Stars
Series (one-dimensional) and dataframes (two-dimensional) for fast and elegant data exploration in Elixir
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
Get your documents ready for gen AI
A fast, helpful, and open-source document parser
Widelands is a free, open source real-time strategy game with singleplayer campaigns and a multiplayer mode. The game was inspired by Settlers II™ (© Bluebyte) but has significantly more variety an…
Semantic similarity testing for Elixir. Test LLM outputs, chatbots, and NLP in Elixir
Learn to build safety-critical systems in C. Prove first, code second.
Working memory for Claude Code - persistent context and multi-instance coordination
Embeddable RAG library for Elixir/Phoenix with agentic pipelines and dashboard
Simple, unified interface to multiple Generative AI providers
A tree-walking interpreter implemented in Rust. All keywords use "mano" slang, and error messages roast you.
🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.
A curated list of open source tools used in analytics platforms and data engineering ecosystem
Open-source data movement for ELT pipelines and AI agents — from APIs, databases & files to warehouses, lakes, and AI applications. Both self-hosted and Cloud.
💫 Toolkit to help you get started with Spec-Driven Development
Code to process many kinds of content by an author into an MCP server
Exercises for the book Artificial Intelligence: A Modern Approach
A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.
A single interface to use and evaluate different agent frameworks
⚡ Cloud-native, AI-powered, document processing pipelines on AWS.
A Python framework for multi-modal document understanding with Amazon Bedrock
ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction for flexible and powerful document workflows.
Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Toolkit for linearizing PDFs for LLM datasets/training
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
Implementation of Nougat Neural Optical Understanding for Academic Documents
A Comprehensive Toolkit for High-Quality PDF Content Extraction