The authentication glue you need.
- saml
- saml-idp
- saml-sp
- oauth2
47,133 repositories indexed
25–48 of 275 · Most stars
The authentication glue you need.
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
Prefect is a workflow orchestration framework for building resilient data pipelines in Python.
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
Universal LLM Deployment Engine with ML Compilation
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Translated100-Days-Of-ML-Code Chinese version
☁️ Build multimodal AI applications with cloud-native stack
Open standard for machine learning interoperability
Machine Learning Engineering Open Book
Turns Data and AI algorithms into production-ready web applications in no time.
The absolute trainer to light up AI agents.
An open source platform for Python in the browser. https://pyscript.net Docs: https://docs.pyscript.net/ Try it: https://pyscript.com/ Community: https://discord.gg/HxvBtukrg2
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.
Stable Diffusion with Core ML on Apple Silicon
Open-source State-of-the-art TTS model which runs on a CPU 😻
ARTEMIS turns natural-language instructions into reliable Android automation. It automates end-to-end workflows, captures logs, and integrates seamlessly with AI coding assistants such as Antigravity, Codex, and Claude Code. It also achieves 99%+ success rate on AndroidWorld Benchmark.
An orchestration platform for the development, production, and observation of data assets.
Machine learning, in numpy
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).
🦉 Data Versioning and ML Experiments
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
TranslatedDaidai Didi (带带弟弟, "take little brother along") general-purpose captcha recognition OCR, PyPI version