FutureHouse ORG

High accuracy RAG for answering questions from scientific documents with citations

PaperQA2 lets you ask plain-English questions about a folder of research PDFs and get answers with exact citations pointing to the specific paper and page each claim came from, using AI-powered search rather than memorized knowledge.

Robin: A multi-agent system for automating scientific discovery

A language agent gym with challenging scientific tasks

A scientific reasoning model, dataset, and reward functions for chemistry.

Framework enabling modular interchange of language agents, environments, and optimizers

Benchmark for LLM-based Agents in Computational Biology

Evaluation dataset for AI systems intended to benchmark capabilities foundational to scientific research in biology

An aviary-based data science agent based on jupyter notebooks

LitQA Eval: A difficult set of scientific questions that require context of full-text research papers to answer

No description.

Documentation and tutorials for the FutureHouse platform API

No description.

No description.

Central LLM client for use by Aviary and PaperQA

FutureHouse fork of trl

Design system for Future House apps

Fork of upstream