$ loading_
Provide coding agents with local-first indexing, extraction, and durable chat memory.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "contxt-box" yet — see the docs or source repo.
Use contxt-box to scan my local code repository, build a file metadata index, and list key modules, entry files, and the most frequently modified files by directory.
A structured project index summary that helps AI quickly understand the codebase structure and key files.
Use contxt-box to extract content from PDFs, Word files, and images in the docs folder, organize it into searchable text summaries, and highlight API-related sections.
Searchable content summaries that make it easy to locate design notes and key information.
Use contxt-box to save this debugging conversation and restore it in the next session, including attempted fixes, error messages, and unfinished tasks.
Durable conversation memory that reduces repeated explanation and improves multi-session collaboration.
Retrieve precise local documentation chunks for more reliable code generation context.
Give AI coding agents persistent local memory across sessions.
Ingest whole repositories into a large context window for coding agents.
Turn local Markdown knowledge into searchable context for AI coding agents.
Provide a personal documentation index to agents and IDEs over MCP HTTP.
Provide local developer context to AI agents for faster, safer initialization.