SQLite Graph Extension

Kimi CLI is your next CLI agent.

🎒 Token-Oriented Object Notation (TOON) – JSON for LLM prompts at half the tokens. Spec, benchmarks & TypeScript implementation.

Grab any element on in your app and give it to Cursor, Claude Code, etc

Machine Learning Foundations: Linear Algebra, Calculus, Statistics & Computer Science

Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

This course is designed to guide beginners through the exciting world of Edge AI, covering fundamental concepts, popular models, inference techniques, device-specific applications, model optimizati…

The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.

ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)

⚡ A Fast, Extensible Progress Bar for Python and CLI

The most cost-effective, highest performance AI voice agent possible today

DOMPurify - a DOM-only, super-fast, uber-tolerant XSS sanitizer for HTML, MathML and SVG. DOMPurify works with a secure default, but offers a lot of configurability and hooks. Demo:

Rich is a Python library for rich text and beautiful formatting in the terminal.

The production agentic context stack. Data streaming + knowledge graphs + vector search + LLM orchestration. All in a single deployment for self hosting, BYOC, or cloud.

Notion-style WYSIWYG editor with AI-powered autocompletion.

An in-depth book and reference on building agentic systems like Claude Code

[EMNLP'25 findings] This is the official repo for the paper, HiRAG: Retrieval-Augmented Generation with Hierarchical Knowledge.

Optimize prompts, code, and more with AI-powered Reflective Text Evolution

A concise, beginner-friendly introduction to the core ideas of linear algebra.

🌵 Mobile first open-source RSVP platform. Alternative for meetup.com & eventbrite and partiful for small companies and groups.

🧠 Cognitive load is what matters

DSPy: The framework for programming—not prompting—language models

Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs

The LLM Evaluation Framework

A collection of methods, techniques, and best practices to improve Retrieval-Augmented Generation (RAG) systems for better accuracy, efficiency, and reliability.

Supercharge Your LLM Application Evaluations 🚀

This repository delivers end-to-end, code-first tutorials covering every layer of production-grade GenAI agents, guiding you from spark to scale with proven patterns and reusable blueprints for re…