headroom: Headroom compresses everything your AI agent reads — tool outputs, logs, RAG chunks, files, and conversation history — before it reaches the LLM. It achieves the same answers with a fraction of the tokens.; codebadger: Codebadger is a containerized Model Context Protocol (MCP) server that performs static code analysis using Joern's Code Property Graph (CPG) technology. It integrates with various LLM clients like GitHub Copilot and Claude to provide advanced program analysis capabilities, especially for vulnerability detection across multiple languages.
Reduce LLM token usage and API costs for AI agents.
Performing advanced static code analysis for multiple programming languages.