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.
1,506
repos tracked
261
surfaced this week
215
created < 30d
Python
top language
40 repos
-
Python-native skills system
-
👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.
-
Fullstack app framework for web, desktop, and mobile.
-
👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.
-
A markdown native slides tool for academics building with agents.
-
Local AI, native to your Mac. Chat, serve, monitor, and connect MLX models from one macOS app.
-
Native macOS and iOS audiobook highlighting with on-device alignment, Readwise, and Marginalia.
-
AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and support for your own .pptx templates. · by Hugo He
-
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.
-
Cloud-agnostic managed Kubernetes
-
Native-Swift game-streaming client for Sunshine/Moonlight hosts (macOS, Apple Silicon)
-
A PyTorch native platform for training generative AI models
-
Python-first native robotics simulation and reinforcement-learning environments
-
PyTorch native quantization and sparsity for training and inference
-
A Swifty take on Commander.js and alternative to Swift's ArgumentParser.
-
Compact and Agent-Native MoE Training System
-
Command & Conquer Generals: Zero Hour running natively on macOS, iPhone & iPad — real engine (EA GPL v3 source, via GeneralsX), DXVK/MoltenVK renderer, RTS touch controls. No game assets included.
-
Python helpers to limit the number of threads used in native libraries that handle their own internal threadpool (BLAS and OpenMP implementations)
-
Toolkit for building native desktop apps
-
A native macOS UI for Apple's platform
-
Fast, powerful, git-native ticket tracking in a single bash script. Dependency graphs, priority levels, zero setup.
-
Open-source control plane for AI coding agents — run, monitor & orchestrate dozens of parallel Claude Code, Codex & Gemini sessions from one web dashboard or your phone. Self-healing, single-file, tmux-native.
-
Bidirectional, stateful control of Logic Pro from AI assistants. 8 dispatcher tools + 7 resources across 5 native macOS channels.
-
Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. A local Wispr Flow alternative. ⭐ helps a ton :) Windows & iOS waitlist open. Linux soon.
-
A PyTorch native library for training speculative decoding models
-
Official implementation of paper "VLM³: Vision Language Models Are Native 3D Learners".
-
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
-
The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/
-
Native macOS PDF presenter with a real second-screen / presenter view (Keynote-style) for Beamer and plain PDF decks.
-
AI-native control plane for Mimestream on macOS.
-
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]
-
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]
-
Fork of Apache MXNet 2.0 — runs legacy MXNet code on CUDA 13 / Blackwell (sm_120) GPUs and native Apple Silicon CPU.
-
Native Agent CLIs manager for macOS. Ghostty Terminals + Codex App Features/UX = Ghostex! Embedded browser & IDE. Strong agents support.
-
Lobster is a Openclaw-native workflow shell: a typed, local-first “macro engine” that turns skills/tools into composable pipelines and safe automations—and lets Openclaw call those workflows in one step.
-
A Mac-compatible AI partner with memory. — local computer access, browser control, IM channels, MCP-native. Built on Shannon.
-
Open-source LLM-based ASR model family for Chinese, dialect, accent, and multilingual speech, with FunASR, vLLM, streaming, and llama.cpp runtimes.
-
KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.
-
Add virtual datarooms, secure sharing, document tracking, and workflow automation on top of your storage (Nextcloud, Google Drive, Dropbox). Self-hosted DocSend alternative.
-
High-quality search for AI-native applications.