Search Results for "compare" - Page 2
Sort By:
Showing 142 open source projects for "compare"
View related business solutions-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
Demo Series - Small Business Backup By VeeamWatch this on-demand demo series and learn how to protect your Microsoft 365 data with clear, simple, actionable steps that are easy to implement for businesses of all sizes.
-
1
Cha
Deprecated AI CLI for terminal based interactions
...Its value today is mostly archival, showing the earlier implementation and design direction that led to Ch. It may still be useful for users who want to understand the migration path, compare versions, or preserve older chat histories before moving to the maintained tool. -
2
LIFELINES
Survival analysis in Python
...It is designed to be accessible to Python users and works well with common scientific computing workflows. Built-in plotting methods and datasets help users explore survival curves and compare groups visually. It is a practical tool for analysts, researchers, and data scientists who need event-time modeling without leaving Python. -
3
US Job Market Visualizer
A research tool for visually exploring Bureau of Labor Statistics
...Bureau of Labor Statistics. It organizes information for 342 occupations into a treemap where area represents employment and color can represent different metrics. Users can compare projected growth, median pay, education requirements, and estimated digital AI exposure. The repository includes tools for scraping BLS pages, converting them to structured data, and building the visualization dataset. An LLM scoring pipeline can evaluate occupations using custom criteria supplied through prompts. The included AI exposure layer is intended as an exploratory estimate rather than a prediction of job elimination. ... -
4
Sprix SAGE Router
State-aware SELF/COLLABORATE/HANDOFF routing for A2A agent networks
...It learns contextual reliability and outcome information from previous execution evidence instead of relying on a single reputation score. Bounded search and replanning allow the router to compare feasible teams and revise decisions as task conditions change. -
PRTG Catches Network Issues Before They Cause DowntimeReactive troubleshooting usually means hearing about a problem from frustrated users, not your monitoring tool. PRTG sets threshold-based alerts across devices, servers and applications, notifying your team by email, SMS or push the moment a metric crosses a set limit. That means catching a failing disk or overloaded server before it becomes an outage and getting time back from firefighting. Start a free trial and set your first alerts today.
-
5
zhengxi-views
Zheng Xi (Efonda Fund Manager) Investment Research Agent Skill
...It also includes real fund data snapshots for managed funds and broader fund comparison workflows. The skill can answer source-grounded questions, explain methodology, compare funds, and score funds against Zheng Xi’s stated framework. It is positioned as a research and learning assistant, not as financial advice. -
6
Perceval
An open source framework for programming photonic quantum computers
An open-source framework for programming photonic quantum computers. Through a simple object-oriented Python API, Perceval provides tools for composing circuits from linear optical components, defining single-photon sources, manipulating Fock states, running simulations, reproducing published experimental papers and experimenting with a new generation of quantum algorithms. It aims to be a companion tool for developing photonic circuits – for simulating and optimizing their design, modeling... -
7
Pearl
A Production-ready Reinforcement Learning AI Agent Library
...Tutorials demonstrate end-to-end workflows on OpenAI Gym tasks and contextual-bandit setups derived from tabular datasets, emphasizing reproducibility and clear baselines. Pearl’s design favors clarity and deployability: metrics, logging, and evaluation harnesses are integrated so you can monitor learning, compare agents, and catch regressions. -
8
Claude Commerce Agents
Reference blueprint for building shopping and merchant agents
Claude Commerce Agents is a reference implementation of customer-facing shopping and staff-facing merchant agents built with Claude. The shopping agent can search catalogs, compare products, plan purchases, manage carts, answer policy questions, and remember customer preferences. The merchant agent analyzes business performance, handles inventory and listing workflows, proposes pricing changes, and drafts campaigns. Both roles share reusable skills, prompts, tool contracts, grounding rules, and safety gates. ... -
9
BigMac
An open-source toolkit for BigMac-style pipeline-parallel training
...A Megatron-Core reference backend and Qwen3 and Qwen3-VL tutorials help developers connect the approach to real training workflows. The simulator lets researchers visualize schedules, compare pipeline strategies, and model timing imbalances caused by compute cost, input size, or uneven stage partitioning. Profiling tools also expose per-operator traces for diagnosing pipeline performance before or during experiments. -
99.99% Uptime for MySQL and PostgreSQL DatabasesCloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
-
10
D4RL
Collection of reference environments, offline reinforcement learning
...The API is based on Gymnasium (via gym.make) and each environment also exposes a method get_dataset() that returns the offline data to learn from. The repository emphasizes open science, reproducibility, and benchmarking at scale, making it easier to compare algorithms on equal footing. -
11
rate.sx
Curl cryptocurrencies exchange rates
...It emphasizes human-readable output by default, with options for concise one-liners or richer summaries including sparkline-style ASCII charts. The service supports multiple coins, fiat conversions, and historical lookups so you can compare prices over time without leaving the terminal. Under the hood it aggregates price feeds and normalizes the results for robust querying, yet keeps the interface dead simple. Because it’s HTTP-based, you can integrate it into shell prompts, tmux status lines, CI logs, dashboards, or chat bots. It’s ideal for developers and power users who want quick answers and scriptable endpoints without installing a heavy client. -
12
KVCache-Factory
Unified KV Cache Compression Methods for Auto-Regressive Models
...KVCache-Factory provides a platform for implementing and evaluating multiple compression strategies that reduce memory usage while preserving model performance. The framework integrates several state-of-the-art methods such as PyramidKV, SnapKV, H2O, and StreamingLLM, allowing researchers to compare and experiment with different approaches within the same environment. It also supports advanced inference configurations such as Flash Attention v2 and multi-GPU inference setups for very large models. -
13
Unstract
No-code LLM Platform to launch APIs and ETL Pipelines
Unstract is a powerful open-source, no-code platform built to automate the extraction and structuring of unstructured documents using large language models and flexible workflows, enabling developers and data teams to turn messy files into organized JSON content without complex coding. It integrates a visual Prompt Studio environment where users can iteratively design extraction schemas, compare outputs from different models, and monitor costs and accuracy side by side, making it easier to refine prompts and extraction logic before deploying at scale. Unstract supports deploying structured extraction as REST API endpoints or embedding it into data engineering ETL pipelines, which allows it to plug directly into data warehouses, cloud storage, or downstream analytics systems. ... -
14
Lingvo
Framework for building neural networks
...Lingvo includes reference models and configurations for domains like machine translation, automatic speech recognition, language modeling, image understanding, and 3D object detection. Centralized hyperparameter configuration files allow researchers to share exact experiment setups so others can retrain and compare results reliably. -
15
Advanced RAG Techniques
Advanced techniques for RAG systems
...It includes hands-on Jupyter notebooks and runnable scripts that show how to implement ideas like optimizing chunk sizes, proposition chunking, HyDE/HyPE query transformations, fusion retrieval, reranking, and ensemble retrieval. There is also an evaluation section that demonstrates how to measure RAG performance and compare different configurations in a systematic way. -
16
AGI (Android GPU Inspector)
Android GPU Inspector
...Beyond per-frame analysis, AGI correlates GPU activity with CPU threads and system events to diagnose contention, scheduling issues, and thermal or power constraints. The tool is designed for reproducible performance investigations, making it easier to iterate, compare captures, and ship smoother, more efficient Android graphics experiences. -
17
Multimodal
TorchMultimodal is a PyTorch library
...The design emphasizes composability: you can mix and match encoder, fusion, and decoder components rather than starting from monolithic models. The repository also includes example scripts and datasets for common multimodal tasks (e.g. retrieval, visual question answering, grounding) so you can test and compare models end to end. Installation supports both CPU and CUDA, and the codebase is versioned, tested, and maintained. -
18
xFormers
Hackable and optimized Transformers building blocks
xformers is a modular, performance-oriented library of transformer building blocks, designed to allow researchers and engineers to compose, experiment, and optimize transformer architectures more flexibly than monolithic frameworks. It abstracts components like attention layers, feedforward modules, normalization, and positional encoding, so you can mix and match or swap optimized kernels easily. One of its key goals is efficient attention: it supports dense, sparse, low-rank, and... -
19
TensorBoardX
tensorboard for pytorch (and chainer, mxnet, numpy, etc.)
...This allows a training program to call methods to add data to the file directly from the training loop, without slowing down training. TensorboardX now supports logging directly to Comet. Comet is a free cloud based solution that allows you to automatically track, compare and explain your experiments. It adds a lot of functionality on top of tensorboard such as dataset management, diffing experiments, seeing the code that generated the results and more. Create special chart by collecting charts tags in ‘scalars’. Note that this function can only be called once for each SummaryWriter() object. Because it only provides metadata to tensorboard, the function can be called before or after the training loop. -
20
Haystack
Haystack is an open source NLP framework to interact with your data
...Ask questions in natural language and find granular answers in your documents using the latest QA models with the help of Haystack pipelines. Perform semantic search and retrieve ranked documents according to meaning, not just keywords! Make use of and compare the latest pre-trained transformer-based languages models like OpenAI’s GPT-3, BERT, RoBERTa, DPR, and more. Pick any Transformer model from Hugging Face's Model Hub, experiment, find the one that works. Use Haystack NLP components on top of Elasticsearch, OpenSearch, or plain SQL. Boost search performance with Pinecone, Milvus, FAISS, or Weaviate vector databases, and dense passage retrieval. -
21
Data Version Control
Git-based data version control for machine learning workflows
...By tracking dependencies between code, data, and parameters, the system ensures that only the necessary stages are re-run when changes occur. DVC also includes experiment tracking capabilities that allow users to compare different training runs. -
22
EasyR1
An Efficient, Scalable, Multi-Modality RL Training Framework
...It emphasizes memory-efficient training strategies so you can train long-context or reasoning-dense models on commodity GPUs. The framework is also organized to help you compare training strategies (e.g., pure SFT vs. preference optimization) so you can see what actually moves metrics in math, code, and multi-step reasoning. For teams exploring open reasoning models, EasyR1 provides an opinionated yet flexible path from dataset to deployable checkpoints. -
23
Agent Stack
Deploy and share agents with open infrastructure
...The platform supports agents built in frameworks like LangChain, CrewAI, etc., enabling them to be hosted, managed and shared through a unified interface. It also offers multi-model, multi-provider support (OpenAI, Anthropic, Gemini, IBM WatsonX, Ollama etc.), letting users compare performance and cost across models. For developers and organizations building AI-agent products or automations, Agent Stack gives a scaffold that handles the “plumbing”, so they can focus on logic and domain. -
24
Lightweight' GAN
Implementation of 'lightweight' GAN, proposed in ICLR 2021
...You should expect it to be 33% faster and save up to 40% memory. Aim is an open-source experiment tracker that logs your training runs, and enables a beautiful UI to compare them. -
25
CompareDir
Tool to Compare 2 directories and handle the files.
...It does not compute md5 sums because that would make it extremely slow. Mind you i use this regular for directories with 2000 photos. Based on Python, pygobject and gtk3. + Python-pillow if you want to compare 2 images. No installation: untar -xvzf CompareDir.tgz where you want and run.
