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.
653
repos tracked
153
surfaced this week
141
created < 30d
Python
top language
233 repos
-
Official Repo: AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery
-
The fastest way to create an HTML app
-
OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
-
slime is an LLM post-training framework for RL Scaling.
-
A high-throughput and memory-efficient inference and serving engine for LLMs
-
All Hands AI OpenHands Self-hosted Cloud
-
Agentic RL Training at Scale
-
OpenHands Agent Canvas is a Open Source AI coding platform. Start locally, connect your tools, and automate workflows.
-
Textbook on reinforcement learning from human feedback
-
Show usage stats for OpenAI Codex and Claude Code, without having to login.
-
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
-
The Teleport Coding Challenge — contest hub at mazesofmenace.ai
-
The agent that grows with you
-
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
-
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI, VSCode Agent, Warp.dev, Windsurf, Xcode, Z.ai Code, Dia & v0. (And other Open Sourced) System Prompts, Internal Tools & AI Models
-
Experimental mini python jupyter kernel
-
A clean, modular SDK for building AI agents with OpenHands V1.
-
Fast and memory-efficient exact attention
-
Port of OpenAI's Whisper model in C/C++
-
Training open models for agentic phone use with real-app and mock-app environments.
-
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
-
Stable Audio LoRA Trainer of salty goodness
-
One policy. Any motion. Train universal whole-body tracking in mjlab—swap clips, not checkpoints.
-
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
-
Google Workspace in your terminal.
-
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
-
Puffing up reinforcement learning
-
Python API for ripgrep-style walking and search
-
Garry's Opinionated OpenClaw/Hermes Agent Brain
-
Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.
-
An interface library for RL post training with environments.
-
macOS video editor built for AI
-
The open-source AI voice studio. Clone, dictate, create.
-
A tool for creating and running Linux containers using lightweight virtual machines on a Mac. It is written in Swift, and optimized for Apple silicon.
-
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.
-
Public Coworld CLI, Python helpers, manifest schemas, runner tooling, and reference worlds.
-
Ongoing research training transformer models at scale
-
[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
-
World's first open-source, agentic video production system. 12 pipelines, 52 tools, 500+ agent skills. Turn your AI coding assistant into a full video production studio.
-
An open source implementation of CLIP.
-
Environments by the Prime Intellect Research Team
-
Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.
-
Point at any URL/YouTube/Podcast or file. Get the gist. CLI and Chrome Extension.
-
Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.
-
Distributed High-Performance Symbolic Regression in Julia