⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA
Repository Index
98,836 visible repositories in the index
49–72 of 284 · Most stars
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.
A hardware-agnostic SDK for optimization problems: define a problem once, then lower it to any quantum or classical solver
- constraint-programming
- quantum-computing
- quadratic-programming
High-performance TensorFlow library for quantitative finance.
Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.
- ai
- chain-of-thought
- collaboration
- dataset-generation
Silky smooth profiling for Django
- debug-toolbar
- debugging
- developer-tools
- django
Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0
- multidiffusion
- stable-diffusion-webui-plugin
- large-image
- stable-diffusion
MlFinLab helps portfolio managers and traders who want to leverage the power of machine learning by providing reproducible, interpretable, and easy to use tools.
- machine-learning
- trading
- investing
- research
An AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails and management. Optimizes Agent & Tool calling, and supports plugins.
- agents
- ai
- api-gateway
- asyncio
Python toolkit for quantitative finance: stock analysis, technical indicators, strategy backtesting, portfolio optimization, and financial modeling.
- stocks
- stock-market
- finance
- python
Optimizing inference proxy for LLMs
- agent
- agentic-ai
- agentic-workflow
- agents
AdalFlow: The library to build & auto-optimize LLM applications.
A Python toolbox for performing gradient-free optimization
:smiley_cat: A tool designed to shorten steps needed to import and optimize models into VRChat. Compatible models are: MMD, XNALara, Mixamo, DAZ/Poser, Blender Rigify, Sims 2, Motion Builder, 3DS Max and potentially more
- mmd
- vrchat
- blender
- mixamo
Task-Aware Agent-driven Prompt Optimization Framework
Cascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop.
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
- pytorch
- reinforcement-learning
- deep-learning
- deep-reinforcement-learning
Python Kalman filtering and optimal estimation library. Implements Kalman filter, particle filter, Extended Kalman filter, Unscented Kalman filter, g-h (alpha-beta), least squares, H Infinity, smoothers, and more. Has companion book 'Kalman and Bayesian Filters in Python'.
A bitmap programming font optimized for coziness 💜
- font
- bitmap-font
- powerline-font
- programming-font
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.
- large-language-models
- prompt-optimization
- compound-systems
- textual-gradients
PennyLane is an open-source quantum software platform for quantum computing, quantum machine learning, and quantum chemistry. Create meaningful quantum algorithms, from inspiration to implementation.
🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools
The next generation deep reinforcement learning tookit
- reinforcement-learning
- transfer-learning
- deep-learning
Insane(ly slow but wicked good) PNG image optimization
- png
- png-compression
- compression
- image-quality