Search Results for "scoring"
Sort By:
Showing 301 open source projects for "scoring"
View related business solutions-
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
1
ImageReward
[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences
ImageReward is the first general-purpose human preference reward model (RM) designed for evaluating text-to-image generation, introduced alongside the NeurIPS 2023 paper ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation. Trained on 137k expert-annotated image pairs, ImageReward significantly outperforms existing scoring methods like CLIP, Aesthetic, and BLIP in capturing human visual preferences. It is provided as a Python package (image-reward) that enables quick scoring of generated images against textual prompts, with APIs for ranking, scoring, and filtering outputs. Beyond evaluation, ImageReward supports Reward Feedback Learning (ReFL), a method for directly fine-tuning diffusion models such as Stable Diffusion using human-preference feedback, leading to demonstrable improvements in image quality. -
2
NGBoost
Natural Gradient Boosting for Probabilistic Prediction
ngboost is a Python library that implements Natural Gradient Boosting, as described in "NGBoost: Natural Gradient Boosting for Probabilistic Prediction". It is built on top of Scikit-Learn and is designed to be scalable and modular with respect to the choice of proper scoring rule, distribution, and base learner. A didactic introduction to the methodology underlying NGBoost is available in this slide deck. -
3
X For You Feed Algorithm
Algorithm powering the For You feed on X
X For You Feed Algorithm is the open-sourced core recommendation system that powers the For You feed on X (the social network formerly known as Twitter), and it represents one of the first times a major social platform has published production-level ranking code for public review and experimentation. The repository contains the full pipeline that ingests user engagement and content candidate data, processes it through retrieval, hydration, filtering, scoring, and selection layers, and ultimately ranks posts to show what appears in a user’s feed. At its heart, the system uses a transformer-based model adapted from xAI’s Grok architecture to predict probabilities for various user actions (such as likes, replies, reposts, clicks, and negative signals), then combines those into a weighted final score that drives ranking. -
4
Retro Bowl
Retro Bowl is an American football game in retro style
...The project focuses on delivering a simplified yet engaging sports simulation where players take on the role of both coach and general manager, making decisions about roster management, player upgrades, and in-game strategy. It recreates core mechanics such as passing, scoring, and play execution while maintaining a retro aesthetic that emphasizes clarity and responsiveness over realism. The codebase is structured to allow developers to modify gameplay systems, tweak mechanics, or expand features, making it suitable for experimentation and learning. It also aims to be portable and easy to run across environments, lowering the barrier for both players and contributors. -
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
5
Prometheus-Eval
Evaluate your LLM's response with Prometheus and GPT4
...It also provides training data and utilities for fine-tuning evaluator models so they can assess outputs according to custom scoring rubrics such as helpfulness, accuracy, or style. -
6
Cinephage
The AIO solution to your self hosted media gathering needs
...The platform boasts built-in support for multiple media acquisition paths (including torrent and Usenet indexers, streaming fallback mechanisms, and metadata discovery), smart quality and format scoring, and automated subtitle fetching, all while feeding results to compatible players and media servers. -
7
CyberStrikeAI
CyberStrikeAI is an AI-native security testing platform built in Go
...It supports role-based testing, letting teams define security roles with tailored tool access and prompts, and includes a skills system that encapsulates specialized testing strategies that the AI can incorporate into its planning. Through comprehensive lifecycle management, results are tracked, aggregated, and visualized, with support for versioned persistence, search, and risk severity scoring. -
8
Stop Slop
A skill file for removing AI tells from prose
...The project targets common AI habits such as filler openings, overused contrasts, unnecessary adverbs, vague language, passive phrasing, and metronomic sentence rhythm. It also includes a scoring rubric that rates drafts across dimensions such as directness, rhythm, trust, authenticity, and density. The skill is useful for drafting, editing, polishing, and quality-checking prose before publication. Its main value is giving writers and AI assistants a practical checklist for making text feel less synthetic and more intentional. -
9
what-to-eat
An AI-based intelligent recipe generation platform
...It supports a wide range of cuisines, including traditional Chinese regional styles and international dishes, making it versatile for different cultural preferences. The system goes beyond simple recipe suggestions by including features such as wine pairing recommendations, sauce design, and health scoring, providing a more holistic cooking experience. It also includes a dynamic configuration system that allows users to switch between AI models and adjust parameters in real time without restarting the application. -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
10
darwin-skill
Autoresearch-inspired autonomous skill optimization for Claude Code
...Instead of treating prompts or skill definitions as static assets, the system applies a continuous improvement cycle that evaluates performance, proposes changes, tests outcomes, and either retains or reverts modifications. The framework introduces a scoring system across multiple dimensions, enabling quantitative assessment of skill quality and ensuring that only improvements are preserved over time. It incorporates a “ratchet mechanism” similar to version control workflows, guaranteeing that performance never degrades as iterations progress. The system also separates the agents responsible for editing and evaluating skills to avoid bias, which improves the reliability of optimization results. -
11
TreeQuest
A Tree Search Library with Flexible API for LLM Inference-Time Scaling
TreeQuest, developed by SakanaAI, is a versatile Python library implementing adaptive tree search algorithms—such as AB‑MCTS—for enhancing inference-time performance of large language models (LLMs). It allows developers to define custom state-generation and scoring functions (e.g., via LLMs), and then efficiently explores possible answer trees during runtime. With support for multi-LLM collaboration, checkpointing, and mixed policies, TreeQuest enables smarter, trial‑and‑error question answering by leveraging both breadth (multiple attempts) and depth (iterative refinement) strategies to find better outputs dynamically -
12
AI Marketing Skills
Open-source AI marketing skills for Claude Code
AI Marketing Skills is a comprehensive open-source framework designed to transform AI agents into fully operational marketing and sales systems by equipping them with structured, reusable “skills” that automate real business workflows. Instead of simple prompts, the project provides complete operational modules that include scripts, scoring systems, and decision-making logic, allowing AI tools like Claude Code to execute complex marketing tasks end-to-end. The system is organized into multiple domains such as growth experimentation, sales pipeline generation, content production, outbound marketing, SEO optimization, and financial analysis, effectively covering the entire revenue lifecycle of a business. ... -
13
Job Recommend
The basics of building a job recommendation workflow
...You can study how to transform raw text into features and how to evaluate simple heuristics or baseline models. The code encourages experimentation, inviting you to swap scoring rules, adjust weights, or plug in alternative representations. It serves as a starting point for understanding recommendation pipelines before moving to production-grade systems. -
14
AutoAgent AI
Autonomous harness engineering
...Instead of manually tuning prompts or workflows, developers define high-level goals in a configuration file, and the system continuously modifies its own tools, orchestration, and logic based on benchmark performance. It operates through a loop of testing, analyzing failures, and refining the agent’s configuration to maximize a scoring metric. The framework uses a single-file agent harness combined with structured tasks and evaluation suites to guide optimization. It runs inside Docker for safe execution and reproducibility. This approach shifts agent development from manual design to automated optimization. The system is particularly useful for building domain-specific agents that need continuous performance improvement. -
15
Output
TypeScript framework for building AI workflows and agents
...It eliminates reliance on fragmented SaaS tools by providing all necessary components locally, ensuring better transparency and control over data and processes. Output includes built-in evaluation systems, such as LLM-as-a-judge scoring, and integrates workflow orchestration tools like Temporal to handle retries, parallel execution, and state management. It also supports multiple model providers through a unified API. -
16
ChainForge
An open-source visual programming environment
...The platform enables rapid experimentation by generating permutations of prompts and inputs, making it possible to test hundreds of variations in parallel and analyze performance trends more effectively. It also includes evaluation nodes that allow developers to define scoring functions, enabling automated benchmarking of outputs based on custom criteria such as accuracy, formatting, or relevance. -
17
TKD Scoring Wi-Fi
TKD Scoring Wi-Fi Server supporting Android and IPhone clients
...This looks even more professional and easier to use than any of the programs I’ve ever seen used at comps.” and “Hey... just installed everything and it’s unreal! Everything works perfectly, looks great!” encouraged us to make it public for everybody Like any scoring system the “TKD Scoring Wi-Fi” system has few basic components: *TKD Scoring Wi-Fi Server(PC or Android) *TKD Scoring Wi-Fi Client(Android or IPhone) *TKD Scoring Wi-Fi Remote Score Display (Android) -
18
WebGLM
An Efficient Web-enhanced Question Answering System
...WebGLM introduces several components that coordinate this process, including a retrieval module that selects relevant web documents, a generator that produces answers, and a scoring system that evaluates the quality of generated responses. The architecture aims to improve the reliability and usefulness of AI systems that answer questions about current or external knowledge sources. -
19
CTFd
CTFs as you need them
...It comes with everything you need to run a CTF and it's easy to customize with plugins and themes. Create your own challenges, categories, hints, and flags from the Admin Interface. Dynamic Scoring Challenges. Unlockable challenge support. Challenge plugin architecture to create your own custom challenges. Static & Regex-based flags. Custom flag plugins. Unlockable hints. File uploads to the server or an Amazon S3-compatible backend. Limit challenge attempts & hide challenges. Automatic bruteforce protection. Individual and Team-based competitions. ... -
20
Elfeed Emacs Web Feed Reader
An Emacs web feeds client
Elfeed is an extensible web feed reader for Emacs, supporting both Atom and RSS. It requires Emacs 24.3 and is available for download from MELPA or el-get. -
21
MLflow
Open source platform for the machine learning lifecycle
MLflow is a platform to streamline machine learning development, including tracking experiments, packaging code into reproducible runs, and sharing and deploying models. MLflow offers a set of lightweight APIs that can be used with any existing machine learning application or library (TensorFlow, PyTorch, XGBoost, etc), wherever you currently run ML code (e.g. in notebooks, standalone applications or the cloud). -
22
ZomboDB
Making Postgres and Elasticsearch work together like it's 2023
ZomboDB is a PostgreSQL extension that integrates Elasticsearch directly into Postgres, allowing for powerful full-text search and analytics capabilities. It manages Elasticsearch indices transparently, ensuring transactional consistency and enabling complex queries through SQL. -
23
StabilityMatrix
Multi-Platform Package Manager for Stable Diffusion
...It provides a framework to run experiments systematically—capturing inputs, model configurations, outputs, and metrics—so researchers and practitioners can reason about differences in quality, robustness, and failure modes. The repository often bundles tooling for automated prompt sweeping, scoring heuristics (such as diversity, coherence, or task-specific metrics), and visualization helpers to make comparisons interpretable. This approach is useful for model selection, prompt engineering, and benchmarking new checkpoints against baseline models under reproducible conditions. By turning ad-hoc tests into tracked experiments, StabilityMatrix reduces bias, surfaces subtle regressions, and accelerates iteration when tuning generative systems. -
24
Agent Zero
Agent Zero AI framework
...There is a lot of freedom in this framework. You can instruct your agents to regularly report back to superiors asking for permission to continue. You can instruct them to use point-scoring systems when deciding when to delegate subtasks. Superiors can double-check subordinates' results and disputes. -
25
ONNX
Open standard for machine learning interoperability
...It defines an extensible computation graph model, as well as definitions of built-in operators and standard data types. Currently we focus on the capabilities needed for inferencing (scoring). ONNX is widely supported and can be found in many frameworks, tools, and hardware. Enabling interoperability between different frameworks and streamlining the path from research to production helps increase the speed of innovation in the AI community.