Agent loop control with decision models

Python kernel of Jev Choice/Score/Noul gates, caches and loops used to admit or reject Lean proof candidates in research pipelines.

Coding agent that runs discriminative Monte Carlo Tree Search, with Gemini proposing actions and Jev Choice and Score guiding the search.

Kernel coordinating several Claude Code agents on one repo: Jev rates collision risk before each write to pass, wait or escalate.

Embodied Minecraft agent where a typed decision plane (Jev or Liquid d1) picks grounded transitions and a kernel owns verification.

Rust agent-facing CLI built on the unofficial jev-sdk crate: predict, choose and score with strict stdout and meaningful exit codes.

Orchvia: local engine with TS and Python SDKs that runs Claude Code and Codex agents as a team, routing tasks by code and typed decisions.

Native Bend executable that owns agent-launched processes and logs, and asks Jev a typed question only when told to.

Local MCP server putting Jev in the coding loop: route next steps, pick prepared tool calls, review patches and verify claims.

MCP server, CLI and Claude Code skill with Choice, Score and Noul primitives and a confidence gatekeeper, hosted or offline.

Russian-language Jev toolkit with a zero-dependency Python client, key pooling and a guide to free credits via a third-party relay.

Minimal web demo: paste an agent step trace and Jev judges whether to continue, retry, escalate or stop.

Explainable day-trip planner where an LLM drafts the itinerary and Jev screens places, compares transport and reviews each step.

Zero-dependency agent harness that sends each loop fork (act?, which tool, risk, done?) to a decision model and keeps the LLM for writing.

Simulated espresso bar where an XState machine defines what is possible and Jev chooses the barista's next event.

Tiny demo that asks Jev whether an agent should continue, downgrade its model, or stop, given budget and plan.

Agent skill that sends closed coding-agent judgments to Jev before asking the user, before risky commands and after failures.

Experimental Hermes Agent plugin for bounded Jev worker checkpoints, route advisories and request-goal tools.

Open-weight 0.6B decision model on a Qwen3 backbone: state and typed questions in, a probability for every option out, nothing decoded.

DeepSeek Harness plugin with jev_decision tools, an opt-in risk and loop auto-guard, and a live self-test benchmark against the Jev API.

Python library and CLI that turns noisy sources like CI logs, diffs and web pages into small, traceable Jev briefings.

Gate that asks Jev whether a timer or event is worth resuming a sleeping agent's LLM, skipping only when confidently not.

JIT-JEV Context OS: deterministic context compiler plus a Jev System 1 gate that scores AST relevance, test proofs and tool targets.

Benchmark where Jev steers an agent through 100 key-and-door grid puzzles, one Choice per move, scored against an exact BFS solver.

Data-analysis agent where an LLM runs Python analysis and Jev decides whether to continue, switch direction, verify or stop.

Project premised on offloading cheap routing decisions from an LLM to a decision model while the LLM writes, tests and revises.

Respan's behaviour classifier for AI traces that returns present, absent or not observable for each plain-language behaviour you define.

Audio-native decision model for live voice agents that picks respond, wait, yield, backchannel or escalate straight from call audio.

Paper on where Jev and Laya fit in LLM pentest agents: finding adjudication, severity recalibration, pruning and confirmation loops.

macOS voice agent where Jev picks each step's operation and target control, escalating to an LLM agent when unsure.

DeepSeek Harness preset where Jev answers an agent's open end-of-turn questions, steering it on only above confidence and safety thresholds.