Anthropic Document Skills (PDF, DOCX, PPTX, XLSX)
Anthropic's official Claude Skills for working with document formats — fill, merge, and extract data from PDFs, Word files, PowerPoint decks, and Excel spreadsheets inside agent workflows.
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
By leveraging Python SDK / OpenAI API, the application isolates runtime dependencies while maintaining low-latency execution traces across multi-step LLM operations.
Clone DeusData/codebase-memory-mcp from GitHub
Install dependencies with pip install -r requirements.txt (or uv sync)
Copy .env.example to .env and add your API keys
Run the skill server and connect your AI client via stdio or HTTP
Anthropic's official Claude Skills for working with document formats — fill, merge, and extract data from PDFs, Word files, PowerPoint decks, and Excel spreadsheets inside agent workflows.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
An AI-powered multi-agent codebase migration assistant built with LangGraph and Streamlit that plans file-by-file refactoring tasks, performs human-in-the-loop (HITL) risk review, fans out parallel refactoring workers, and aggregates...
RAG Tutorials & PipelinesA conversational RAG application that connects to any GitHub repository, allowing developers to query codebases, pull requests, and commit logs with conversational AI.
Starter AI AgentsPocket Flow: Codebase to Tutorial.