Search awesome repositories

Easiest and laziest way for building multi-agent LLMs applications.

Developer-friendly incident response with brilliant Slack integration

The free and open-source Download Manager written in pure Python

Simple RL training for reasoning

A library for mechanistic interpretability of GPT-style language models

LeanCTX — Context Gateway for AI Systems. Control what your AI can see. Open-source Engine for context selection, supported controls, and evidence.

VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

3D visualization and mesh analysis for science and engineering

The Pants Build System

[ICML'26] SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

A flexible, high-performance 3D simulator for Embodied AI research.

Fast Python Collaborative Filtering for Implicit Feedback Datasets

Python library for backtesting trading strategies & analyzing financial markets (formerly pythalesians)

Trade autonomously on Polymarket using AI Agents

Open-source security automation platform for teams and AI agents

🤖 Build voice-based LLM agents. Modular + open source.

Fast and powerful SSL/TLS scanning library.

Vizro is a low-code toolkit for building high-quality data visualization apps.

Build a full-featured home server or NAS replacement with an Ubuntu box and this playbook.

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.

The Harness of Harnesses: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.

Tools for managing DNS across multiple providers

a library for audio and music analysis

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

A collection of scientific methods, processes, algorithms, and systems to build stories & models.

agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes and reinforcement learning (RL).

A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.)

Open-source multimodal retrieval engine (Morphik Core)

Power CLI and Workflow manager for LLMs (core package)