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.
2,235
repos tracked
175
surfaced this week
194
created < 30d
Python
top language
775 repos
-
A self-hosted drop-in replacement for TypeSafe's jev, powered by GliFormer.
-
Proxy Policy Steering: inference-time adaptation for robotics foundation models
-
Batched single-token choice inference for open language models, compatible with TypeSafe
-
Evidence-backed, model-agnostic runtime contracts for physical agents
-
Generic floating-point types in Python
-
Generic floating-point types in Python
-
tiny Jev-like model built on top of Qwen2.5-0.5B you can train and run on your MacBook
-
🚀 The fast, Pythonic way to build MCP servers and clients.
-
Raw results of solver benchmark campaigns run with bodono/solver_benchmarks
-
Jev-compatible API endpoint based on open models (prefill-only)
-
A Python library for running thousands of MuJoCo simulations in parallel on CPU
-
Hexapod walker: STS3215 prototype, RL training orchestrator (CoreWeave), MuJoCo sim, robot control
-
Pyskills for Answer.AI coding sessions: skill text and companion tooling for clikernel
-
Solver benchmarking tools
-
A high-throughput and memory-efficient inference and serving engine for LLMs
-
A lightweight execution guard for running LLM-generated Python in a normal Python process
-
Verified Line-Addressed File Editor
-
You like pytorch? You like micrograd? You love tinygrad! ❤️
-
Open-source framework for the research and development of foundation models.
-
JAX/Equinox implementation of ProteinMPNN and LigandMPNN for protein sequence design
-
An open-source execution engine for AI-SQL and LLM-powered dataflow
-
Environments by the Prime Intellect Research Team
-
Home robot ++
-
High-Performance Symbolic Regression in Python and Julia
-
Python helpers to limit the number of threads used in native libraries that handle their own internal threadpool (BLAS and OpenMP implementations)
-
Public registry for OpenHands extensions.
-
Data and software for building the ACL Anthology.
-
Open Machine Learning Compiler Framework
-
A clean, modular SDK for building AI agents with OpenHands V1.
-
OpenHands automation service
-
Agentic RL Training at Scale
-
SGLang is a high-performance serving framework for large language models and multimodal models.
-
Our library for RL environments + evals
-
Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.
-
A library of experiments using frontier LLMs/VLMs for robotics tasks, currently focusing on GPT-6 Astra.
-
Programmable chat templates for LLM training and inference.
-
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
-
Mac OS X and Linux optimal configuration files
-
Local typed decisions, contrastive data curation, and model evaluation.
-
TabICLv2: An open tabular foundation model
-
Manipulating RLHF corpus to reduce sycophancy outcomes
-
Autonomous RL research loop for lukas/hexapod: fleet launcher, watcher, status board, MCP server, metaagent reviewer
-
Private code/config backup (secrets & large artifacts excluded)
-
Benchmarks scikit-learn-compatible machine learning libraries