Highlights
- Pro
Starred repositories
Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
A collection of code snippets from the publication Daily Dose of Data Science on Substack: http://www.dailydoseofds.com/
Multi-agent systems, memory, planning, reasoning loops
Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
OpenResume is a powerful open-source resume builder and resume parser. https://open-resume.com/
The world's most flexible commerce platform for agents and developers
Set of tools to assess and improve LLM security.
Utilities intended for use with Llama models.
A curated list of resources dedicated to table recognition
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthr…
A high-throughput and memory-efficient inference and serving engine for LLMs
A curated list of papers about key information extraction.
A plugin for Strapi Headless CMS that provides navigation / menu builder feature with their possibility to control the audience and different output structure renderers like (flat, tree and RFR - r…
Interactive code examples for documentation, education and fun.
TableBank: A Benchmark Dataset for Table Detection and Recognition
Import flow for Excel (.xlsx) and CSV file with automated column matching and validation.
A Data Streaming Library for Efficient Neural Network Training
Ceph is a distributed object, block, and file storage platform
PaddlePaddle Docker images and K8s operators for PaddleOCR/Detection developers to use on public/private cloud.
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.