Open-source alternatives to ARC AGI

Learn_Prompting is an educational project focused on prompt engineering, providing the principles and techniques required to craft effective inputs and improve the quality of generative AI outputs. The project covers advanced prompting strategies to enhance reasoning, reliability, and output quality. This includes techniques for task decomposition, chain-of-thought reasoning, and the use of few-shot and zero-shot guidance. It also addresses model security through the study of prompt hacking, vulnerability analysis, and privacy auditing to prevent sensitive data leaks. The scope extends to th

Youtu Agent is an open-source framework for building, running, and evaluating autonomous agents powered by large language models. It provides the core infrastructure for creating agents that follow reasoning loops, use toolkits, and coordinate with other agents to solve complex tasks, all managed through YAML-driven configuration files. The framework distinguishes itself through its support for multi-agent orchestration, where a planner agent decomposes tasks and coordinates specialized worker agents, and through its integration with the Model Context Protocol for connecting to external toolk

Evidently is an AI observability platform and evaluation framework designed to quantify the performance of machine learning models and large language models. It functions as a monitoring tool for detecting data drift and quality degradation in tabular datasets, while providing a specialized analyzer for the faithfulness and correctness of retrieval augmented generation systems. The project distinguishes itself through an evaluation framework that utilizes judge models and custom rubrics to score language model outputs. It includes tools for iterative prompt optimization and the generation of

sam-hq is a collection of pre-trained vision foundation models and adapters designed for high-quality image segmentation, multimodal feature extraction, and depth estimation. It provides a zero-shot vision model capable of performing segmentation and classification across diverse domains without requiring task-specific training. The project features a high-quality image segmentation tool based on the Segment Anything Model that generates precise masks from spatial prompts. It includes a multimodal feature extractor to generate high-dimensional vector embeddings from both image and text inputs

This project is a language model evaluation framework and benchmarking tool designed to measure the accuracy and performance of models across diverse datasets. It provides a system for implementing model-based graders, running standardized tests for mathematical reasoning, coding, and factuality, and calculating quantified performance metrics such as precision, recall, F1 scores, and pass-at-k. The framework utilizes model-based grading and rubrics to validate response quality against expert-defined criteria. It includes a multi-model benchmarking loop and a model-agnostic API interface to co

Lighteval is an open-source framework for running standardized benchmarks and custom evaluation tasks against language models. It provides a system for defining new evaluation tasks with custom prompts, metrics, and scoring in YAML configuration files, and integrates with the Hugging Face Hub for storing and comparing results. The framework supports evaluating models across multiple inference backends, including transformers, vllm, and custom APIs, through a unified generation and log-probability interface. It includes a pluggable metric registry for built-in and custom scoring, a prediction

OpenCompass is a comprehensive evaluation platform, benchmarking suite, and distributed model evaluator designed to measure the performance and accuracy of large language models. It provides a framework for benchmarking both open-source and API-based models against diverse datasets using standardized metrics and reproducible pipelines. The project features an automated judging framework that uses language models as judges to score and verify the quality of generated text. It includes a performance leaderboard system for comparing the relative capabilities of various models across industry-sta

PhiCookBook is a technical guide and implementation framework for integrating small language models into applications. It provides instructions for deploying these lightweight models to perform reasoning, coding, and math tasks across various hardware environments and serving platforms. The project functions as a tutorial for developing intelligent AI applications by chaining prompts and code into executable sequences. It includes a framework for evaluating model behavior and calculating quality metrics to verify the accuracy and reliability of these workflows. The repository covers a broad

OpenCompass is an open-source framework for standardized benchmarking of large language models. It provides a configurable evaluation pipeline that supports both objective and subjective assessment, using a dual-engine architecture to handle closed-form answer comparison and open-ended response rating. The framework is designed as a modular platform where datasets, models, and metrics are composed through declarative YAML configuration files. The framework distinguishes itself through its extensible model integration layer, which supports custom models, HuggingFace models, and third-party API

ChatALL is a desktop application that functions as a multi-model chat client and aggregator for artificial intelligence services. It enables users to send a single prompt to multiple AI models simultaneously, allowing for the side-by-side comparison of generated responses within a unified interface. The application distinguishes itself through a local-first approach to data management, ensuring that all conversation logs and user configurations are stored directly on the user's device. This architecture supports privacy and offline access while providing a centralized system for managing and

This project serves as a comprehensive educational resource and technical handbook for engineers building applications powered by large language models. It provides a structured framework for mastering the principles of artificial intelligence engineering, covering the full lifecycle of model development from initial design to production deployment. The repository distinguishes itself by offering a deep dive into the practical implementation of advanced design patterns, including retrieval-augmented generation, agentic tool orchestration, and parameter-efficient model adaptation. It emphasize

Evals is a framework designed for automating, managing, and executing repeatable benchmarking suites to analyze the quality and performance of language models. It provides a platform for running standardized tests to measure model accuracy and track behavioral changes over time. The system distinguishes itself through a modular architecture that uses a standardized adapter layer to normalize inputs and outputs, allowing different models to be swapped and tested interchangeably. It supports the creation of custom benchmarks using proprietary data, enabling quality assurance on sensitive tasks

mcp-feedback-enhanced is a human-in-the-loop orchestrator and feedback tool for the Model Context Protocol. It provides a graphical interface for reviewing and approving AI-driven operations to prevent automated execution errors, using a socket-based system to synchronize state between backend AI processes and a user-facing interface. The project distinguishes itself by supporting a cross-platform deployment model available via native desktop wrappers and web browsers. It includes environment-aware context detection to identify if the system is running locally, via SSH, or within WSL, allowin

Langfuse is an open-source observability and evaluation platform designed for language model applications. It provides a centralized system for tracking execution traces, monitoring performance metrics, and managing prompt templates. By capturing hierarchical units of work and telemetry data, the platform enables developers to debug complex application lifecycles and analyze token usage, latency, and model interactions in production environments. The platform distinguishes itself through an integrated evaluation framework that allows for systematic benchmarking and automated scoring of model

This project is a development platform for managing the lifecycle of generative artificial intelligence models. It provides a unified environment for accessing, fine-tuning, and deploying large language models, serving as an orchestrator that handles the integration of diverse models into custom applications. The platform distinguishes itself by offering a managed infrastructure for hosting and scaling models, which removes the requirement for manual server maintenance or configuration. It includes integrated tools for supervised fine-tuning and vector embedding optimization, allowing for the

This project is a Python collection of algorithms and data structures that implement the concepts from the Artificial Intelligence: A Modern Approach textbook. It serves as an educational resource for learning core artificial intelligence concepts through the implementation of classic algorithms for searching, logic, and problem solving. The repository functions as an automated reasoning toolset for managing knowledge bases, a game theory engine for calculating optimal moves in competitive games, and a search and optimization library. It provides specialized frameworks for deriving logical co

This project is a transformer-based language model and autoregressive text generator designed to predict the next token in a sequence to produce human-like prose and synthetic text. It functions as a large language model that utilizes a transformer architecture to learn linguistic patterns from large datasets for unsupervised multitask learning. The repository provides a distribution of pre-trained weights, enabling natural language processing tasks without requiring additional training. This allows the model to perform zero-shot task generalization by applying learned patterns to new tasks.

Latent Diffusion is a framework for high-resolution image synthesis that performs the denoising process within a compressed latent space. It uses variational autoencoders to encode images into a lower-dimensional representation, reducing the computational cost of noise prediction compared to operating on raw pixels. The project enables text-to-image generation by integrating natural language descriptions through cross-attention conditioning. It also supports image inpainting and restoration, filling masked or missing image areas with generated content, and example-based synthesis using retrie

This project is an alignment framework and suite of pipelines for training language models using supervised fine-tuning and preference optimization. It provides tools for executing large-scale distributed training across multiple GPUs and compute nodes, alongside a system for measuring model helpfulness and dialogue quality through single-turn and multi-turn benchmarks. The framework includes specialized tools for direct preference optimization to refine model behavior using paired data without a separate reward model. It also supports constitutional AI alignment and the training of reward mo

Open Llama is an open source large language model and pre-trained transformer designed as a permissively licensed alternative to proprietary weights. It serves as a base model reproduction of the Llama architecture, providing a set of weights for a decoder-only transformer. The project provides a transparently trained model based on the RedPajama dataset, supporting unrestricted commercial and research use. It includes systems for serving pre-trained weights in various sizes. The project covers natural language processing research and performance benchmarking through text quality evaluation

This project is a technical curriculum and development guide focused on large language model prompt engineering, fine-tuning, and the creation of retrieval augmented generation applications. It serves as a comprehensive resource for developers to master crafting precise instructions and textual patterns to improve the quality and predictability of model outputs. The material covers the end-to-end workflow of adapting open-source models to specific datasets and integrating language models with vector databases to generate responses based on private information. It also provides a systematic ap

DeepAnalyze is an autonomous data science agent and research pipeline designed to transform raw datasets into comprehensive analysis reports. It operates by generating and executing Python code to perform data preparation, modeling, and visualization. The system utilizes a secure, containerized execution environment to run generated scripts in isolation from the host system. It includes a benchmarking tool to evaluate the accuracy and performance of large language models against standardized data science tasks and a standardized API gateway for managing model completions and file uploads. Th

RLinf is a distributed reinforcement learning orchestrator and embodied AI training framework. It provides the infrastructure to train vision-language-action models and robotic policies using a combination of reinforcement learning and supervised fine-tuning. The system is designed for scaling workloads across GPU clusters, managing the placement of actors, rollout workers, and environment components. It features a specialized robotics data collection pipeline for gathering teleoperated demonstrations and simulation trajectories into standardized replay buffers, alongside a hardware interface

This project is a collection of generative AI implementations focused on the development of AI agents, retrieval-augmented generation pipelines, and vector search integration. It provides a framework for connecting managed cloud databases to language models to create context-aware applications. The project covers the orchestration of autonomous agents that use multi-step reasoning and external tools to complete tasks. It includes implementations for semantic retrieval using high-dimensional embeddings and the use of model-agnostic prompting to ensure consistent outputs across different large

The Kaggle API command line interface is a suite of utilities for managing datasets, machine learning models, and competition entries from a terminal. It functions as a command line wrapper that translates user input into API calls to control remote cloud resources. The project differentiates itself by providing specialized tools for automating the execution of notebook kernels and managing the lifecycle of machine learning models, including version iteration and performance tracking. It also includes a utility for executing evaluation tasks against large language models and downloading the r

58069 Java source code diffs. http://arxiv.org/pdf/1807.03200

WaveFunctionCollapse is a procedural generation engine that creates complex, non-repeating patterns by treating spatial arrangement as a constraint satisfaction problem. It functions as a stochastic solver that derives output structures from a single input example, ensuring that every element placed within a grid satisfies specific adjacency requirements relative to its neighbors. The system distinguishes itself by using an entropy-driven approach to grid collapse, where it iteratively selects the cell with the fewest remaining possibilities to trigger a cascade of logical updates. By decompo