scientific-workflow - 技术专题

A blueprint-driven AutoResearch runtime for orchestrating AI research workflows from idea generation and experiments to paper writing and peer review.

Open-source, local-first desktop AI research workbench for scientific computing with Python/R, MCP bioinformatics tools, SSH/WSL/GPU runtimes, and OpenAI/Anthropic models.

An AI workflow skill pack for research, competitions, and innovation projects.

Paired-scientist AI assistant for reproducible research — lightweight Go runtime, lifecycle hooks, manuscript integration, 12 baseline scientific skills. PicoClaw-compatible.

HyperFlow: a scientific workflow engine

Open-source infrastructure for AI-native scientific labs

Turn Claude Code into an interactive scientific workspace: workflow, file system, and knowledge graph.

Start research with the material you have: guided tasks, durable local progress, literature, writing, experiments, revision and rehearsal. Seven Codex skills for research beginners.

AITP Research Charter and Protocol: a charter-first protocol, contract, and adapter surface for AI-assisted theoretical physics research.

SciLoom 科研舱 — AI 辅助的桌面科研管理工作台

A collection of tools for the analysis of nanocrystals.

AI-assisted 13-stage academic research workbench for Codex: 40 bundled skills, research ledger, novelty audit, three-round review, de-AI polish, publication-grade figures.

R-LAM is a reproducibility-constrained execution framework for Large Action Models in scientific workflow automation. It enables adaptive, agent-driven workflow execution while enforcing strict guarantees on auditability, determinism, and replayability.

This repository contains exemplary workflow using programming tools and libraries for data rescue of historical biodiversity data. These tools combine OCR and text mining approaches to retrieve valuable information like species, functional traits and environments.

Local-first agentic research platform that turns project bundles into evidence-bound scientific papers with deterministic gates, scientist-panel review, fault localization, and rollback.

General evidence-grounded workflow for quantitative research, with first-class support for econometrics and quantitative economics—from idea discovery to reproducible delivery.

Full-SMS (Full Single Molecule Spectroscopy) is a collaborative research platform where scientists upload experimental data, run analysis pipelines and visualize results. It offers shared workspaces for seamless collaboration and a plugin marketplace that lets researchers extend the platform with custom analysis tools for specific research needs.

🌱 This repository is devoted to the emergence of Generative Simulation—a concept that hybridizes large language models (LLMs) and simulation. Simulation engines are developed or wrapped in such a way that they can be directly manipulated by generative AI, without requiring intensive retraining or fine-tuning.

Turn a curiosity into a question that can be settled, freeze what would count as an answer before running anything, and leave a verdict auditable from git alone. Skills for Claude Code / Codex; pip install newlife.

天津大学记忆与推理课题组 · AI for Science 科研全自动化平台的项目之家：产品纲领与 ADR、spec、真实科研案例卡、发布到 GitHub Pages 的公开调研、跨仓 CLI；生产代码在独立的 TJU-AI4Science-Platform，以 nested git 挂在 platform/ 下，本仓不放业务代码