工具说明为英文。
令牌效率
降低令牌成本并压缩上下文的工具。
用途
活跃度
排序方式
96
工具排名
按实测增长排序,并在不同来源间归一化。 原始值保留各自的数据窗口;计算变化需要 7 天内至少两次测量。
- 1活跃
llmtrim
MCPMCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.
mcp实测增长打开来源 ↗
安装
claude mcp add llmtrim -- npx @llmtrim/cli222GitHub 星标稳定 - 2未知最近提交:暂无数据
AI agent token-cost telemetry + 429 prediction. Per-agent attribution, anomaly + routing + quota.
mcp实测增长打开来源 ↗
安装
claude mcp add openclaw-cost-tracker-mcp -- uvx openclaw-cost-tracker-mcp1297 天下载量稳定 - 3活跃
Reduces AI agent token usage by 90% via context compression and task checkpoint persistence.
mcp实测增长打开来源 ↗
安装
claude mcp add smart-context-mcp -- npx smart-context-mcp4GitHub 星标稳定 - 4休眠
Save tokens while coding — your AI agent gets structured code context, not file dumps.
mcp实测增长打开来源 ↗
安装
claude mcp add codeweave -- npx @codeweave/mcp4GitHub 星标稳定 - 5休眠
Analyze your MCP setup: token costs, grades, duplicates, and optimization tips
mcp实测增长打开来源 ↗
安装
claude mcp add mcp-checkup -- npx mcp-checkup1GitHub 星标稳定 - 6活跃
Cut AI agent token costs 5-15x — routes only relevant code symbols instead of full files.
mcp实测增长打开来源 ↗
安装
claude mcp add agent-booster -- uvx agent-booster1GitHub 星标稳定 - 7活跃
Cut vision-LLM token costs by snapping images to tile boundaries — Claude, GPT, Gemini, Llama, Qwen
mcp实测增长打开来源 ↗
安装
claude mcp add vision-squeezer -- npx vision-squeezer2GitHub 星标稳定 - 8活跃
Token cost math for LLM API calls: verified per-1M-token rates for 69 models, 17 providers.
mcp实测增长打开来源 ↗
安装
claude mcp add comparedge-llm-cost -- npx @comparedge/llm-cost-mcp2GitHub 星标稳定 - 9活跃
Review and compact prompts, docs, and AI-agent skills to save tokens, preserving structure.
mcp实测增长打开来源 ↗
安装
claude mcp add compactprompt -- uvx compactprompt0GitHub 星标稳定 - 10活跃
MCP server that cuts AI coding agent token usage via framework-aware context optimization
mcp实测增长打开来源 ↗
安装
claude mcp add ai-optimizer -- npx @ai-optimizer/core0GitHub 星标稳定 - 11活跃
Reversible context compression for AI agents: cut token usage up to 94%, originals retrievable
mcp实测增长打开来源 ↗
安装
claude mcp add token_optimizer -- uvx slimctx1GitHub 星标稳定 - 12活跃
rtk
CLICLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
github实测增长打开来源 ↗
78 476GitHub 星标+725 (+0.93 %) - 13活跃
headroom
MCPCompress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
github实测增长打开来源 ↗
68 835GitHub 星标+901 (+1.3 %) - 14休眠
nekte
其他Agent-to-Agent coordination that doesn't waste your context window. Token-efficient protocol with progressive discovery, zero-schema invocation, gRPC transport, and task lifecycle management.
github实测增长打开来源 ↗
1GitHub 星标稳定 - 15活跃
voly
智能体Control plane for AI coding agents: route tasks, reduce token spend, run multi-agent workflows, fallback executors, and track cost per task.
github实测增长打开来源 ↗
16GitHub 星标稳定 - 16活跃
Statically audits MCP tool surfaces for token cost, schema quality, and design issues.
mcp实测增长打开来源 ↗
需在 MCP 配置中声明的远程服务器
https://mcplint-web.vercel.app/api/mcp0GitHub 星标稳定 - 17活跃
Lossless context compression plugin for Claude Code & OpenCode.
github实测增长打开来源 ↗
安装
/plugin marketplace add aerovato/magic-compact147GitHub 星标+4 (+2.8 %) - 18活跃
Measure and shrink the token cost of Claude Code skills, tier by tier: the always-on system-prompt tax, the per-invocation body, and on-demand references, each priced at the rate it is actually billed.
github实测增长打开来源 ↗
1GitHub 星标稳定 - 19休眠
SpiderBrain v3 is a multi-platform skill/framework to reduce token usage and AI hallucinations across Claude, Cursor, and other AI tools.
github实测增长打开来源 ↗
安装
git clone https://github.com/abhishek-performdigital/Spiderbrain-V3 ~/.claude/skills/Spiderbrain-V365GitHub 星标稳定 - 20活跃
Freeze Claude Code's prompt prefix so DeepSeek's automatic cache always hits — alignment proxy + coalescing + keepalive, installable as a CC plugin. Measured 64% cheaper on real Claude Code traffic.
github实测增长打开来源 ↗
安装
/plugin marketplace add jianzhichun/permafrost21GitHub 星标稳定 - 21活跃
Usage-aware status line for Claude Code: session & weekly rate-limit gauges with reset countdowns and a precise context-window meter, plus tokens, git & weather. Template-driven and extensible — set it up by chatting with Claude or via a…
github实测增长打开来源 ↗
1GitHub 星标稳定 - 22活跃
toonify-mcp
MCPContext compression plugin for Claude Code. Automatically trims large tool output—JSON, YAML, stack traces, and logs—before it enters the context window.
github实测增长打开来源 ↗
65GitHub 星标+1 (+1.6 %) - 23活跃
somtum
技能Local-first memory and prompt-cache layer for Claude Code
github实测增长打开来源 ↗
安装
/plugin marketplace add riz007/somtum7GitHub 星标稳定 - 24休眠
bonsai
技能Drop-in Cursor rules to cut AI response tokens (no filler/hedging, preserve code + technical strings). Includes local, reproducible benchmarks.
github实测增长打开来源 ↗
安装
git clone https://github.com/marcomondelli/bonsai ~/.claude/skills/bonsai0GitHub 星标稳定
无公开指标的条目
混合排名:实测增长优先。 原始值保留各自的数据窗口;计算变化需要 7 天内至少两次测量。
- 1未知最近提交:暂无数据
Semantic context compression and cognitive memory layer for LLM swarms.
mcp指标未公开打开来源 ↗
需在 MCP 配置中声明的远程服务器
https://recallmax-mcp.vercel.app/api/mcp—无公开指标