lowfat - slim your command output. strips noise, saves tokens.
A safe bridge for Codex and ChatGPT to hand off coding work, save tokens, and keep local execution under control.
Architecture intelligence for AI coding agents - deterministic, cross-repository code analysis through MCP.
OpenCode package for Caveman: terse AI responses, slash commands, compact reviews, commit messages, and markdown memory compression.
Claude省钱版 — 效果基本一致的情况下可以节约Token消耗约90%，超级省Token，支持OpenAI及国产大模型(DeepSeek/GLM/通义千问)的AI编程助手。本项目基于ClaudeCode源码实现。
Guardian Agent and Token Savings for Claude Code
ContextCore: An MCP server for Claude (or any AI tool) that enables massive token saving through hybrid search (BM25 + Embeddings)
Turn any OpenAPI spec into a native CLI binary. No MCP, no bloat, no runtime dependencies, ONLY CLI.
🦴 paleo — token-saving skills for LLM agents: compress output, trim context, cap budget (Claude Code / Codex / Gemini / Hermes)
Local-first Trello cache with Git-style sync — built and optimised for AI agent workflows.
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.
Project-agnostic dual-memory MCP CLI for Claude Code, Cursor, and OpenCode (Qdrant tuned hybrid retrieval + structural memory hooks)
P2P token recycling network for AI Agents. Put unused tokens into a piggy bank, then cashing them out as help when you need it. 💸
Claude Code 委派 plugin:把任务派给换脑的子 agent(也可 --codex 委派给本机 codex),既省主 Claude 的 token,也借不同模型/harness 的视角。
Opencode lazy load plugin Saves 85%+ on tools and MCP servers tokens per request. The LLM loads tool instructions on-demand instead of receiving thousands of tokens of schemas it never uses.
TDD-first AI dev pipeline for Claude Code, Cursor, Codex, Gemini CLI & Antigravity. /dev /fix /quick + token-saving hooks. npx aicrew install
这个skill专门为Claude code+DeepSeekv4，做的一个清理工具。当出现缓存命中低，token消耗突然增加时，可以直接使用，并告知哪里能够优化。
🎭 Talk to Claude in 100% emoji. A stylized communication mode for Claude Code.
Auto model-switching plugin for Claude Code — routes prompts to haiku/sonnet/opus (or any custom tier) to save API tokens
High-Trust Open-Core framework for Windows AI Agents. Crushes latency to 3.9ms, enables background UIA invocation, and protects enterprise RPA workflows.
Add a description, image, and links to the token-saving topic page so that developers can more easily learn about it.
To associate your repository with the token-saving topic, visit your repo's landing page and select "manage topics."