token-saver 话题在 GitHub 上没有填写简介，这里按 Star 数汇总最相关的热门仓库。
永不停歇地编程。免费 MIT AI 网关：一个端点，375 家提供商（150+ 家免费），1,400+ 个模型：Kimi、Claude、GPT、Gemini、GLM、DeepSeek、MiniMax。兼容 Claude Code、Codex、Cursor、OpenCode、Cline 和 Copilot。配额感知自动回退，RTK+Caveman 压缩可节省 15-95% token，支持 MCP/A2A、桌面端/PWA。由 900+ 贡献者构建
无限免费 AI 编程。通过 40+ 提供商将 Claude Code、Codex、Cursor、Cline、Copilot、Antigravity 连接到免费的 Claude/GPT/Gemini。自动回退，RTK -40% tokens，永不触及限制。
Unified AI Gateway for 30+ LLMs (OpenAI, Anthropic, Bedrock, Azure etc) with Caching, Guardrails, A/B test & cost controls. Go-native Fastest & Scalable AI Gateway LiteLLM & Kong AI Gateway alternative.
通过将复杂的LLM上下文转换为简洁的PNG文件格式，可以将您的 Claude 使用成本降低59–70%。实现100%的读取准确率，能够精确计算各提供商的计费情况（包括Anthropic、OpenAI和Gemini等平台）。系统具备故障关闭机制，并拥有经过验证的测试基准。支持命令行界面、代理服务器以及Cloudflare Workers技术。文档支持42种语言。该解决方案属于OmniRoute系列产品的一部分。
10Router — local AI routing gateway & dashboard · npm i -g @techysy/10router
Enchant Version of 9Router. 304+ Providers (API-key, OAuth, free-tier, and 39 web-cookie providers), 6 combo strategies (fallback, round-robin, fusion, swarm, cascade, smart-routing) in One Hand
Local CLI and MCP server for compacting test and build output, with retrieval from a redacted local cache.
Shorter replies with Claude Code. Save output token spend.
JavaScript/TypeScript implementation of LLMLingua-2 (Experimental)
智能AI代理路由器，连接Claude代码、光标、Codex、Copilot和50+编码工具与拥有100+模型的40+人工智能服务提供商。通过RTK压缩、订阅自动回退到廉价到免费服务商、多账户轮询以及本地仪表盘，节省20-40%的代币。
Save 87% token usage for Claude Code. Zero install. 8 rules covering input+output+context. 6 months verified.
DeepSeek Harness bash executor plugin that routes eligible commands through rtk (Rust Token Killer) to compress tool output and save tokens.
Self-hosted AI gateway — one endpoint, many providers, auto-fallback. OpenAI-compatible REST API with Cloudflare Workers AI automation.
9Router fnOS app — FREE AI Router & Token Saver packaged for 飞牛 NAS
Project-agnostic dual-memory MCP CLI for Claude Code, Cursor, and OpenCode (Qdrant tuned hybrid retrieval + structural memory hooks)
🤿 The cheapest multi-agent workforce that is actually user-friendly: 7.7x more productive and 50x cheaper compared to your ultracode mode, an intelligent multi-agent swarm of Claude Code agents on DeepSeek or other providers, integrated with your own Claude Code or Codex.
AI-powered coding agent for code generation, debugging, review, and deployment automation.
⚡ Ultra-fast LLM router & proxy in Rust. Multi-account quota pooling (Gemini, Codex, Claude), Token Saver engine, sub-millisecond latency & embedded Web UI.
Comet helps you save 15,000+ tokens! Comet is a TUI application that automatically generates descriptive git commit messages using local language models via Ollama or LMStudio or Openrouter. It analyzes your staged git diffs and provides a clean interface to review, edit, regenerate, and commit your changes instantly.
Spend 20–50% fewer tokens and get responses ~1.5× faster in Claude Code: automatic reasoning effort for every turn — xhigh for plans, medium for building, low for questions and trivial tasks like git commits.