code-context-engine: Code Context Engine (CCE) indexes your codebase using tree-sitter parsing and vector embeddings, allowing AI coding agents to search for relevant code instead of re-reading entire files. It saves up to 94% input tokens, works across multiple editors (Claude Code, VS Code, Cursor, Gemini CLI, Codex CLI), and runs entirely locally for privacy. With built-in compression, graph expansion, and cross-session memory, CCE reduces costs and speeds up responses.; mcp-language-server: The MCP Language Server exposes language server capabilities like definition, references, and diagnostics to Large Language Models. It helps MCP-enabled clients navigate codebases more easily by providing semantic tools for code understanding and manipulation.
Reduce Claude Code costs by cutting input tokens
Enabling LLMs to navigate and understand complex codebases