AI Scientist Showcase

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

High accuracy RAG for answering questions from scientific documents with citations

AlphaFold 3 inference pipeline.

The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas

Genome modeling and design across all domains of life

Robin: A multi-agent system for automating scientific discovery

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

AI agents running research on single-GPU nanochat training automatically

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

Universal memory layer for AI Agents

A programming framework for agentic AI

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

LlamaIndex is the leading document agent and OCR platform

aider is AI pair programming in your terminal

Build, run, and manage agent platforms.

Build resilient agents.

DSPy: The framework for programming—not prompting—language models

A modular graph-based Retrieval-Augmented Generation (RAG) system

ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration

Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 160,000+ scientists worldwide. 148 ready-to-use skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

An autonomous agent that conducts deep research on any data using any LLM providers

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

Tongyi Deep Research, the Leading Open-source Deep Research Agent

An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the simplest implementation of a deep research agent - e.g. an agent that can refine its research direction overtime and deep dive into a topic.

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

Open source code for AlphaFold 2.

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

Open-source reproduction of OpenAI-style deep research using LangGraph and multi-step planning.

Fully local web research and report writing assistant

Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology

[NeurIPS2025] "AI-Researcher: Autonomous Scientific Innovation" -- A production-ready version: https://novix.science/chat

Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning

Segment Anything in Medical Images

Official repository for the Boltz biomolecular interaction models

Biomni: a general-purpose biomedical AI agent

The official sources for the RDKit library

Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2

FAIR Chemistry's library of machine learning methods for chemistry

Toward High-Accuracy Open-Source Biomolecular Structure Prediction.

A deep learning package for many-body potential energy representation and molecular dynamics

This API provides programmatic access to the AlphaGenome model developed by Google DeepMind.

Official implementation of MatterGen -- a generative model for inorganic materials design across the periodic table that can be fine-tuned to steer the generation towards a wide range of property constraints.

📄 🤖 AI for medical and scientific papers

Deep probabilistic analysis of single-cell and spatial omics data

Foundation model for single-cell multi-omics — cell typing, perturbation, and batch integration.

Chemcrow

Foundation Models for Genomics & Transcriptomics

A virtual lab of LLM agents for science research

[ACL 2024 Findings] MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning https://arxiv.org/abs/2311.10537

Repo housing the open sourced code for the ai2 scholar qa app and also the corresponding library

AI agent specialized in single-cell type annotation and analysis for genomics research.

Autonomous chemical research agent (Nature 2023) that designs, plans, and executes experiments with lab tools.

Curated index of AI-for-science tools, papers, datasets, and frameworks — the field at a glance.

Open platform for AI software engineers — runs in a sandbox, edits code, browses the web, executes shells.

AI2's toolkit for training, evaluating, and releasing open instruction-following models.

Open LLM for formal theorem proving in Lean 4, advancing automated mathematical reasoning.

A language-agent gym with challenging scientific tasks for training and evaluating research agents.

Open-source automated theorem prover pushing state-of-the-art whole-proof generation.

Discovering new mathematics and algorithms by pairing an LLM with a systematic evaluator (Nature 2024).

Google Research's pretrained time-series foundation model for zero-shot forecasting.

Foundation model for Earth-system forecasting — weather, air quality, ocean waves, and cyclone tracks.

Moonshot AI's reinforcement-learned theorem prover for Lean, with strong miniF2F results.

OpenAI's framework for evaluating LLMs and AI systems on a registry of benchmarks.

Natural-language code execution layer — lets LLMs run code locally to complete arbitrary tasks.

Princeton NLP's autonomous coding agent that resolves real GitHub issues, achieving top scores on SWE-bench.

Benchmark of real GitHub issues used to measure end-to-end coding-agent capability.

Transformer that solves small tabular prediction problems in a single forward pass — no training needed.