Tool and skill selection with decision models

Python library adding a Jev-based System 1 layer to agents for intent routing, tool safety checks and stuck-loop detection.

Async Python intent and tool router: Jev picks the handler, and a code-side confidence gate stops weak or invented decisions.

Claude Code plugin that scores every installed skill against every prompt with one Jev Noul each and invokes or suggests the winners.

Local Python MCP service that keeps the skill catalog out of the agent's context and lets Jev pick which SKILL.md files to load.

OpenCode plugin that uses two gated Jev calls to inject at most one SKILL.md into the system prompt, or none.

Codex skill and Python CLI that recommends one installed skill per task using Jev Choice ranking and Noul fit checks, or returns none.

Per-prompt capability router for coding agents that picks at most one installed skill, MCP server, subagent or command via Jev, or none.

Fourteen opt-in Claude Code and Codex skills where Jev makes one bounded choice: which skill, model, test, file or next step.

Python agent runtime where Jev Choice decisions pick tools and arguments, and low-confidence picks go to an LLM for review.

Router that puts models, subagents, skills, MCP tools and CLIs in one candidate set and asks Jev one Choice about which handles the step.

Toolkit where Jev condenses large MCP responses for Claude Code and maps Codex requests to reviewed, fixed repository operations.

Middleware for LangChain deepagents where Jev ranks and verifies which SKILL.md skills each turn needs, keeping the rest out of the prompt.

Decision middleware for AI agents that uses local Laya to pick tools and judge results, falling back to an LLM when unsure.

Self-improving multi-platform agent harness with an optional Jev companion for typed judgments and per-session model routing.

Local gateway, MCP server and Claude Code hooks that let coding agents delegate explicit choices, classification and scoring to Jev.

MCP router that catalogs and deduplicates tools and exposes each agent only a relevant, authorised subset using typed decisions.

OmO/senpi agent plugin where Jev or Span-01 rates which skills and next tools fit the task and spots loops or completion.

opencode plugin that routes the agent's small multiple-answer decisions to Jev and labels each answer auto or escalate by confidence.

Claude Code plugin with three Jev tools: verbatim context compaction, per-edit model routing and per-prompt skill selection.

Pi extension for Jev-based tool routing, skill discovery, typed judgments and optional model, thinking, guard and compaction modes.

Pi extension that removes the skill catalogue from the system prompt and adds a skill_search tool where Jev rates each skill 0-2.

Pi extension that strips the inlined skill list and asks Jev which single skill, if any, to load per turn.

ROS 2 robot diagnostics CLI where an optional agent uses Jev to choose which read-only evidence tool to call next.

CLI for Claude Code that ranks installed skills against a session's goal with Jev and says which to load, or to search skills.sh.

Claude Code mod that asks Jev one Noul per skill on every prompt and suggests the skills over a threshold to the model.

Self-hosted, versioned skills library for AI agents with MCP and optional Jev recommendations scoring skills against a task.

CLI that routes a task to one specialist Agent Skill from a Tink library using Jev, then verifies and prints it.

JS and Python library that selects and prunes agent tools and MCP schemas, using offline vector search or Jev with calibrated probabilities.

Prompt router for Claude Code, Codex and Antigravity that picks model, effort, skill and language per request via Jev.

Opt-in Hermes Agent plugin that asks Jev to name the one installed skill worth loading before the model call.