← Latest products

Caveman

why use many token when few do trick. 🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman. Keep your coding agent. Add recoverable context compression, measure token usage, and find practical guides for reducing AI agent costs. One command wraps Claude Code, Codex, Hermes, and more with a local proxy that compresses logs, tool output, and files before every provider call.

Open source

117,382 stars · GitHubexternal site

Visit caveman.soexternal site

Reactions (2)

Similar products

by description similarity

  1. OpenSkills

    news.ycombinator.com

    Stop bloating your LLM context with unused instructions

    Hacker News9 pts

  2. TokenMaxxer

    tokenmaxxer.xyz

    track every AI token you spend across your coding tools

    Hacker News7 pts

  3. Tokenmaxx

    github.com

    CLI that merges usage across Claude Code and Codex accounts

    Hacker News5 pts

  4. Graft

    github.com

    Claude Code hooks that cut grep tokens by 42%

    Hacker News39 pts

  5. Local Coding Agent with LLMs to Delegate Tool Calls to Small AI Models

    github.com

    Enables small-to-large self-hosted ai models to use local source code when running tool-calling agentic workloads. We actively data mine 20,900+ (2+ TB) popular github repos using large and small ai models to create reuseable: json, markdown and parquet files for local-first tool-calling models.

    Hacker News9 pts