Agent tooling — page 13

Jev powered pre-execution guard for terminal coding agents

pi-thinking-router-jev —— pi 的自适应 Thinking Level Router。在任务起点、推理型失败与稳定窗口咨询 jev 决策模型（未配置时本地 规则兜底），动态选择 low/medium/high/xhigh 推理档位：简单改动降档、复杂 debug 升级、失败可升级、稳定可降级。含防抖钳制 、失败安全回退与 JSONL 决策日志，不切换模型、零侵入 agent loop。

Jev-judged context compaction for DeepSeek Harness: semantic tool-result pruning + deterministic receipt compaction

Jev-powered model and reasoning-effort router for Codex in DeepSeek Harness

OpenCode v2 plugin that uses Jev (TypeSafe AI) to dynamically select relevant skills and tools per turn, reducing context window usage.

Verdict-based context compaction for DeepSeek Harness — replaces lossy LLM summaries with fast keep/truncate/drop decisions from jev-latest; everything kept stays verbatim. Port of tamaratran/fast-jev-compaction.

jevkit: fast typed decisions for agents. CLI and MCP tools (route, triage, guard, grep, rank, compact, judge) on TypeSafe Jev. Zero dependencies.

Practical agent skills and examples for building with Jev. API setup, routing, ranking, and evidence checks.

Message triage CLI in Go, built on the Jev decision model from TypeSafe AI. Categorizes messages, scores urgency, and flags low-confidence ones for human review.

DSH plugin: register TypeSafe Jev (System One decision model) as an agent tool — jev_decide returns calibrated probabilities (noul/choice/score) for routing/triage/guardrail judgments, no text generation. 把 TypeSafe Jev 决策模型注册为 DSH agent 工具

Smart Codex overlay featuring JEV-model-based routing, contextual optimization, and Kanban automation. Reduce token consumption by up to 70% while maintaining control

Jev Decisions Plugin for Hermes (and other AI Agents): tool risk reviews, human approval recommendations, evidence checks, a local decision journal, local decision supervision, and learned corrections.

See what Jev thinks about your SaaS website — powered by ReplyNodes web context and Vercel AI Gateway.

Telegram channel X-ray: Jev judges a year of posts, you get a card. One Cloudflare Worker.

Continuous verbatim context pruning for OpenCode, powered by TypeSafe Jev. Port of fast-jev-compaction adapted to OpenCode's context hook.

Agent skill that spots bounded-judgment steps, tries a typed decision model (TypeSafe's Jev) first, and documents every attempt

npx skills add raydocs/ego-verified-actions — bounded ego-lite clicks with checkable SUCCESS_MATCH

A tiny virtual pet cared for by TypeSafe Jev through OpenRouter

A typed Python framework for controlling Android over ADB with Jev.

Claude Code plugin that scores how well you prompt a coding agent, and shows whether your habits are improving. Runs on TypeSafe's Jev model. Zero added latency.

Agent Skill: harvest links from newsletter emails into Raindrop.io with the author editorial context attached - Gmail read-only, three-layer dedup, zero-context library compare

Plugin for oh-my-pi that uses Typesafe Jev API to classify tool calls as safe/unsafe/ask

Tell Claude Code which installed skill a session needs, using Jev (TypeSafe AI) for the decision and skills.sh for discovery.

Worked examples for TypeSafe's Jev System One decision model, runnable today through OpenRouter