MCP servers and skills: search, filter by where they run, and compare.
A Model Context Protocol (MCP) server for enhanced shell command execution — RTK token minimization, persistent caching, execution logging, and safe file writes for AI coding agents
Node.jsMIT★ 2Few starsNo key
RTK(Rust Token Killer) setup skill for OpenClaw - enforces token-saving commands via AGENTS.md
SkillLink only★ 5
Token-optimizing MCP proxy - sits between Claude and any MCP server, compressing tool responses by 60-90% through an 8-stage filter pipeline.
SkillMIT★ 4Few starsNo key
Token Saver: RTK Protocol — CLI proxy that filters bash output to save 55-90% LLM tokens. Platform-agnostic: works with any AI coding tool (OpenCode, Claude Code, Codex, Cursor, Gemini CLI).
SkillApache-2.0★ 3Few starsNo key
One memory, every coding agent — shared brain + usage dashboard for Claude Code, Codex, Gemini (subscription plans, no API keys)
SkillMIT★ 3Few starsNo key
SkillApache-2.0★ 4Few starsNo key
Cut token cost in 4 layers, without cutting model intelligence: handoff, rtk, headroom, caveman — token-saving skills for DeepSeek Harness.
SkillMIT★ 2Few starsNo key
One-command setup that makes Claude Code use fewer tokens: rtk shell compression, stash search index, web-search, codebase-memory, fast-jev-compaction, ponytail, plus Jev skill suggestions and model r
SkillMIT★ 1Few starsNo key
Token-saving starter pack for Claude Code, Codex and other coding agents — paste one line, the agent installs the lot.
SkillMITFew starsNo key
Use Claude Code with fewer tokens: installer, agents, usage dashboard, local history memory. Not affiliated with Anthropic.
SkillApache-2.0★ 1Few starsNo key
Never stop coding. Free AI gateway: one endpoint, 160+ providers, RTK+Caveman stacked compression up to ~95% eligible context savings, smart auto-fallback, MCP/A2A, multimodal APIs, Desktop/PWA.
Node.jsMIT★ 3Few starsNo key
Cross-host operational companion for Compound Engineering across AI coding agents. Fleet version governance, project adoption, agent guardrails, and advisory workflow observation.
SkillMIT★ 6No key
concierge is a set of skills for claude-code that allows a very opinionated usage of gastown (and some other tools) to speed even further creation/maintenance of projects.
SkillMIT★ 3Few starsNo key
Token optimization layer for Claude Code: installs and wires RTK, tilth, Serena, and ICM so your AI agent reads what it needs, not everything.
SkillMIT★ 1Few starsNo key
Opencode plugin for Entire CLI for Git Hook AI Session capture
SkillMIT★ 1Few starsNo key
Token-efficiency skill for coding agents: RTK shell filtering + caveman-ultra output compression + entire-graph search-first navigation. Claude Code plugin or plain skill.
SkillMIT★ 4Few starsNo key
SkillApache-2.0★ 3Few starsNo key
Extensions etc. to customize agents like opencode, pi-mono, etc.
SkillMIT★ 3Few starsNo key
Jump-start and measure token-efficient AI coding workflows for GitHub Copilot and Claude Code.
SkillMIT★ 6No key
SkillGPL-3.0Few starsNo key
AI Router & Token Saver — One endpoint for all your AI providers
SkillMIT★ 7No key
Token-efficiency proxy for Codex/OpenAI Responses API: recoverable storage, MCP server, opt-in visual compaction, effort routing
Node.jsApache-2.0★ 3Few starsNo key
Who stands behind it
