Sign in

Repository Index

142,187 visible repositories in the index

Tags: All Tags
Tags

A repository shows when it has any selected Tag.

Filters

Filters

Clear all filters

25–48 of 533 · Most stars

MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.

  • agent
  • browsecomp
  • deep-research
  • futurex

The Easel Javascript library provides a full, hierarchical display list, a core interaction model, and helper classes to make working with the HTML5 Canvas element much easier.

[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

A lightweight, object-oriented finite state machine implementation in Python with many extensions

  • python
  • state-machine
  • nested-states
  • hierarchical-state-machine

Numenta Platform for Intelligent Computing is an implementation of Hierarchical Temporal Memory (HTM), a theory of intelligence based strictly on the neuroscience of the neocortex.

TranslatedAn innovative cross-platform slacking-off tool that supports slacking-off modes for novels, stocks, web pages, videos, live streams, PDFs, games, and more. A must-have tool for office workers, it makes work feel much more relaxed and keeps you away from the ICU.

In this noteboook I will create a complete process for predicting stock price movements. Follow along and we will achieve some pretty good results. For that purpose we will use a Generative Adversarial Network (GAN) with LSTM, a type of Recurrent Neural Network, as generator, and a Convolutional Neural Network, CNN, as a discriminator. We use LSTM for the obvious reason that we are trying to predict time series data. Why we use GAN and specifically CNN as a discriminator? That is a good question: there are special sections on that later.

Kodezi Chronos is a debugging-first language model that achieves state-of-the-art results on SWE-bench Lite (80.33%) and 67% real-world fix accuracy, over six times better than GPT-4. Built with Adaptive Graph-Guided Retrieval and Persistent Debug Memory. Model available Q1 2026 via Kodezi OS.

:pencil: Markdown code for lots of small badges :ribbon: :pushpin: (shields.io, forthebadge.com etc) :sunglasses:. Contributions are welcome! Please add yours!

  • forthebadge
  • badges
  • markdown
  • markdown-cheatsheet