Translate, simplify, review, and rewrite text like a caveman. Save 75% on AI tokens with the viral caveman ecosystem.
MCP proxy that compresses prose fields (tool descriptions, etc.) using caveman rules. Same accuracy, fewer context tokens.
Caveman Code — a terminal coding agent
Why use many token when few do trick. Caveman mode for pi — cuts ~75% output tokens while keeping full technical accuracy.
Cross-agent persistent memory with compressed storage. Plug-and-play memory for Claude Code, Gemini CLI, OpenCode, Codex, and Cursor.
Token compression plugin for OpenCode AI — multi-layer filtering, semantic compression, and dynamic context pruning.
Session intelligence for Claude Code — active token management via skills and hooks
Caveman communication mode plugin for opencode
Native Pi caveman communication mode with session persistence, slash command control, status badge, and settings-manager integration.
Various graph generators for graphology.
General-purpose agent with transport abstraction, state management, and attachment support
Unified LLM API with automatic model discovery and provider configuration
OpenCode plugin — injects caveman compression rules every turn, survives /compact, supports live mode switching
Safe multi-account auto-rotate for Codex CLI with isolated CODEX_HOME profiles
A fast JS templating engine.
Compact, language-agnostic codebase mapper for LLM token efficiency.
Course video player (Plyr) + floating mini-window host for Vue 3
A caveman needs their tools. Token-compression MCP server for any agent.
Token-light per-story workflow for Claude Code. Delegates to BMad + ECC.
Terminal User Interface library with differential rendering for efficient text-based applications
Module federation runtime package collection. You can just install it instead of installing all the packages separately.
Run commands concurrently
Slack bot that delegates messages to the caveman-code coding agent
Caveman token-compression plugin for OpenCode