scientific-ai

The open-source AI research workbench for scientific research and agent workflows. Local-first, model-agnostic desktop app with extensible skills, MCP tools and connectors, Python/R execution and traceable artifacts for reproducible research on macOS, Windows and Linux.

A curated list of awesome AI tools, libraries, papers, datasets, and frameworks that accelerate scientific discovery — from physics and chemistry to biology, materials, and beyond.

Physics-Informed Neural Networks (PINN) Solvers of (Partial) Differential Equations for Scientific Machine Learning (SciML) accelerated simulation

Pre-built implicit layer architectures with O(1) backprop, GPUs, and stiff+non-stiff DE solvers, demonstrating scientific machine learning (SciML) and physics-informed machine learning methods

Build and simulate jump equations like Gillespie simulations and jump diffusions with constant and state-dependent rates and mix with differential equations and scientific machine learning (SciML)

Extension functionality which uses Stan.jl, DynamicHMC.jl, and Turing.jl to estimate the parameters to differential equations and perform Bayesian probabilistic scientific machine learning

A framework for developing multi-scale arrays for use in scientific machine learning (SciML) simulations

Easy scientific machine learning (SciML) parameter estimation with pre-built loss functions

Scientific reliability layer for AI-assisted biology: evaluates what evidence warrants, caps unsupported claims, audits analytical validity, and prevents silent scientific overreach.

Privacy-safe Codex skill for battery evidence and mechanism audits | 电池与材料电化学证据、机理及论文结论审查

A local web platform for blind and model-assisted MS/MS structure annotation.

Scientific AI and the Future of OME-Zarr: Building Intelligent Bioimage Analysis Workflows

An end-to-end, multi-agent platform that accelerates scientific workflows by rigorously validating hypothesis novelty through adversarial literature review

Self-hosted evidence-gated scientific AI with isolated Python/R, independent review, deterministic validation, and complete provenance.

Scientific AI and the Future of OME-NGFF: Intelligent Bioimage Analysis Workflows

Putting science back on track: a memory system for scientific research.

an AI system that does scientific research end-to-end, autonomously.

RelicScope AI — local multimodal scientific forensics infrastructure for artwork, with Android Scout, NVIDIA DGX Spark and NIM

Evidence-backed scientific AI report infrastructure

Discover AI tools, MCP servers, and agent skills for scientific research across literature, data, writing, and lab work