claudeers.

Projects tagged #jev

// jev (16)

🔓

A curated list of public projects, integrations, and discussions built on Jev — TypeSafe AI's System One model for typed decisions.

// uncategorizedyibie/⟨Python⟩★ 2,559[ claude ]
🔓

Jev-compatible API server for open decision models. Ollama for decision models: pull and serve 25 model families (Laya, pplx-decider, Clef, Winnow, coba...)…

// uncategorizedollaya-dev/⟨Rust⟩★ 1,451◷ Apache-2.0[ claude ]
🔓

Auto mode for every coding agent, built on Jev: risk-scores every tool call with session context (deny / ask / allow), flags prompt injection in results, che…

// securityleepokai/⟨JavaScript⟩★ 153◷ MIT[ claude ]
🔓

Small, calibrated decision models on your own machine: systemone-compatible local server, 6 agent skills, Claude Code guard, MCP tools. Weights on Hugging Face.

// skillslawrence3699/⟨Python⟩★ 135◷ Apache-2.0[ claude ]
🔓

Claude Code skill: hand bulk judgment calls to Jev. 86% fewer Claude tokens on a 12-task benchmark, up to 20x faster. One-line npx install.

// devtoolsUditAkhourii/⟨JavaScript⟩★ 142◷ MIT[ claude ]
🔓

A calibrated context sieve for Claude Code: every tool result is judged by a System One model before it enters context.

// pluginsGhalebDweikat/⟨Python⟩★ 115◷ MIT[ claude ]
🔓

Jev based decision tools for claude code

// pluginsOqura-ai/⟨Python⟩★ 77[ claude ]
🔓

Jev, TypeSafe's System One classifier, as a tool inside Claude Code, Codex, Pi, and OpenCode: typed classify, check, score, rank, and ask, plus one-command s…

// mcp-serversFrancoisChastel/⟨TypeScript⟩★ 61◷ MIT[ claude ]
🔓

Claude Code plugin that auto-picks the right model for each turn — micro, low, medium, or high tier — using Jev/Clef routing.

// pluginsalexei-led/⟨JavaScript⟩★ 39◷ MIT[ claude ]
🔓

Claude Code plugin: Jev for rule checks, verbatim compaction, and prompt routing

// plugins0x7067/⟨Python⟩★ 27◷ MIT[ claude ]
🔓

A Claude Code mod that uses TypeSafe's Jev to decide auto mode tool calls. 2x faster than the built-in classifier on the calls it decides.

// pluginsmadisonrickert/⟨TypeScript⟩★ 36◷ MIT[ claude ]
🔓

Context-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into https://gith…

// devtoolscompozy/⟨TypeScript⟩★ 32◷ MIT[ claude ]
🔓

Pass-through model router for Claude Code and Codex CLI that picks a model tier per human turn with Jev, TypeSafe AI's decision model

// mcp-serversdirien/⟨JavaScript⟩★ 20◷ Apache-2.0[ claude ]
🔓

An open-source, model-agnostic decision router for Claude Code and Codex.

// devtoolsruban-24/⟨TypeScript⟩★ 18◷ Apache-2.0[ claude ]
🔓

Reference implementation for Jev builders: a Claude Code hook that asks TypeSafe's Jev which skill fits each prompt and logs the answer. Run for a week, 28 o…

// pluginsshimo4228/⟨Python⟩★ 22◷ MIT[ claude ]
🔓

Evidence over eloquence. Unofficial Claude Code plugin that checks "done" claims and small judgement calls with TypeSafe Jev, and keeps receipts.

// pluginsismaildasci/⟨TypeScript⟩★ 11◷ MIT[ claude ]