Stars
LLM4AD: A Platform for Algorithm Design with Large Language Model
Days: a Performant Discrete-Event Simulator for Network Simulations
RHO: Evolving Agents in the Dark — Retrospective Harness Optimization via Self-Preference. Improving LLM agents from unlabeled past trajectories (arXiv:2606.05922).
Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize
Efficient multi-token attribution for reasoning language models — Python package, CLI, and HTML token traces
Soft-pastel, research-blog-style matplotlib figures as an installable Claude Code plugin.
PaperBanana: Automating Academic Illustration For AI Scientists
Meta-Harness: 76.4% on Terminal-Bench 2.0 (Claude Opus 4.6)
mstar: Optimizing memory architecture for every LLM task as executable Python code.
Easy parallel project management for Claude Code agents.
AI agents running research on single-GPU nanochat training automatically
Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork
Elevate your AI research writing, no more tedious polishing ✨
MCP server for converting ar5iv papers to Markdown with arXiv search
bloom - evaluate any behavior immediately 🌸🌱
Self-evolve your LLM's capabilities with just a task and a success criterion.
VS Code extension: turn terminal messages into native system notifications
📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools lik…
This is the official implementation for "AUTOPR: LET'S AUTOMATE YOUR ACADEMIC PROMOTION!".
Replace the default file explorer in Obsidian with a clean two-pane interface featuring folder tree, tag browsing, file previews, keyboard navigation, drag-and-drop, pinned notes, and customizable …