs, using Jev to search a nested capability tree and return only the context attached to the selected operations.
A Jev decision layer for agents, shipped as an MCP server, an embeddable DecisionModel library, and an escalate-only Claude Code plugin.
A local server running Laya's typed-decisions checkpoint on a Mac's GPU through PyTorch MPS, with a Pong demo and a memory-versus-latency tradeoff reaching about 32ms median decisions at 2.1GiB RAM on an M5 Pro.
Routes agent skill selection through typed, confidence-aware Jev questions so a weak match is sent for review instead of guessed. On 72 synthetic requests it routed 68 correctly (94.4%) against 51 (70.8%) for a lexical baseline, at a median 1,287 ms; the author labels the results exploratory.
A stock decision terminal, self-titled Jevinik: it pulls live market evidence through Valyu and uses Jev to estimate the probability a stock trades higher in 30 days, without calling a general-purpose LLM.
Measures what a Jev classifier's confidence score is actually worth against real outcomes, and sets the threshold for handing a decision to a human based on what a mistake costs.
Open-source, local decision models inspired by Jev and System One, built on Qwen3 and sized for an NVIDIA DGX Spark.
A native Elixir runtime for Laya built on Nx and Bumblebee, downloading the official checkpoint on first load and answering typed choice and noul questions in-process.
Unofficial Swift 6.4 SDK for TypeSafe that follows the Python SDK's 0.6.0 API, with macro-based question sets for Choice, Noul and Score. Supports macOS 26+, iOS 26+, tvOS, watchOS, visionOS and Linux, and tracks the upstream version it mirrors.
TypeScript browser agent for ego lite with no Chrome, Playwright or browser harness. Each observation produces a numbered element table, and one TypeSafe request picks the operation and the target element. A coding agent can drive the page itself or ask Jev for ranked directions.
An OpenCode plugin that embeds the running session state with Laya and scores how far it has drifted from the calibrated plan using weighted Jensen-Shannon divergence, shown live as a sidebar score.
Pi coding-agent extension that splits large tool results into blocks, has Jev score whether the agent will need each one, and hides low-scoring blocks behind a stub recallable with pi_jev_recall.
Eugene TrapeznikovOpenpi-jev-triage on github.com14 starsContext freed 9.7%Judge spend $0.65
A minimal Pareto-optimal router for OpenRouter models in the Pi coding agent, using Jev to pick a model on the cost-quality frontier for each turn.
Two AI models play real-time Tetris against each other: Jev faces Claude Haiku, Gemini Flash, or an open-weight typed-decision model, with the same piece sequence and clock for both sides.
A fuzzy linter that uses Jev to check code against rules and conventions written in plain language, shipped as a CLI, a GitHub Action and a pi package.
A Three.js first-person flight game where a glowing fly chases goblins in a garden; Jev chooses its heading and dive about five times per second.
TypeScript library that wraps Jev choice, score and noul answers in the parts production needs: a policy, a confidence gate, shadow mode, reusable recipes and an offline eval CLI. On the same row-filter job it measured 1.3 s against 48.9 s for the Claude Code CLI.
Pi extension that lets Jev choose a model and reasoning effort through Vercel AI Gateway, then keeps both pinned for the session. Generation still runs on your existing Pi providers and credentials.
Dependency-free Python CLI that sends text, JSON, files or stdin to Jev and returns machine-readable noul, choice or score answers. Several questions go in one request, and output can be reduced to the primary value for shell scripts.
Agent skill that runs a /jev-me planning interview. Jev scores which questions would change the plan and whether the user's answers actually settle them, and logs the interview for later inspection.
Three runnable experiments: support-message triage producing six independent judgments, a driving simulation where Jev picks lane and target speed against traffic and signs, and an alternative Fable implementation. Shows questions and probability distributions for each call.
Browser-native Doom agent using a Chocolate Doom WebAssembly runtime, structured spatial state, composable AI controls and live decision telemetry.
Rust client for the System One evaluation API with async and blocking backends, Noul, Choice and Score responses deserialised into typed enums, and several judgments batched over one shared state. Retries can be observed step by step and errors stay inspectable.
Open-source LLM router that uses Jev to pick a model, built on LiteLLM. Clients send a single model ID and Jev routes each request; it falls through without a TypeSafe API key.
A minimal grammY Telegram bot that deletes only the messages Jev is confident are spam.
Decision layer for the Pi coding agent, where Jev answers the closed questions a harness asks dozens of times per session: is this command destructive, did that output leak a key, did the agent verify its claim. Rules live in JSON packs, every answer is recorded, and everything fails open.
TypeScript harness that connects evidence to Jev judgments, permitted actions and verified outcomes, with pluggable data sources, local JSONL traces and no runtime dependencies. Marked experimental at V0.2.0, with offline demos and mocked API tests passing.
Scores OpenTelemetry log records with Jev for diagnostic value, priority and routing, so expensive LLM analysis can be skipped for low-value traces. Every record stays in your archive.
Zero-shot robot tasks on a simulated Franka Panda in ManiSkill. Given a plain English goal and the scene, Jev picks one of about 30 hardcoded primitives per step and Python runs it, at roughly one second per pick. No training, demos or policy.
Nothing matches those filters
Clear a filter to widen the search, or send us the thing you were looking for.
