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

aider is AI pair programming in your terminal

Granite Code Models: A Family of Open Foundation Models for Code Intelligence

A benchmark that challenges language models to code solutions for scientific problems

Discovering Data-driven Hypotheses in the Wild

Agentless🐱: an agentless approach to automatically solve software development problems

LLM101n: Let's build a Storyteller

CodeBERTScore: an automatic metric for code generation, based on BERTScore

Official codebase for the paper "Beyond A* Better Planning with Transformers via Search Dynamics Bootstrapping".

AIDE: the Machine Learning CodeGen Agent

The Official Repo of ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code (https://arxiv.org/abs/2311.09835)

A programming framework for agentic AI 🤖

This repo contains code+pre-trained models for extracting information from camera-trap images. The pre-trained models have been trained on the Snapshot Serengeti dataset.

Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji.

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

[ICLR 2024] SWE-Bench: Can Language Models Resolve Real-world Github Issues?

Cognition's results and methodology on SWE-bench

An self-improving embodied conversational agent seamlessly integrated into the operating system to automate our daily tasks.

This is the repository for the BioCLIP model and the TreeOfLife-10M dataset [CVPR'24 Oral, Best Student Paper].

PyTorch Wildlife: a Collaborative Deep Learning Framework for Conservation.

Official implementation for <Large Language Models for Automated Open-domain Scientific Hypotheses Discovery>, accepted by ACL 2024.

Official implementation of the ACL 2024: Scientific Inspiration Machines Optimized for Novelty

🙌 OpenHands: Code Less, Make More

Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"

Chemcrow

[ICLR 2024] Code for the paper "Text2Reward: Automated Dense Reward Function Generation for Reinforcement Learning"

Code for "Learning to summarize from human feedback"