#token-efficiency

GitHub repositories that have self-applied the topic "token-efficiency" — a creator-tagged metadata that surfaces how AI projects describe themselves.

tagged repos

top 8 stars

with tool sigs

shown

REPOS Repos for #token-efficiency (top 8 by stars)

realgarit/fable-baton

Claude Code plugin: Fable 5 as a token-frugal orchestrator with tiered Opus/Sonnet/Haiku agents

HTML ★ 26 AI 70 2 sig

CorvinLabs/CorvinOS

Self-hosted agentic OS — a Vibe-Engineering platform for Builders. Connect Claude Code, Codex or Hermes Agent to Discord, Telegram, WhatsApp, Slack & Email. EU AI Act 2026 & GDPR compliance by architecture.

Python ★ 13 AI 70 1 sig live ↗

Jimmynycu/token-efficiency

A Claude Code plugin that shows exactly where your AI coding session wasted tokens — and how to fix it. Flags waste, never quality. Runs locally.

Python ★ 3 AI 70 Solo live ↗

lesterppo/hermes-token-efficiency

Cut LLM token consumption 65-80% in Hermes Agent — RTK (tool-output) + Caveman (agent-output) compression plugins, one-command install.

Python ★ 2 AI 70 1 sig

Allan-Nava/qrspi

Questions → Research → Spec → Plan → Implement: a phase-gated Claude Code plugin that keeps a coding agent under 40% context by writing one artifact to disk per phase.

JavaScript ★ 1 AI 70 Solo 2 sig live ↗

207studio/jev-claude-tools

Experimental opt-in Jev skills and config for Claude Code — the companion to jev-codex-tools.

Shell ★ 0 AI 100

hraness/system-one-skills

System One Skills gives Devin, Claude Code, and Codex one skill that runs a noisy check once, returns a short result, and saves the full log locally.

Python ★ 0 AI 70 2 sig live ↗

QiDouZu/retcon-form

让 AI 的结论可回查、可推翻：每条判断写成「进行时」+原文指针，按段取原文不整包读（省 token、省上下文）。零依赖，17 场景沙盘可跑。

Python ★ 0 AI 70