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
1,139 repos
-
Code for Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention
-
An NES CPU compiled into the weights of a stock Qwen3.5 model
-
Open-source Slack for your AI agent swarm
-
An open-source inference engine for AI functions in SQL
-
TabICLv2: An open tabular foundation model
-
Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.
-
scikit-learn: machine learning in Python
-
Dive into Deep Learning - Quarto rebuild
-
An interactive HTML pretty-printer for machine learning research in IPython notebooks.
-
Skills for agents
-
Complete logs of the experiments in the blog post 'LLMs can understand and write neural network weights'
-
An open atlas of simulation games, part by part: the mechanics they share, the combinations no one has built yet, and where AI can change how a game plays.
-
🧱 Experimental library for building inference engines
-
Open ML Compiler Foundation
-
liberating known unknowns
-
Prototyping on AI Foundry's ET-SoC-1 (1088-core RISC-V): sys_emu setup, hello world, tensor-unit matmul FLOPs/W vs A100
-
Lectures for INFO8006 Introduction to Artificial Intelligence, ULiège
-
Environments by the Prime Intellect Research Team
-
A high-throughput and memory-efficient inference and serving engine for LLMs
-
An LLM-powered agent for Datasette
-
Tensors and Dynamic neural networks in Python with strong GPU acceleration
-
Access large language models from the command-line
-
A clean, modular SDK for building AI agents with OpenHands V1.
-
Apps that live inside Datasette
-
Our library for RL environments + evals
-
Open-source framework for the research and development of foundation models.
-
Voice-agent implementations of Rory, the Acme Energy utility billing agent from the VAmoS Energy benchmark
-
A framework for few-shot evaluation of language models.
-
Personal email archive with SQLite+FTS5 full-text search and MCP server for LLM access. Part of the *-memex ecosystem.
-
Learn harness engineering by building Claude Code from scratch. Free, open-source course: 8 articles, 6 videos, 1 codebase.
-
DODS study: chatbot vs workshop as elicitation formats (referia reconstruction of An elicitation fallacy?)
-
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
-
Linguine data oriented architecture python framework.
-
A benchmark for evaluating AI agents on realistic business workflows
-
Benchmarks scikit-learn-compatible machine learning libraries
-
Reviewing framework initially created for reviewing REF papers then heavily modified.
-
Skills for the Gemini API, SDK and model/agent interactions
-
Prebuilt Indexes for Anserini and Pyserini
-
Basic computer music utilities for Python / NumPy
-
SGLang is a high-performance serving framework for large language models and multimodal models.
-
Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.
-
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
-
Train transformer language models with reinforcement learning.
-
Python helpers to limit the number of threads used in native libraries that handle their own internal threadpool (BLAS and OpenMP implementations)
-
Dion optimizer algorithm
-
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.
-
Public repository for Agent Skills
-
Centralized network visibility and continuous asset discovery. Monitor devices, detect change, and stay aware across distributed networks.