Tracing and observability with decision models

Example of using Jev as a webhook guardrail inside the agentgateway proxy to inspect model requests and responses.

Agent observability platform that finds and fixes agent failures, with an optional Jev preclassifier for conversation checks.

Large Claude Code plugin of skills, agents and hooks that can optionally ask Jev to classify a session's work category.

Open-source workspace for building, deploying and monitoring AI agents and workflows, listed as integrating TypeSafe System One.

Cognitive control layer for OpenCode that uses Jev to compute GO, DELIBERATE, VERIFY or BLOCK for agent actions, observing by default.

Local desktop pal that verifies what a coding agent really did, with optional Laya or Jev double-checks of unclear test results.

DeepSeek Harness plugin checking whether an agent's 'done' claim is true, using deterministic evidence plus one batched Jev assessment.

Supervisor for unattended coding agents: one batched Jev Choice over the trajectory decides continue, pause or escalate.

Local guard layer for coding agents that blocks dangerous tool calls by deterministic rules, with optional Jev judgments.

Nautilus Compass agent memory layer whose jev-trust middleware logs Jev decisions and measures calibration in your domain.

Scores OpenTelemetry logs with Jev for diagnostic value, priority and routing before any expensive LLM analysis.

Local gateway and MCP tools that let Jev predict which tool a coding agent should call next, from suggestions to enforced choices.

Splunk search command that asks Jev typed questions about events and adds probabilities, choices and scores as fields.

MCP server that lets Claude Code or Codex drive real Chrome with Jev picking elements and checking steps, plus safety gates and traces.

GitHub Action where Jev rates each PR across 19 software-quality dimensions, gates on thresholds and logs to a RawTree dashboard.

Toolkit for Jev decision contracts: compiled policies, egress controls, tracing, stability checks and certified decision SLOs.

Decision-forensics library that explains a Jev answer by ablating parts of the input and measuring how far the probability moves.

CLI that grades the coding-agent sessions on your disk (Claude Code, Codex, opencode, Gemini CLI) with Jev for cents.

Rust CLI and TUI that streams Kubernetes logs, applies offline rules and Jev analysis to flag what matters, then hands off.

Zero-dependency local gateway and live visualiser that proxies Jev calls, logs every decision to SQLite and draws them on a real-time map.

Local-first macOS coding workspace that runs your agents and lets a local Laya or hosted Jev selector pick a route the host validates.

Records the full distribution of every Jev answer by state, question and model, so thresholds can move over history with no new calls.

Single-agent Jev coprocessor for Pi: semantic pre-edit gates, evidence checks, diff review and append-only telemetry.

Pi extension that judges each new message unit once with Jev, omitting unneeded units from context and logging removal reasons.

Slack-like playground for watching computer-use agents work, with replays, comparable runs and Jev choosing from a menu of visible actions.

Code navigation tool where a lexical index proposes candidates and Jev's typed judgments decide which files and lines belong.

Tern plugin that beeps when a coding agent finishes or needs you; Jev picks mood, voice, pitch, pace and energy for the sound.

Monitoring proxy and client that records Jev answer probabilities and alerts on version changes, drift, edge crowding or accuracy drops.

macOS app showing each Claude Code or Codex session as a bird; Jev optionally flags abusive messages and plain-text questions.

Chinese-documented LLM gateway with virtual model routing, protocol conversion and a transparent Jev System One proxy.