Stars
A java implementation of the Identity Map design pattern
Data Journalist Agent: Transforming Data into Verifiable Multimodal Story
Automated auditing pipeline for LLM and agent benchmarks — surfaces task ambiguity, environment conflicts, and evaluation bugs.
Skills to help your coding agents use Together AI products.
What LLMs Think When You Don’t Tell Them What to Think About?
[ICLR 2026] When Does Divide and Conquer Work for Long Context LLM? A Noise Decomposition Framework
A holistic framework for advancing LLMs as data science agents
A clean, modular SDK for building AI agents with OpenHands V1.
ReasonIF: Large Language Models Fail to Follow Instructions During Reasoning
The Open Deep Research app – generate reports with OSS LLMs
Open AI data scientist agent that automates complex data analysis tasks using the ReAct framework. Execute Python code locally or in the cloud, upload datasets, and generate detailed analytical rep…
An open source TypeScript deep research implementation
Together Open Deep Research
A collection of notebooks/recipes showcasing usecases of open-source models with Together AI.
A curated list of Large Language Model (LLM) Interpretability resources.
Large Language Model Text Generation Inference
Associated Repository for "Translation between Molecules and Natural Language"
Official implementation of the ACL 2024: Scientific Inspiration Machines Optimized for Novelty
FAIR Chemistry's library of machine learning methods for chemistry
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Benchmarking LLMs with 80k multiple-choice chemistry questions for the LLM Hackathon for Applications in Materials and Chemistry.
InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery (COLING 2025)
BAMBOO (Bytedance AI Molecular BOOster) is an AI-driven machine learning force field designed for precise and efficient electrolyte simulations.
A high-throughput and memory-efficient inference and serving engine for LLMs
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthr…