OPAL: a reactive optimizer. A coding agent rewrites the optimizer while your model trains.
- deep-learning
- llm-agents
- optimizer
- pytorch
Repository Index
80,339 visible repositories in the index
241–264 of 309 · Most stars
pure-Python (Numpy optional) 3D coordinate conversions for geospace ecef enu eci
- coordinate-conversion
- coordinate-transformation
- geodesy
TranslatedOne zero-dependency MCP gateway CLI for every server and agent skill. Token optimization, tool discovery and context compression: 71,929 -> 581 tokens (-99.2%, measured), schemas stay out of context. One config for Claude Code, Codex, Cursor, every agent. 561KB, pure Python. | Zero-dependency CLI: manages all MCP tools and skills, and tool discovery saves 99.2% of tokens.
- mcp
- claude
- claude-code
- cursor
A model generator for energy system modelling and optimisation (LP/MILP).
- energy
- energy-system
- modelling
- modelling-framework
Iterative Linear Quadratic Regulator with auto-differentiatiable dynamics models
- trajectory-optimization
- differential-dynamic-programming
- theano
- dynamics-models
Hyperparameter optimization and feature selection for scikit-learn using evolutionary algorithms. A modern alternative to GridSearchCV and RandomizedSearchCV.
An extension for Inkscape that makes it easier to draw optical diagrams.
- inkscape-extension
- optics-simulation
- python
- optics
Find, verify and organize your game library. Native Windows and Docker, DAT checks, ROM Hub plugins, and optional RomM/Cartridge integration.
Self-improving code for any git repo: give it a measurable goal, a coding agent (Claude Code or Aider) proposes changes, the kernel scores them, keeps winners and rolls back failures. Open-source AlphaEvolve / FunSearch-style evolution loop, sandboxed, with an auditable ledger.
- agent-harness
- ai-agents
- aider
- alphaevolve
Official repository for the paper “RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution”
An autonomous agent that profiles, optimizes, and validates AI training code.
Comi (可米) — a tiny 3D plush desktop companion for macOS and Windows: hops around, waves, claps her clapperboard and keeps you company while you work. Optional local status bridge for DSH / ZCode / Claude Code / Cursor / OpenCode / Codex. Zero dependencies.
Maze Applied Reinforcement Learning Framework
OpenAeroStruct is a lightweight tool that performs aerostructural optimization using OpenMDAO.
- openmdao
- optimization
- aerodynamics
- open-source
Descriptor computation(chemistry) and (optional) storage for machine learning
One-link downloader for the Mac (videos, documents, images, articles, web pages), with optional automatic YouTube monitoring that translates and subtitles new videos.
Bayesian Optimization using GPflow
- gpflow
- bayesian-optimization
- machine-learning
- hyperparameter-optimization
Free global SEO/GEO skill for Claude Code, Codex & 10 agent hosts — 18 market portals, 56 stdlib scripts, 672 golden tests, self-update intel loop, monitoring daemon, CI gates. Multilingual GEO, pSEO, CWV, penalty recovery.
- agent-skills
- ai-seo
- answer-engine-optimization
- backlinks
TOMC Memory: CPU context compression and task memory for Codex, Claude Code, Cursor, TRAE, WorkBuddy and other MCP clients.
- agent-memory
- claude-code
- codex
- context-compression
zoofs is a python library for performing feature selection using a variety of nature-inspired wrapper algorithms. The algorithms range from swarm-intelligence to physics-based to Evolutionary. It's easy to use , flexible and powerful tool to reduce your feature size.
- machine-learning
- python
- evolutionary-algorithms
- genetic-algorithm
Trading Environment(OpenAI Gym) + PPO(TensorForce)
- ppo
- proximal-policy-optimization
- tensorforce
- trading
Ankh: Optimized Protein Language Model
A high-performance, general-purpose toolkit for versatile robotic tasks.
- inverse-kinematics
- model-predictive-control
- motion-planning
- optimization
Open source compiler for your whole ML repo (support python, CUDA C/C++) into sass and cuda binary (which are closed sourced by Nvidia); 3-40% faster than Openai Triton for Neural Network (primarily LLM) based training/inferencing
- compiler
- compiler-backend
- compiler-optimization
- gpu-acceleration