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.; context-mode: Every tool call in an MCP (Model-Controller-Program) environment dumps raw data into the context window, quickly consuming space and causing the agent to lose track of ongoing tasks. Context Mode is an MCP server that tackles this by sandboxing tool outputs to significantly reduce context usage, tracking session events in SQLite for continuity, and promoting 'think in code' to minimize data processing within the LLM.
Reduce Claude Code costs by cutting input tokens
Deep repository research and analysis (e.g., architecture, contributors, issues)