AI Dev Impact Lab JA
← Rankings · AI-RELATED REPO

LeonardoCalancea/atrain-claude

Dynamic Claude model + effort routing plugin for Claude Code. 5 tiered subagents, hook-based classification, 16/16 tests.

Python MIT GitHub ↗
★ 1
stars
75
AI relevance
50
solo dev
1
tool sigs

SUMMARY AI summary by gpt-5-mini

ATrain is a Claude Code plugin that reduces model costs by routing each tool call to the cheapest Claude model capable of the task (Haiku for reads, Sonnet for edits, Opus for sensitive/architectural work). Intended for developers using Claude Code—especially API-billed users or teams with Opus-heavy sessions—to cut token costs without changing workflow. Key features: - Per-call router/classifier that enforces Opus for sensitive items - Caveman “terse” compression for natural-language outputs - Local caching and FTS5 indexing (SQLite) across sessions - Bash/test output rewriting to reduce context size - Six simple commands to enable/disable stacks, check status, or autopsy past sessions - Pure stdlib Python, no API key, quick install Reported savings: typical 64–82% (avg ~73%) in real sessions; classifier accuracy reported 108/108. Licensed MIT.

AI Coding Tools Used

This repository contains config files from these AI coding tools, indicating AI-assisted development.

Claude Code .claude/

DETECTED Detected AI stack

AI-related keywords found in this repo's description, topics, or README summary — grouped by category. Each badge links to the corresponding ranking detail page.

🤖 LLM models (1)
Claude
💾 Databases (1)
SQLite

Language breakdown (by bytes)

Shell
2.2%
Python
97.8%

Owner

Account
LeonardoCalancea
Type
User
Followers
0

Dates

Created on GitHub 2026-05-07
Last push 2026-05-10
First seen here 2026-05-09
Last fetched 2026-05-10 16:11

Similar repos (same language)

bgzhang1/sw2api

Reverse proxy for your ai quota from the SW platform.

Python 19 AI 45
dea6cat/2b-agent

This llm Agent was created based on necessity for one that could simply use local models without making them hallucinate and keep them focus

Python 1 AI 75
Zuboy/Carbon-Cost-Optimizer-Agentic-AI

An AI agent that decides where and when to run ML training jobs to minimize cost and carbon emissions, then launches them autonomously — exposed entirely through MCP tools.

Python 1 AI 75
FuchaZ/lm-studio-vision-bridge

给纯文本 AI agent 装上眼睛——通过 LM Studio 本地视觉模型提供 MCP 图片识别服务

Python 1 AI 45
Shrutirowlo/AI-Video-Agent

AI-powered video generation agent that automates script analysis, scene planning, and video creation.

Python 1 AI 75
Shivang0/social-vision

Paste an Instagram/TikTok/YouTube/X link and Claude watches it for you — transcribes audio, reads on-screen text & visuals, explains what it's about. Local, cross-platform Claude Code plugin.

Python 1 AI 70
markusbegerow/claude-fuer-oeffentliche-verwaltung

⚠️ Experimentelle Skill-Sammlung für Digitalisierung, Fachverfahren und Organisation der deutschen öffentlichen Verwaltung (OZG, FIM, FIT-Connect, KI-Einsatz, eIDAS, BSI-IT-Grundschutz, DSGVO) – bitte testen, Issues/PRs willkommen! Keine Rechts-/Datenschutzberatung, keine verbindliche Behördenentscheidung. Keine Bürger-/Mitarbeiterdaten im Repo.

Python 1 AI 75
knowledgegut/course-distiller

把有權使用的工作坊/課程回放消化成套品牌色的步驟式學習 PDF;最後的重組交還人腦。A Claude Code skill by 知識包小腸.

Python 1 AI 45