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
254
surfaced this week
209
created < 30d
Python
top language
1,242 repos
-
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
-
Official AMD catalog of AI agent skills. Empower your AI agents with AMD's optimized SW stack.
-
Gotta see 'em all! :)
-
A terminal IPython extension that adds Claude and Codex powered prompting
-
Python tools for Anki
-
A library of creative canvas components. Real HTML with WebGL effects running over it. React, Vue, Svelte, vanilla.
-
JSON:API Serializer and Query Handler for Elixir
-
A curated list of awesome Phoenix LiveView repositories, blog posts or other resources
-
A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.
-
WHATWG-compliant HTML parsing, mutation, and serialization for Python, powered by Rust's html5ever
-
Easily benchmark a Julia package over its commit history
-
ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.
-
Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 3.1 Pro, GPT 5.5, Grok 4.3, Claude model through API
-
Ibex — the JavaScript/TypeScript runtime extracted from Exact (LLP 0180). Hermes-based; consumed by Exact and Snapback.
-
Read, search, and edit AI dialogs stored as Jupyter notebooks, and convert them to and from LLM chat histories
-
Transcript-first terminal UI
-
Unsloth is a local UI for training and running Gemma 4, Qwen3.6, DeepSeek, Kimi, GLM and other models.
-
A hive mind communication platform
-
🛰 A loupe for your agents — a real-time Mission-Control dashboard and workspace for AI coding agents, across every provider and every project on your machine
-
ggml speech-to-text inference for 16+ model families
-
FrontierSWE is an ultra long-horizon coding agent benchmark that tests implementation, performance eng and ML research
-
Beautiful, Modern & Opinionated Linux
-
Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 3.1 Pro, GPT 5.5, Grok 4.3, Claude model through API
-
Our library for RL environments + evals
-
A delightful and complete interface to GitHub's amazing API
-
Python supercharged for the fastai library
-
The Hypothesis web-based annotation client with AI affordances added
-
A modern, lightweight syntax highlighter for python
-
Local-first release CLI tools: ship_bump, ship_pypi, ship_release_gh
-
Structured RAG: ingest, index, query
-
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
-
Useful skills for agents and claws.
-
ClawSweeper scans all issues and PRs and suggest what we can close, and why. It runs every PR / Issue once a week.
-
OpenHands Agent Canvas is a Open Source AI coding platform. Start locally, connect your tools, and automate workflows.
-
Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
-
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
-
Our library for RL environments + evals
-
SGLang is a high-performance serving framework for large language models and multimodal models.
-
You like pytorch? You like micrograd? You love tinygrad! ❤️
-
Incredibly fast JavaScript runtime, bundler, test runner, and package manager – all in one
-
OpenClaw docs + translation
-
Unsloth is a local UI for training and running Gemma 4, Qwen3.6, DeepSeek, Kimi, GLM and other models.
-
Open-source framework for the research and development of foundation models.
-
WebKit with patches
-
The Teleport Coding Challenge — contest hub at mazesofmenace.ai
-
The agent that grows with you