OpenRadar

Tag

#token-optimization

6 open-source projects filed under this tag.

01 JavaScript

caveman

Caveman is a Claude Code skill that cuts 65% of AI output tokens by making agents talk like caveman — same accuracy, fewer words, lower cost. 70K GitHub stars.

#developer-tools#prompt-engineering#ai-agents#token-optimization
69.9k 3.9k Read
02 TypeScript

codesight

CodeSight is a universal AI context generator that cuts token usage by 91x across Claude Code, Cursor, Copilot, and Codex. Supports 14 languages, 30+ frameworks, zero dependencies.

#ai-context#developer-tools#token-optimization#mcp
1.1k 101 Read
03 Python

headroom

Headroom is a context compression layer for AI agents that reduces token usage by 60-95% while preserving answer quality. Library, proxy, MCP server.

#ai#token-optimization#context-engineering#mcp
18.4k 1.2k Read
04 Rust

lowfat

Rust CLI that filters noisy shell command output before it reaches AI coding agents, saving up to 91% of tokens with a plugin-based architecture.

#developer-tools#cli#token-optimization#ai-agents
486 16 Read
05 Python

opensquilla

Token-efficient microkernel AI agent with local model router, persistent memory, layered sandbox, and support for 20+ LLM providers — same budget, higher intelligence density.

#ai-agent#llm#token-optimization#developer-tools
3.8k 299 Read
06 Rust

rtk

RTK is a Rust CLI proxy that sits between your AI coding agent and the shell, compressing command output by 60-90% to slash LLM token costs.

#developer-tools#ai-coding#token-optimization#rust
63.2k 3.9k Read