CLI output compressor for Claude Code. Reduces token consumption by 50–90% by compressing verbose command output before it enters the context window. Supports 52+ commands — git, docker, kubectl, npm, terraform, and more.

Hook-based token compressor for 5 AI CLI hosts (Claude Code, Copilot CLI, OpenCode, Gemini CLI, Codex CLI). Up to 95% bash compression, signature-mode for code reads, cross-call dedup, MCP server, self-teaching protocol. Zero runtime deps.

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.

Config-driven CLI tool that compresses command output before it reaches an LLM context

Never stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 550+ contributors

Audit and shrink your Claude Code startup context. Measures what every skill, plugin, agent, and memory file costs in the system prompt, then reversibly disables the dead weight. No proxy, no compression.

Save tokens. Maximize context, Safely

vMLX - Use MLX models easily - JANGQ (GGUF for MLX) - Not dependant on mlx_vlm

Your agent pays twice for output it has already seen. OMNI returns a handle instead: 97.2% off a file read twice. Nothing deleted, nothing invented.

MCP tool lists eat 71,929 tokens at 255 tools — more than half a 128K window before you ask anything. mcptoon reads the same tools back at 581 (-99.2%, measured). 128KB CLI, zero deps. Compute your own: activeing123.github.io/mcptoon/tools/token-tax