Tracing and observability with decision models

Desktop app running coding agents in parallel git worktrees, with optional Jev judgments of each changed file against the task.

Hackathon agent monitor that scores chains of sandboxed agent actions with Jev and escalates through a fixed L1-L5 containment ladder.

Observable browser stealth game where Jev supplies guards' typed threat, suspicion and intent judgments while code owns the world.

Python guardrail with a Streamlit dashboard that sends agent tool calls to Jev and allows, blocks or asks for clarification.

Local dashboard to watch Jev play Freedoom via ViZDoom, showing choices, probabilities, latency and cost with spending bounds.

Smart-meter fleet dashboard where code pre-filters telemetry and Jev classifies anomalies for remediation across millions of endpoints.

UiPath prior-authorisation triage agent with a Jev guardrail that measures and records PII crossing the model boundary without masking.

Imports agent traces from LangSmith, Langfuse or OpenTelemetry and tests whether a smaller decision model can make routine choices.

Local-first, outcome-aware model router for coding harnesses that picks a capability tier per task with Jev and learns from history.

OpenTelemetry Collector processor that asks Jev how useful each metric is from its metadata and applies keep/drop policy.

OpenTelemetry trace processor that asks Jev whether an operation is diagnostic, business-critical and worth keeping, and annotates spans.

AI life-and-civilization simulation where Jev makes every person's next action as an auditable Choice and LLMs only plan.

Linear-backed work ledger for coding agents where a Jev-compatible model verifies done reports, blockers and plan changes against the task.

Open lab on using Jev routing in front of Claude Code correctly: measured bugs and patch, hard fallback, completion gate.

Offline Python toolkit that measures sensitivity, Fisher information and information loss in the probabilities of Jev-style agent systems.

Community Go client for the System One API with functional options, context cancellation and optional Langfuse tracing.

Community Rails integration for System One with configuration, persisted usage and cost telemetry, and fail-closed confidence policies.

TypeScript runtime that turns Jev's probabilistic answers into versioned, replayable decisions via ordered YAML policy rules.

Browser driving simulator on real Canadian streets where you can replay every decision the AI driver made and why.

Browser Doom experiment where two WebAssembly engines play from the same start and Jev picks tactical macros from structured state.

Industrial demo replaying compressor telemetry where code flags anomalies and Jev picks the manual fault, severity and certainty.

Local Python toolkit and web dashboard for trying Jev via OpenRouter or TypeSafe, with review analysis, topic routing and request history.

Standalone Android agent on Mobilerun where Jev picks every operation and target, with a live React studio, CLI and traces.

Open 150M encoder that answers noul, choice and score questions in one pass, trainable on a free Colab T4 in about 30 minutes.

Offline CLI that measures whether a classifier's confidence matches reality and turns mistake costs into a human hand-off threshold.

Openlayer library packing agent evals and guardrails (tool choice, grounding, injection, PHI) into one decision-model request.

Benchmarks Jev against frontier LLMs on Who&When Pro: attributing multi-agent failures to an agent, step and error type.

Benchmark asking Jev and a local LLM whether each collusion.wiki page was agent-written; neither beats the majority baseline.

Python trust middleware for the Jev API that logs decisions, measures calibration from your recorded outcomes and signs the evidence.

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