Trending repositories: token-optimization

9 of 9 repositories

• JuliusBrussee/caveman

  🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

  AI summary: A prompt engineering tool that cuts AI coding agent output tokens by 65% by forcing them to speak like a caveman.

  96,657developer-toolsJavaScriptMITaianthropiccavemanclaude

• rtk-ai/rtk

  CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

  AI summary: A CLI proxy that drastically reduces LLM token consumption on common development commands.

  75,164developer-toolsRustApache-2.0agentic-codingai-codinganthropicclaude-code

• headroomlabs-ai/headroom

  Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

  AI summary: An open-source platform for conducting and analyzing AI-driven user research interviews.

  65,316productivityPythonApache-2.0agentaianthropicclaude-code

• headroomlabs-ai/headroom

  Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

  AI summary: The context compression layer for AI agents, reducing tokens for tool outputs, logs, and RAG chunks.

  62,966ai-mlPythonApache-2.0agentaianthropicclaude-code

• teamchong/pxpipe

  cut Claude Code token usage by rendering text context as images

  AI summary: A local proxy for Claude Code that reduces token costs by rendering bulky context into dense, compact images.

  6,966developer-toolsTypeScriptMITclaude-codeproxytoken-optimizationcost-saving

• drona23/claude-token-efficient

  One CLAUDE.md file. Keeps Claude responses terse. Reduces output verbosity on heavy workflows. Drop-in, no code changes.

  AI summary: A drop-in configuration file that forces Claude to generate terse, token-efficient responses.

  5,926developer-toolsPythonMITclaudeprompt-engineeringtoken-optimizationcost-reduction

• MinishLab/semble

  Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read

  AI summary: A fast, embedding-based code search tool designed specifically to save tokens for AI agents.

  5,834developer-toolsPythonMITagentscode-searchembeddingsmcp

• forloopcodes/contextplus

  Semantic Intelligence for Large-Scale Engineering. Context+ is an MCP server designed for developers who demand 99% accuracy. By combining RAG, Tree-sitter AST, Spectral Clustering, and Obsidian-style linking, Context+ turns a massive codebase into a searchable, hierarchical feature graph.

  AI summary: Advanced context management tool for LLMs, optimizing token usage and relevance.

  1,968developer-toolsTypeScriptMITmcp-serverllm-toolscontext-managementtoken-optimization

• forloopcodes/contextplus

  Semantic Intelligence for Large-Scale Engineering. Context+ is an MCP server designed for developers who demand 99% accuracy. By combining RAG, Tree-sitter AST, Spectral Clustering, and Obsidian-style linking, Context+ turns a massive codebase into a searchable, hierarchical feature graph.

  AI summary: Advanced context management tool for LLMs, optimizing token usage and relevance.

  1,963developer-toolsTypeScriptMITmcp-serverllm-toolscontext-managementtoken-optimization