Havuz

Agent skill for better research loops

Meet Reviewer 2 before they meet you ！ A Claude Code skill that red-teams your paper draft — a simulated peer-review panel + an evidence

Generalizing ARIS from 科研 to 研究 — same five-step loop (plan · draft · adversarial review · iterate · persist) applied beyond academic resear

Open-source Python toolkit for analysing environmental and IoT data from the DigiTech Smart House.

Overnight experiment: can an AI agent make money, and can you trust what it reports? The agent produces claims; a separate verifier it canno

AI-operable research workspace for Zotero, Obsidian, and NotebookLM. Use any two, or all three, through CLI, MCP, REST, and dashboard.

X/Twitter research MCP for Claude, Cursor, Windsurf and any MCP-compatible AI agent

Open benchmark datasets republished in stressed form to evaluate ML/LLM robustness. Curated by Santander AI Lab.

Experimental autonomous-agent living-room kernel with auditable boundaries.

Academic research agent skills for Claude Code and other Agent Skills-compatible tools. Hypothesis generation, experiment design, paper draf

When asked to pick a random number between 1 and 100, ChatGPT does not follow a random uniform distribution

面向科研工作的开源 Agent Skill 合集：文献引用 · 期刊选刊 · 论文格式 · 学术制图 · 多模型协作

Implementation of LatentMoE,Toward Optimal Accuracy per FLOP and Parameter in Mixture of Experts (Elango et al., NVIDIA 2026) — in Pytorch.

💬 Trace citation chains for any concept across research papers and render them as an interactive graph.

Research-backed Harness Engineering study repo with a runnable Python MVP built around Plan -> Work -> Review.

Public research and education companion to the AI-Native Operating Framework, with reusable events, curriculum, labs, and tool tracks.

Local-first YouTube outlier research — find the videos that outperform their channels, and learn why

Research Pilot helps AI agents understand, maintain, and advance research projects through papers, claims, evidence, experiments, and human-

Search, preview, and analyze datasets from 20+ platforms via a single MCP connector. Works with Claude instantly.

Claude Code CLI — original source code snapshot for research. Property of Anthropic.

Self-hosted alphaxiv-style paper-reading app (FastAPI CORS proxy + Vite/React/TS SPA)

USEL is an open-source CPU-based scientific computing framework for computational physics and quantum research. It provides modular numerica

Official research repository for CeloHT, containing research papers, RFCs, technical specifications, architecture, security studies, and evi

Rust Noiron/Norion self-evolving local LLM runtime engine for non-commercial research deployment

amore (ah-my-openresearch) is opencode-based research workspace with personas, bundled skills, project lab contracts, and literature-wiki wo

Ontological based research and development software engineering agent, that is math heavy.

Convert scientific papers into executable, reproducible codebases

中文公司调研 Agent

Fast, daily-updated skill and CLI for arXiv, PubMed, PMC, and policy retrieval

Multimodal document QA: vision + retrieval over PDFs (LLaVA + LlamaIndex)

Comprehensive research co-pilot for Claude Code and claude.ai — 14 skills covering literature review, methodology, ethics review, data analy

Research design for a Jev-native agent system:enable more options than jev provided with virtulization and paging, tool integration, externa