Search awesome repositories

Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning.

Django-environ allows you to utilize 12factor inspired environment variables to configure your Django application.

Graphical client for the Soulseek peer-to-peer network

A Python Finance Library that focuses on the pricing and risk-management of Financial Derivatives, including fixed-income, equity, FX and credit derivatives.

Improved file parsing for LLM’s

[NeurIPS 2026] DataFlex: A Unified Benchmark and Evaluation Platform for Data-Centric Training of Large Language Models

Foundation Architecture for (M)LLMs

Model-rocketry aerodynamics and trajectory simulation software

a delightful machine learning tool that allows you to train, test, and use models without writing code

[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

Source code for Gramps Genealogical program

TensorFlow Reinforcement Learning

Security scanner for AI agents, MCP servers and agent skills.

Postgres extension for vector search (DiskANN), complements pgvector for performance and scale. Postgres OSS licensed.

A GUI front-end for youtube-dl, partly based on youtube-dl-gui and written in Python 3 / Gtk 3

FlameScope is a visualization tool for exploring different time ranges as Flame Graphs.

Reverse engineering tool for Linux

Skills, MCP servers, Custom Agents, Agents.md for SDKs to ground Coding Agents

Your Bambu Lab. No Cloud. Your Rules. Self-hosted command center for Bambu Lab — from one A1 to an entire print farm.

SABnzbd - The automated Usenet download tool

Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.

A developer reference project for creating Retrieval Augmented Generation (RAG) chatbots on Windows using TensorRT-LLM

A collection of themes/skins for 50 selfhosted apps!

A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 37.3% tasks (pass@1) in SWE-bench lite and 46.2% tasks (pass@1) in SWE-bench verified with each task costs less than $0.7.

AI Multi-Agent Framework in .NET

No description.

Video Editor for Linux

Implementation for MatMul-free LM.

High performance, easy-to-use, and scalable machine learning (ML) package, including linear model (LR), factorization machines (FM), and field-aware factorization machines (FFM) for Python and CLI interface.

High performance datastore for time series and tick data