ServiceNow

BrowserGym, a Gym environment for web task automation

AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.

N-BEATS is a neural-network based model for univariate timeseries forecasting. N-BEATS is a ServiceNow Research project that was started at Element AI.

ServiceNow AI Platform documentation for LLM consumption.

A scalable asynchronous reinforcement learning implementation with in-flight weight updates.

PICARD - Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models. PICARD is a ServiceNow Research project that was started at Element AI.

Accelerating your LLM training to full speed! Made with ❤️ by ServiceNow Research

TapeAgents is a framework that facilitates all stages of the LLM Agent development lifecycle

Pytorch implementation of HighRes-net, a neural network for multi-frame super-resolution, trained and tested on the European Space Agency’s Kelvin competition. This is a ServiceNow Research...

WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?

A New End-to-end Framework for Evaluating Voice Agents

Codebase for Embedding Propagation: Smoother Manifold for Few-Shot Classification. This is a ServiceNow Research project that was started at Element AI.

GEO-Bench: Toward Foundation Models for Earth Monitoring

seasonal-contrast is a ServiceNow Research project that was started at Element AI.

ECCV 2018 - Where are the Blobs: Counting by Localization with Point Supervision. This is a ServiceNow Research project that was started at Element AI.

Codebase for EnterpriseOps-Gym from ServiceNow

Fluent SDK

TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series, from ServiceNow Research

GroundCUA

Java implementation of Seasonal-Trend-Loess time-series decomposition algorithm.

Python API for ServiceNow

Mythic C2 agent with a full in-memory BOF loader for macOS and Linux

The implementation of https://papers.nips.cc/paper/7352-tadam-task-dependent-adaptive-metric-for-improved-few-shot-learning . TADAM is a ServiceNow Research project that was started at Element AI.

Codebase for "Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning". This is a ServiceNow Research project that was started at Element AI.

Context is Key: A Benchmark for Forecasting with Essential Textual Information

This project contains source code for an example Node.js web application that interacts with ServiceNow's REST APIs.

SyGra - Graph-oriented Synthetic data generation Pipeline

Examples of the ServiceNow SDK

A comprehensive framework to test audio comprehension of Large Audio Language Models.

Helping AI practitioners better understand their datasets and models in text classification. From ServiceNow.

A verified version of the WebArena Benchmark

Adaptive Cross-Modal Few-shot learning OSS code. This is a ServiceNow Research project that was started at Element AI.

DoomArena is a Framework for Testing AI Agents Against Evolving Security Threats

Multithreading inference in Tensorflow Estimators. This is a ServiceNow Research project that was started at Element AI.

DuoRAT is a ServiceNow Research project that was started at Element AI.