✂️ Token-saving OMP add-ons: terse Caveman replies, compact RTK shell output, lean Ponytail code calls — one-command combo presets.

Token-saving proxy for Claude Code: renders bulky context (system prompt, tool docs, old history) as dense PNGs to cut input tokens. Runs on Node and Cloudflare Workers.

OpenCode plugin for OpenToken — token-saving companion

Extension that exposes `codebase-memory-mcp` as native Pi tools, adds auto-indexing and deliberate obtimizations for agent-workflows and token saving.

Token-saving Cyrillic markdown translation layer for Antigravity (agy): fast Gemini 3.7 Flash translate tier, lazy EN doc cache via PreToolUse hook, AGENTS.md / GEMINI.md sync, MCP and skills

Token-saving Cyrillic markdown translation layer for OpenAI Codex CLI / ChatGPT App using gpt-5.6-luna (Low) via existing subscription auth

Universal token-saving core — pure-logic compression pipeline, no platform dependencies

33-agent AI software agency framework for Claude Code, Cursor, and Gemini CLI. Orchestrates specialized agents for SaaS Engineering, Cybersecurity (Red Team), McKinsey PPT Design, Spatial CAD/GIS, and PhD Research. Features Caveman & Graphify token-saving

Token Saving for the Masses — zero-config token-saving toolkit for AI coding agents

Token-saving multi-agent orchestration for Factory AI Droid CLI. Native Rust compactor, auto-rewrite hooks, 18 expert sub-droids, learning memory.

Token-saving proxy for Claude Code: renders bulky context (system prompt, tool docs, old history) as dense PNGs to cut input tokens. Runs on Node and Cloudflare Workers.

The ultimate AI token-saving MCP middleware — compression, caching, injection shield, multi-server routing, and more.

Agentic Gemini proxy with multi-account OAuth, token saving, and OpenAI-compatible API

One endpoint for your whole MCP fleet. Streamable HTTP gateway with auto-discovery, per-tenant RBAC, OAuth PKCE, rate limits, circuit breakers, audit, and token-saving lean tool schemas. Forwards W3C traceparent across upstreams.

Lightweight Claude Code and Codex CLI hook that suggests token-saving prompt improvements.

Automatic token-saving router for the Pi CLI using Pi's openai-codex provider, with visible local usage and quality evidence.

Trust-first token saving CLI for agent terminal output

MCP server for @vakra-dev/reader (scrape/crawl websites) with token-saving artifact truncation.

BuilderForce Agent Memory — MCP transport. Exposes @seanhogg/builderforce-memory to any MCP client (Claude Agent SDK in-process, stdio, or HTTP) over a pluggable MemoryBackend, with token-saving fetch-on-demand recall.

Universal token-saving pipe tool for AI coding agents