AI Skill Hub 推荐使用:开源Token助手 是一款优质的AI工具。AI 综合评分 7.5 分,在同类工具中表现稳健。如果你正在寻找可靠的AI工具解决方案,这是一个值得深入了解的选择。
压缩层次达42层,零风险,高效Token保存
开源Token助手 是一款基于 TypeScript 开发的开源工具,专注于 compression、llm、opencode 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
压缩层次达42层,零风险,高效Token保存
开源Token助手 是一款基于 TypeScript 开发的开源工具,专注于 compression、llm、opencode 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
# 方式一:npm 全局安装 npm install -g opentoken # 方式二:npx 直接运行(无需安装) npx opentoken --help # 方式三:项目依赖安装 npm install opentoken # 方式四:从源码运行 git clone https://github.com/MrGray17/opentoken cd opentoken npm install npm start
# 命令行使用
opentoken --help
# 基本用法
opentoken [options] <input>
# Node.js 代码中使用
const opentoken = require('opentoken');
const result = await opentoken.run(options);
console.log(result);
# opentoken 配置说明 # 查看配置选项 opentoken --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export OPENTOKEN_CONFIG="/path/to/config.yml"
<img src="https://raw.githubusercontent.com/MrGray17/opentoken/main/.github/opentoken-banner.svg" alt="OpenToken" width="600" />
```bash
bun x opentoken wrap git diff HEAD~1
bash
npm install @opentoken/core ```
Bun v1.2+ required. Install Bun — one command, 2 seconds.
---
npm install -g opentoken
┌─────────────────┐
│ @opentoken/core │
│ 51 modules │
│ Pure logic │
└───────┬─────────┘
│
┌────────────────────┼────────────────────┐
▼ ▼ ▼
opentoken CLI opentoken-mcp @mrgray17/opentoken
pipe │ wrap │ stats JSON-RPC stdio OpenCode plugin
any terminal Claude Code, auto-loads
any shell Cursor, Aider, transparent
any AI agent any MCP host to user
---
See packages/core/src/index.ts for all exports. TypeScript definitions included — everything is strictly typed.
---
Every tool output passes through 35 compression stages. Each stage ends with a conservative safety check — if output grew, the original is returned untouched.
| Feature | OpenToken | Truncation | Caveman | Raw |
|---|---|---|---|---|
| Preserves semantics | ✅ | ❌ | ❌ | ✅ |
| Conservative safety | ✅ | N/A | N/A | N/A |
| Secrets redaction | ✅ | ❌ | ❌ | ❌ |
| Family-specific filters | 10 families | ❌ | ❌ | ❌ |
| Lossless compression | LZ77 + LZW | ❌ | ❌ | ❌ |
| Cross-call dedup | ✅ | ❌ | ❌ | ❌ |
| CLI pipe mode | ✅ | ✅ | ❌ | ✅ |
| MCP protocol | ✅ | ❌ | ❌ | ❌ |
| Model speaks normally | ✅ | ✅ | ❌ | ✅ |
| Token savings | 70–80% | 10–50% | 50–80% | 0% |
---
<details> <summary><strong>Does OpenToken change what the model sees?</strong></summary>
Semantically, no. Compressed output preserves all actionable information — file paths, error messages, line numbers, function signatures, class names, test results. The model answers identically whether it sees the raw output or the compressed version.
The conservative safety filter at every stage guarantees: if compression produces a larger or corrupted output, the original is returned instead. </details>
<details> <summary><strong>Does it work with any AI coding agent?</strong></summary>
Yes. Three interfaces: - CLI — opentoken wrap <cmd> works in any terminal with any agent - MCP — opentoken-mcp works with Claude Code, Cursor, Windsurf, any MCP host - Library — @opentoken/core can be integrated into any Node.js/Bun tool </details>
<details> <summary><strong>Is it safe to compress secrets / API keys?</strong></summary>
Yes. Secrets redaction runs first, before any other stage. 35+ patterns cover: AWS keys, GitHub tokens, OpenAI/Anthropic keys, JWT tokens, Stripe keys, connection strings, private keys, and more. </details>
<details> <summary><strong>What's the performance overhead?</strong></summary>
Negligible. Typical pipeline latency is 1–5 ms per tool call. The LZW compressor has an O(n) pre-check that skips expensive scanning on non-compressible input (6,000× faster on random data). Token estimation uses simple heuristics, not full tokenizers. </details>
<details> <summary><strong>Why Bun and not Node.js?</strong></summary>
The core library uses Bun-native APIs for filesystem I/O (Bun.file(), Bun.write(), Bun.spawn()). Bun is the fastest JavaScript runtime and has 80%+ market share in AI tooling (OpenCode, Claude Code MCP servers, etc.). The CLI and MCP server are pure Node.js compatible. </details>
---
高效的Token保存和压缩工具
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
总体来看,开源Token助手 是一款质量良好的AI工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | opentoken |
| 原始描述 | 开源AI工具:Token-saving companion for OpenCode — 42 compression layers, zero risk, no cavem。⭐80 · TypeScript |
| Topics | compressionllmopencodetoken-savings |
| GitHub | https://github.com/MrGray17/opentoken |
| License | MIT |
| 语言 | TypeScript |
收录时间:2026-05-27 · 更新时间:2026-05-27 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。