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
51 repos
-
AI constitutions and model specs, in date order, with quotes from studies on what generalises
-
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
-
*Principles of Computer Music* is a textbook that teaches music computing from a computer science perspective in Python
-
Open-source skills for designing and reviewing software with AI agents
-
Rails as a specification; the deployment target is a build flag
-
Rails as a specification; the deployment target is a build flag
-
Automatic formal verification for warp-specialized GPU kernels.
-
Python SDK for ProgramAsWeights — compile natural language specs into neural programs that run locally
-
Code for the AgentTime experiments: duration following, forecasting and retrospective forks
-
Task output grading with declarative verifier specifications and structured verdicts
-
A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models
-
Docker Sandbox Kit Specification v3 - the kit descriptor grammar, the OCI artifact, the build frontend, and the conformance suites
-
★ 1.7k ai-evals-course/evals-skillsSkills that guide AI coding agents to help you build product-specific AI evals.
-
Compile natural language specs into small neural functions on a single GPU.
-
Keep specialist bots, their memory, and their conversations together across projects.
-
Interactive image Fourier transform visualization with phase-aware previews and spectral painting
-
Question video transcripts, inspect the evidence, and organize clips from the terminal.
-
Dynamic OpenAPI and discovery spec client for Python — turn any API spec into a fully-typed async client with attribute chaining, streaming, and file uploads
-
AXorcist • Swift wrapper for macOS Accessibility—chainable, fuzzy-matched queries that read, click, and inspect any UI. The power of Swift compels your UI to obey!
-
In-depth analysis of AI agent transcripts.
-
Evaluation harness and tooling for measuring model compliance with the OpenAI Model Spec.
-
Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)
-
Open format for specifying structured assumptions and requirements about code.
-
Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
-
Bioinformatics pipeline for selecting patient-specific cancer neoantigen vaccines
-
🌊 FFT so pretty, your ears will be jealous. See your sound—spectrograms, mel, chroma, and more.
-
💫 Toolkit to help you get started with SDD or any other process!
-
Offline compatibility inspector for mocking OpenClaw and testing plugins 💊
-
Speculative programmatic tool calling (sPTC) for harnesses like RLM, CodeAct, etc.
-
A curated list of awesome video frameworks, libraries, specifications and software.
-
Exo is an agent + harness architecture that is fully recursive, able to safely edit all aspects of itself at runtime to get better at your tasks.
-
Interactive 3D visualization of pinhole-camera perspective projection.
-
Automatic integrate all Xiaomi devices to HomeAssistant via miot-spec, support Wi-Fi, BLE, ZigBee devices. 小米米家智能家居设备接入Hass集成
-
vLLM 0.25.1 serving stack for poolside/Laguna-S-2.1-NVFP4 with DFlash speculative decoding — DGX Spark & RTX 6000 PRO
-
RFC document, tooling and other content related to the array API standard
-
Set up your GitHub Actions workflow with a specific version of https://docs.astral.sh/uv/
-
VibePrompter is a desktop app for visually designing process flows with typed inputs/outputs, validating connections, and exporting diagrams as JSON or LLM-ready prompts. Built with Python and pywebview, it provides a native, lightweight interface for turning workflows into implementation-ready specifications.
-
liquid-spec is a test suite for the Liquid language.
-
A Liquid template engine, 100% vibe coded by Claude Code against liquid-spec
-
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
-
Cursor plugin specification and official plugins
-
A PyTorch native library for training speculative decoding models
-
Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights.
-
Skills that guide AI coding agents to help you build product-specific AI evals.
-
DFlash: Block Diffusion for Flash Speculative Decoding
-
Run Inspect AI evals in the cloud
-
Show usage stats for OpenAI Codex and Claude Code, without having to login.
-
A public-domain dataset of prompts and scenarios for evaluating compliance with the OpenAI Model Spec.
-
A modern library to swizzle elegantly in Swift.