A fast JS templating engine.
MCP proxy that compresses prose fields (tool descriptions, etc.) using caveman rules. Same accuracy, fewer context tokens.
Caveman Code — a terminal coding agent
Caveman communication mode plugin for opencode
Why use many token when few do trick. Caveman mode for pi — cuts ~75% output tokens while keeping full technical accuracy.
OpenCode plugin — injects caveman compression rules every turn, survives /compact, supports live mode switching
Native Pi caveman communication mode with session persistence, slash command control, status badge, and settings-manager integration.
Caveman token-compression plugin for OpenCode
Caveman mode for pi — terse output, ~75% fewer tokens, full technical accuracy
Always-on caveman mode extension for Pi
Unified AI router with 160+ providers, RTK+Caveman compression, auto fallback, MCP/A2A, desktop, PWA, and OpenAI-compatible APIs.
Caveman mode for pi: ultra-compressed responses that save tokens.
Slack bot that delegates messages to the caveman-code coding agent
Pre-compile Caveman templates.
Rendered markdown + LaTeX preview for caveman-code, with terminal, browser, and PDF output
Translate, simplify, review, and rewrite text like a caveman. Save 75% on AI tokens with the viral caveman ecosystem.
TypeScript SDK for the caveman-code daemon HTTP + WebSocket API. Generated from openapi.yaml.
Claude Code skill that makes Claude respond like a caveman while maintaining full technical capability
GSD Hermes + Caveman - Spec-driven development with compressed communication. Inspired by get-shit-done (TÂCHES) and caveman (JuliusBrussee). ~75% token reduction + phase-based planning.
Caveman Mode extension for pi. Makes assistant responses terse and blunt.
Converts Caveman templates to ES6 modules
Caveman mode plugin and commands for OpenCode
A caveman needs their tools. Token-compression MCP server for any agent.
A structured AI development system for Claude Code, Antigravity, and OpenCode. Real subagent delegation, lean save/resume, polish loop, integrated Graphify + MemPalace + Caveman.
Library for OogaBoogaGames Caveman game and asset format.
OpenAI profile pooling and safe auto-rotate for Codex CLI and Claude Code
CLI that orchestrates coding agents (Claude Code and others) through a phased implementation plan, with automatic test/commit loops and a TUI dashboard
Token-Oriented Object Notation encoder. 30-60% fewer LLM tokens than JSON for the same data.
Deterministic text compression for LLM token reduction — Rust-native Caveman Compression with Python bindings
Terminal UI for monitoring AI coding agents (Claude Code, Codex, Aider, Cursor, Gemini, Goose, ...) — like top, but for agents.
Asset and game bundler for OogaBoogaGames, using the Caveman format.
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.
A CLI for interacting with OpenAI compatible APIs
A blazingly fast file and directory renaming tool with gitignore support
Ripgrep-style search plus safe, transactional, AST-aware rewrites with built-in undo. Designed for LLM coding agents.
The most advanced terminal markdown reader
Takes any text and returns it how a caveman would say it.
Crummy is a simple and tasty way to add breadcrumbs to your Rails applications.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.