Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
rtk
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
58.8kstars
3.6kforks
Rust
agentic-codingai-codinganthropicclaude-codeclicommand-line-toolcost-reductiondeveloper-toolsllmopen-sourceproductivityrust
Quality signals
ActiveNo testsNo CIThin docsNo licensePopular
AI summary
Auto-generated overview of what this skill does and when to reach for it.
CLI tool that cuts LLM token usage by 60-90% for common developer commands via a local proxy.
Use this when
- Running git diff or grep with large files
- Executing npm install or pip install repeatedly
- Using grep/ack/sed on multi-MB logs
- Debugging with verbose compiler output
- Automating code review with large diffs
Don't use when
- Need real-time, non-cached LLM responses
- Working with proprietary or sensitive code
- Commands requiring exact, unmodified LLM output
Capabilities
- Caches LLM responses for identical prompts
- Strips verbose logs before sending to LLM
- Supports git diff, grep, npm, pip, and common dev tools
- Local Rust binary with no external dependencies
- Reduces token count by 60-90% on typical dev commands
- Works offline after initial cache population
InstallSKILLInstall as a Claude Code skill
Universal installANY TOOL
$ npx skillcity@latest rtk-ai/rtkAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor, Cline, OpenCode, Gemini CLI, Anti-Gravity, OpenClaw and Hermes.
Requires Node.js 18+ (ships with npx).
Or install manually
# Install into ~/.claude/skills/ mkdir -p ~/.claude/skills/rtk curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/main/SKILL.md -o ~/.claude/skills/rtk/SKILL.md
Loading README…
Ask a simulated agent to run this skill. It loads the real SKILL.md and reasons over your task with NVIDIA.
rtk — sandboxAI sandbox
Pick a quick prompt below or type your own — watch the agent execute this skill step by step.
guest@skillcity:~$Try a prompt