Repo · Search & RAG

ReadyCode Reader

MCP and browser Reader: retrieve PDF/DOCX/XLSX passages locally, then TypeSafe Jev checks relevance, sufficiency, conflicts, and spreadsheet plan fit…

Open github.com ↗

From the repository

Save Tokens and time on huge PDFs, Word & excel questions; get only the cited passages that answer. Codex test on a 200-page PDF spent 913,468 tokens, 3VS ReadyCode.ai MCP of only 41,997 tokens and ~20 s with Reader, both 8/8 correct. MCP server for Claude Code, Cursor and Codex, or use it in your browser at Readycode.ai .

How builders describe it

Local-first MCP and browser tool that uses Jev decisions to keep PDF, Word and Excel passages likely to answer a question, flag conflicting or instruction-like evidence, and decide when spreadsheet requests need exact local calculation.

MCP and browser Reader: retrieve PDF/DOCX/XLSX passages locally, then TypeSafe Jev checks relevance, sufficiency, conflicts, and spreadsheet plan fit before cited answers.

The decision Jev makes

Rank candidates against a query, or answer whether a passage is relevant.

Where it fits

Search pipelines retrieve too much. These projects use Jev as a reranker or relevance check after the first search, so only useful results reach the user or the model. All 108 search & rag projects →

Related projects