$ loading_
Use a local LLM to index codebases and compress Claude Code context.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "cctx" yet — see the docs or source repo.
Use cctx to build a local index for the current repository, and return compressed key context for my follow-up questions to reduce token usage while preserving core implementation details.
A local index is created, and later code Q&A uses concise yet accurate context summaries.
Use cctx to compress this build log and test output, keeping only errors, warnings, relevant file paths, and suggested fix directions so I can continue debugging.
A condensed log summary highlighting key errors, impact scope, and suggested next debugging steps.
Use cctx to summarize our past turns about refactoring the authentication module, keeping completed work, unresolved issues, related files, and next steps for a new session.
A structured handoff summary for a new session, reducing repeated explanations and context cost.
Understand your codebase in terminal and accelerate coding with natural language.
Delegate code investigation, edits, and verification to Claude Code with background job management.
Track Claude Code token usage, costs, and plan limits for better control.
Compress Claude Code and OpenCode context losslessly for longer, more efficient coding tasks.
Coordinate Codex and local Claude Code for engineering, review, and automation workflows.
Read, search, and update codebase documentation context through MCP.