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.
2,991
repos tracked
117
surfaced this week
232
created < 30d
Python
top language
47 repos
-
Mathematical foundations, information-theoretic methods, optimization algorithms, and research papers on Kelly wagering, risk, and betting markets.
-
Information, Energy and Intelligence
-
Emacs major mode for Bend 2 (bendlang/bend): syntax highlighting, indentation, Eglot formatting, and Flymake diagnostics.
-
Convert your data to Markdown files you can use in Obsidian. Works with Apple Notes, OneNote, Evernote, Notion, Google Keep, and many other formats.
-
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
-
Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.
-
Dumps umamusume veteran list (and more) in a JSON format
-
Anserini is a Lucene toolkit for reproducible information retrieval research
-
A CLI tool for transforming arbitrary text into Biblical scripture format across 15 translation styles, including 8 English Bible translations and 7 historical languages with original script output.
-
A GLSL type checker, code formatter, and minifier for WebGL
-
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
-
A low-level, lightweight protocol buffers implementation in JavaScript.
-
Faster, better zipper: a compression-format research workbench
-
RankLLM is a Python toolkit for reproducible information retrieval research using rerankers, with a focus on listwise reranking.
-
The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.
-
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
-
Minimal Jupyter protocol commons: wire-format sessions and kernel-client call conventions
-
Generative Representational Instruction Tuning
-
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.
-
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
-
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
-
Experimental single-channel Slack–Zulip bridge with threads, edits, reactions, images, and formatting.
-
JAX/Equinox implementation of ProteinMPNN and LigandMPNN for protein sequence design
-
OnCo: total information dominance on cancer. A public, cited knowledge graph of oncology with a website, JSON API, MCP server and CLI: one page per cancer, treatment, target, trial, institution, person and idea.
-
Attentiophagēs, a class of digital entities designed to exist sustainably within the modern information ecosystem.
-
Convert sessions across harnesses to a unified trajectory format - designed to be consumed by agents (e.g. for memory formation, dreaming, search)
-
A trajectory visualization demo using Harbor Task format and ATIF Agent Trajectory visualization.
-
Open format for specifying structured assumptions and requirements about code.
-
A rewrite of the original good regulator theorem paper with information theory.
-
Bioinformatics pipeline for selecting patient-specific cancer neoantigen vaccines
-
Plättli is an opinionated dataformat for logging a series of metrics
-
DimCut is a novel editing interaction design that folds the 1D timeline into multiple rows, integrating text, audio, and visuals — multidimensional information at a glance.
-
Faster, better zipper: a compression-format research workbench
-
A new open-source format for interactive video on the web, with a built-in state machine, frame-accurate transitions, and packed-alpha transparency.
-
An extremely fast Python linter and code formatter, written in Rust.
-
The open-source AI workbench for scientific research
-
★ 132 prinz-ai/prinzbenchprinzbench is a private benchmark that ranks LLMs based on their ability to conduct legal research and analysis and locate obscure publicly available information online.
-
universal text transformation, translation, mutation, encoding/decoding, and promptcrafting
-
Tongyi Deep Research, the Leading Open-source Deep Research Agent
-
Open Source AI Platform - AI Chat with advanced features that works with every LLM
-
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
-
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]
-
An extremely fast Python linter and code formatter, written in Rust.
-
Quantum information game code
-
Online learning of rotation matrices: three ways to insert information (GD, projected GD, geodesic), with convergence rates 1 : 1.5 : 2
-
Lens is a 3.8B-parameter text-to-image diffusion model that achieves quality competitive with and in several cases surpassing models like FLUX and SD3, while requiring significantly less training compute. Key ideas include maximizing data information density per batch and accelerating convergence.