Caveman - Reduce Token Usage by 65%

Caveman - Reduce Token Usage by 65%

4.0

Caveman optimizes AI prompts to cut token usage by 65%, saving costs. Compatible with Claude Code, Cursor, Windsurf, Cline, and 30+ agents. GitHub 74k+ stars.

Last Updated Nov 10, 2026
Caveman - Reduce Token Usage by 65% screenshot

About

Caveman is an open-source optimization tool stack for AI coding agents, built around one simple philosophy: "Why use many token when few token do trick" — making AI output as concise as a caveman. It started as a Claude Code skill plugin that dramatically cuts token consumption by changing how AI responds (lean, direct, no fluff), and has since evolved into a full-stack solution spanning five layers including a gateway, memory layer, and terminal agent. The project has earned 74k+ stars on GitHub, once hit #1 on Hacker News, and is supported by 30+ mainstream AI coding agents including Claude Code, Codex, Gemini, Cursor, Windsurf, Cline, and Copilot. Core author Julius Brussee has fully open-sourced it under the MIT license, with a managed cloud service available at caveman.so.

Key Features

Caveman Skill Plugin: Compresses AI coding agent responses from verbose explanatory text into blunt, precise "caveman-style" replies, reducing output tokens by roughly 65-75% on average while maintaining full technical accuracy.
Caveman Code (Terminal Agent): An npm-installable terminal AI agent with built-in four-layer compression, support for 20+ model providers, plan-then-execute workflow, and single-turn autonomous loops that cut token usage by about half.
Caveman Gateway (Traffic Compression Gateway): Coming soon — replace a single base URL to compress all LLM traffic with zero changes on the agent side, plus real token-level billing.
Cavemem (Persistent Memory Layer): A recall layer delivered via MCP protocol, built on local SQLite + FTS5 + vector indexing, retrieving only necessary information instead of resending full context.
Cave Architect (Cost Insights): Turns telemetry data into a prioritized optimization roadmap, tagging each change with its dollar-per-day cost impact to help teams make better decisions.
Evaluation-Gated Releases: Every optimization must pass evaluation tests before shipping, and any change that degrades quality is automatically rolled back — so savings never come at the cost of quality.

Pricing & Fees

  • Pricing: Caveman itself is free and open source; Caveman Cloud is free for one person, $300/month for a team (including $300 of monthly usage), and Enterprise is custom-priced annually for VPC deployment.
  • Free tier: The Free Cloud plan includes every Cloud feature for one person — 100,000 events, 600 agent minutes, 25,000 routing decisions and $10 of Caveman AI per month, with no card needed.
  • Trial: The Team plan starts with a 7-day free trial; cancel within the trial and pay nothing.
  • Plan limits: Included Team usage does not roll over; past the allowance, standard rates apply (events from $0.00035), and overage is capped at $50 a month per product unless you raise the limit.
  • Deployment options: The open-source tool runs locally at $0; Team adds semantic cache, project access control and audit logs, while SSO is available on the Scale package at $750 a month.

Who It's For

Heavy AI coding users who rely on tools like Claude Code or Cursor daily and want to cut API costs. Development teams that can set up Caveman Gateway once and let the whole team enjoy automatic token compression without per-developer configuration. AI agent developers building custom agents who want to integrate Caveman's compression and memory capabilities. And token-budget-sensitive teams — startups and indie developers — who need precise control over AI API spending.