Python

Spectrum

https://github.com/QuixiAI/spectrum This repository contains the implementation of Spectrum, as detailed in the paper Spectrum: Targeted Training on Signal to Noise Ratio.

https://github.com/Lightning-AI/torchmetrics Torchmetrics - Machine learning metrics for distributed, scalable PyTorch applications. 🔗 https://lightning.ai/docs/torchmetrics/

🔧🔗https://github.com/google/langfun

OO for LLMs

A feature-rich command-line audio/video downloader

LLMs from scratch

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step 🔧🔗https://github.com/rasbt/LLMs-from-scratch

MLX-lm

🔧🔗https://github.com/ml-explore/mlx-lm Run LLMs with MLX

🔧🔗https://github.com/mem0ai/mem0 Memory for AI Agents; SOTA in AI Agent Memory; Announcing OpenMemory MCP - local and secure memory management.

🔧🔗https://github.com/modelscope/modelscope-agent

ModelScope-Agent: An agent framework connecting models in ModelScope with the world

https://github.com/Upsonic/Upsonic Self-Driven Autonomous Python Libraries

🔧🔗https://github.com/leon-ai/leon

🧠 Leon is your open-source personal assistant.

🔗https://getleon.ai

https://github.com/netbox-community/netbox.git

MLX

🔧🔗https://github.com/ml-explore/mlx An array framework for Apple silicon

🔧🔗https://github.com/meta-llama/llama-stack-client-python

Python SDK for Llama Stack

🔧🔗https://github.com/google/tensorstore Library for reading and writing large multi-dimensional arrays.

🔧🔗https://github.com/google/grain Library for reading and processing ML training data.

Docker Official Image packaging for Python

🔧🔗https://github.com/docker-library/python

https://github.com/element-hq/synapse

Synapse: Matrix homeserver written in Python/Twisted.

🔧🔗https://github.com/lmstudio-ai/venvstacks

Virtual environment stacks for Python

🔧🔗https://github.com/tensorzero/llmgym LLM Gym is a unified environment interface for developing and benchmarking LLM applications that learn from feedback. Think gym for LLM agents.

As the space of benchmar

🔧🔗https://github.com/bytedance/deer-flow DeerFlow is a community-driven framework for Deep Research, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.