token-optimization

rtk-ai/rtk

+735

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

headroom

+771

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

cdaf

+100

CDAF (Cached Descriptive Asset Files) - open sidecar format for video so AI agents stop re-analyzing the same footage. Spec, CLI, agent skill, reproducible benchmark.

token-optimizer

+44

Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.

jcodemunch-mcp

+31

Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.

Chisle

+23

Cut your AI coding agent's token bill on three axes: terse prose, YAGNI-first code, and tool-output compression. Claude Code, Pi, Cursor, Codex, Gemini + 4 more. Zero deps, published benchmarks including the runs it loses.

context-attachment-manager

+13

Codex and Claude Code plugin (works in Claude Desktop): choose which past images go to the model with your next message. Unchecked images become placeholders, the conversation goes on, and requests stay small.

honey-for-devs

+15

Honey (I Shrunk the AI) by GreenPT: a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs — write less code, less prose, and denser agent-to-agent handoffs (−53%, lossless in benchmarks) with no loss of quality. Works with Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, Windsurf, Cline & Kiro.

lean-ctx

+8

LeanCTX — Context Gateway for AI Systems. Control what your AI can see. Open-source Engine for context selection, supported controls, and evidence.