L

large language models

Coordinated Agent Swarm Testing — open-source framework that deploys 100 Claude AI agents in five specialized squads (Security, Logic, Robustness, Performance, Data Integrity) to systematically analyze codebases for bugs, security issues, and code quality problems. A research-backed substitute for human beta testing. Empirical results from the published paper: 100 agents analyzed a 12,500-line React/TypeScript application in 63 minutes, identified 687 unique findings, at a total cost of $7.97 — compared to $2,000-$20,000 for equivalent human beta testing. Available via npm (cast-swarm) and as an MCP server. Apache 2.0 licensed. Published preprint available.

Notes from the PhD course "Using LLMs for Scientific English: Writing and Presenting" held at the University of Modena and Reggio Emilia in March 2025.

StockChat: A Stock Market Assistant

Use fully dynamic LLM agent networks to handle more ambiguous and difficult prompts than individual LLMs or fixed LLM agent networks can handle on their own.

Fork of Rubrix for natural language processing machine learning dataset labeling and RLHF (reinforcement learning human feedback) and active learning. Original license was Apache 2.0 which allows Argilla.io to modify the software without sharing it with the community.

A simple (WIP) GUI for chatting with llama via few-shot prompts!