Dev
GitHub repos gaining traction - what high-signal users are starring and what's climbing the board, captured daily and enriched from GitHub. Raw material for spotting new tech and patterns worth building on.
3,195
repos tracked
105
surfaced this week
193
created < 30d
Python
top language
20 repos
-
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
-
Splitting Conic Solver
-
Python interface for SCS
-
Mathematical foundations, information-theoretic methods, optimization algorithms, and research papers on Kelly wagering, risk, and betting markets.
-
The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Find what you want without reading the repo, then check you built what you meant — blast radius, tests-to-run, quality deltas. Signatures at 74.7% fewer bytes than bodies; every guess labelled, every loss published. Paddle out with a map.
-
Differentiable convex optimization layers
-
Nonlinear optimisation (root-finding, least squares, ...) in JAX+Equinox. https://docs.kidger.site/optimistix/
-
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
-
Official Code Repository for the ICLR 2026 Paper "Human Behavior Atlas: Benchmarking Unified Psychological and Social Behavior Understanding" & ICML 2026 Paper "Omnisapiens: A foundation model for social behavior processing via heterogeneity-aware relative policy optimization"
-
Sub-real-time MiniMax H3 on Hopper: 13.506 s for a 14.375 s 768p video with audio on 8xH100. Four runtime patches removing 9.72 s of non-model overhead from FastVideo.
-
The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.
-
Control-data flow separation for stable prompt optimization in multi-agent LLM systems
-
Playing Prince of Persia (1989) using Reinforcement Learning.
-
Interactive computer vision, machine learning, and optimization visualizations by Kosta Derpanis
-
AIDE: an LLM agent for machine learning engineering - the research Weco grew out of. Referenced in OpenAI MLE-bench.
-
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
-
Optimize prompts, code, and more with AI-powered Reflective Optimization
-
TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.
-
Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation preconditioner and more)
-
Production-Grade Autoresearch. Ideal for agent harness engineering, prompt engineering, ML model development, GPU kernels, and other optimizable code.