A simple and easy-to-use library to enjoy videogames programming

The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of …

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

Streamlit — A faster way to build and share data apps.

A catalog of design patterns when building generative AI applications

Building Applications with AI Agents

High-performance safety rules engine for real-time event processing at scale

React rendering engine to make users into builders

List of Awesome Red Teaming Resources

Directory of open source tools for online safety

Share evaluation outcomes and implementation tips for using open safety models in Trust & Safety workflows

The Open Source Code for LLM4SD (Large Language Models for Scientific Synthesis, Inference and Explanation)

Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning, achieving state-of-the-art performance on 38 out of 60 public benchmarks.

TextCrafter: Accurately Rendering Multiple Texts in Complex Visual Scenes

Ovis-Image is a 7B text-to-image model specifically optimized for high-quality text rendering, designed to operate efficiently under stringent computational constraints.

Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding

String-to-String Algorithms for Natural Language Processing

aider is AI pair programming in your terminal

Live-SWE-agent: live, runtime self-evolving software engineering agent

The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

AI benchmark runtime framework that allows you to integrate and evaluate AI tasks using Docker-based benchmarks.

In this repository, 16 models compete to outperform each other in the game Town of Salem. Each model is randomly assigned roles like Vampire, Peasant, Clown, or special variants of Peasants with un…

This repository contains ScholarQABench data and evaluation pipeline.

A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future …

Lexicon of frame files used by Propbank annotation. A searchable, readable version of the latest release is here: http://propbank.github.io/v3.4.0/frames/

The official released annotations, both in .prop pointer format and as conll files. Does not contain the source texts

Simple, Pythonic, text processing--Sentiment analysis, part-of-speech tagging, noun phrase extraction, translation, and more.