Search

A reusable RAG package and optional Streamlit app for academic question answering.

Audit golden evaluation datasets for LLM/RAG application quality risks.

A continual reinforcement learning benchmark

Three-layer semantic compression for LLM prompts (L1+L2+L3 + Lean Mode + Columnar JSON)

Moroccan Darija NER and semiotic class tagging — rule-based NER engine that outperforms GPT-4o-mini on Darija text. Built in Rust for O(1) lookup, 750x faster than LLMs.

LangChain Chain - NEAR Staking optimization

LangChain Tool - NEAR import key

LangChain Tool - NEAR upgrade key

LangChain Tool - NEAR update wallet

LangChain Chain - NEAR DeFi arbitrage

Build LangChain Tool: NEAR Price & Market Data

LangChain Tool - NEAR delete key

LangChain Tool - NEAR encrypt wallet

Python SDK for the Factive fact-checking API. Stream LLM output and get verified claims back in real time.

Tool for detecting sensitive data leaks in files and cloud storage

LangChain Tool - NEAR decrypt wallet

76 audit-ready Claude skills automating the industrial robot, cobot, AMR, ROS2, V&V, AI/ML, and IEC 62443 lifecycle. 38 builder + reviewer pairs anchored to ISO 10218, 13849, 62061, 12100, 9283, 15066, 3691-4, and IEC 62443.

Portable SKILLs workspace for Claude Code, Codex, and Gemini — issue-driven workflows and cross-agent collaboration via bridge scripts with session continuity.

Claude Code and Codex SKILLs for PDF, Excel, Word, and PowerPoint manipulation — extraction, forms, formulas, tracked changes, adapted from Anthropic skills.

Claude Code and Codex SKILLs for consulting-quality decks — strategy storyboarding, brand-system identity, and pixel-perfect PDF or editable PPTX output.