Graph-based long-term memory skill for AI (LLM) coding agents — faster context, fewer tokens, safer refactors
Open-source AI model evaluation and benchmarking framework for LLMs (OpenAI, Ollama, Claude, Gemini)
A powerful command-line interface for interacting with AI models via Python.
Local RAG pipeline that ingests PDF, DOCX, PPTX, XLSX, and images into ChromaDB and answers questions with inline citations. Hybrid BM25 + semantic retrieval with RRF, Claude Vision for embedded images, multi-turn chat. Streamlit UI and CLI.
Hierarchical coding CLI: frontier models plan and review, a local Ollama model drafts the code. $0 incremental cost on a bring-your-own-subscription setup.
Simple MCP server enabling Claude Desktop to download earthquake and waveform data via ObsPy - (Developed at the request of Professor Weiqiang Zhu, Earth & Planetary Science, UC Berkeley)
Claude Code template for AI-collaboration projects: a governance scaffold that lets a non-engineer direct and approve the work without reading code. Bootstraps a repo with memory, contracts, policies, checks, and ops docs pre-wired.
Add a description, image, and links to the calude topic page so that developers can more easily learn about it.
To associate your repository with the calude topic, visit your repo's landing page and select "manage topics."