token-optimizer 开源项目推荐（45 个）

alexgreensh /token-optimizer

找出幽灵 token，修复它们，熬过上下文压缩，避免上下文质量衰减。

claudioemmanuel /squeez

Hook-based token compressor for 7 AI CLI hosts (Claude Code, Copilot CLI, OpenCode, Gemini CLI, Codex CLI, Pi, Hermes). Up to 95% bash compression, signature-mode for code reads, cross-call dedup, MCP server, self-teaching protocol. Zero runtime deps.

mischasigtermans /laravel-toon

TOON encoding for Laravel. Encode data for AI/LLMs with ~50% fewer tokens than JSON.

oanhduong /token-ninja

token-ninja routes deterministic shell commands locally — zero LLM calls, ~19µs latency. Works silently inside AI tools via MCP.

lucasmartins-ai /lcc

Compact coding-agent context without summarizing it away. Verbatim, offline, with a receipt and recall for every cut. CLI, MCP server, Claude Code plugin. MIT.

NailShakurov /logzip

Compress logs for LLM analysis — Rust-powered, Python API. 40-60% token savings.

toprakahmetaydogmus /TZeroAlgorithm

Deterministic AST Context Compressor, Pre-Flight Reality-Lock & 20-Tool MCP Server for Claude, Cursor, Windsurf & Copilot. Up to 95% token reduction, 1-Click Auto-Vault, and local engine.

Zoria-Lind /cc-token-optimizer

Cut your Claude Code token bill: tool-output trimming, read dedup, model-tier discipline, and live cost + cache-hit stats.

samibajwaisking /Token-Optimizer-Skill

该项目在 GitHub 上没有填写描述

lnrd390 /claude-workflow-toolkit

A modular toolkit for Claude Code to optimize context, planning, and agent execution with lower token usage and less repeated codebase discovery.

palpalani /astro-agent-optimized

astro-agent-optimized(AAO) is agent-optimized output for Astro JS tools.

pomagrenate /ice_age

⚡ Universal IDE plugin & proxy that cuts LLM token consumption by up to 70% using deterministic AST pruning & context compression. Written in Go.

boyScavedo /prompt-optimizer

A simple open source vibecoded prompt optimizer for personal use, you are free to use it as needed.

vale-dinap /gearSecond

A skill that makes LLMs think faster and cheaper: up to 77% fewer thinking tokens and answers up to 2x faster, with the same quality. Benchmarked on Claude, Grok, Gemma, Qwen and gpt-oss.

pareshrnayak /token-trim

Trim Python code for LLMs by removing comments, docstrings, and whitespace. Save AI tokens, reduce API costs, and fit more code into ChatGPT, Claude, and Gemini.

ExLuna-rs /claude-autorouter

Auto-route Claude Code prompts to Haiku, Sonnet or Opus. Learns from escalations, saves tokens.

Mishit18 /claude-code-doctor

🩺 Diagnose, lint, and auto-fix your Claude Code setup. 9 zero-dependency ML engines: prompt injection scanner, dependency graph intelligence (PageRank + Tarjan SCC), CLAUDE.md auto-generator, .claudeignore optimizer, session cost predictor. 45+ checks, auto-fix, CI/CD ready. The missing DevTool for Anthropic Claude Code.

totalbrain /TokenOptimizer

Cut up to 75% of tokens for Grok • GPT • Claude • Llama • Gemini 100% offline • Open source • AI-safe token minifier

Sr-Claude /tokerizen

Proxy local para la API de Anthropic que reduce el consumo de tokens entre un 70–90% de forma transparente. Aplica caché de prefijos, compresión de historial, batching automático y ajuste dinámico de tokens sin modificar el código cliente. Compatible con Fable 5, Sonnet, Haiku y Opus.

VrushankPatel /relay

High-performance Reverse Proxy for LLM Caching and Deduplication (OpenAI, Anthropic, Gemini, Copilot). Saves API costs, encrypts cache at rest, and multicasts concurrent streams.