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.
2,235
repos tracked
175
surfaced this week
194
created < 30d
Python
top language
142 repos
-
Hexapod walker: STS3215 prototype, RL training orchestrator (CoreWeave), MuJoCo sim, robot control
-
A spy satellite simulator in your browser, except the data is real. Live open source spatial intelligence on a photorealistic 3D globe.
-
Agentic RL Training at Scale
-
GTSAM is a library of C++ classes that implement smoothing and mapping (SAM) in robotics and vision, using factor graphs and Bayes networks as the underlying computing paradigm rather than sparse matrices.
-
Our library for RL environments + evals
-
Manipulating RLHF corpus to reduce sycophancy outcomes
-
Autonomous RL research loop for lukas/hexapod: fleet launcher, watcher, status board, MCP server, metaagent reviewer
-
Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research
-
Implement a reasoning LLM in PyTorch from scratch, step by step
-
Harbor is a framework for running agent evaluations and creating and using RL environments.
-
Official CLI and Python SDK for Prime Intellect - access GPU compute, remote sandboxes, RL environments, and distributed training infrastructure for AI development at scale.
-
Online Goal-Conditioned Reinforcement Learning in JAX. ICLR 2025 Spotlight.
-
Point at any URL/YouTube/Podcast or file. Get the gist. CLI and Chrome Extension.
-
Complete Control and Automation for Seestar S50
-
Train transformer language models with reinforcement learning.
-
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
-
RewardBench: the first evaluation tool for reward models.
-
Hyprland is an independent, highly customizable, dynamic tiling Wayland compositor that doesn't sacrifice on its looks.
-
Brand every Mac in your fleet — colored frame, name tag, watermark, and connect splash as click-through overlays. Never wonder which Mac you remoted into again.
-
Hyprland is an independent, highly customizable, dynamic tiling Wayland compositor that doesn't sacrifice on its looks.
-
An emulated RISC-V Linux computer in your browser.
-
Paste any GitHub URL → interactive architecture map. See how files connect, find what breaks if you change something. No install, no accounts — runs entirely in your browser.
-
web-based loom frontend, serverless, openrouter and openai-compat
-
Standing on the shoulders of giants — a warm sepia-on-paper dark theme for Omarchy
-
Native Wayland screenshot and annotation editor for Omarchy and Hyprland
-
Reproducible Microduck RL experiments, policies, simulation assets, and hardware add-ons
-
Textbook on reinforcement learning from human feedback
-
Our library for RL environments + evals
-
Autonomous research agents that co-develop benchmark tracked repos
-
NetHack as-a-library. Semantic world exploration engine.
-
A shared, persistent world for people and AIs — the networking, persistence, and multi-participant layer over the eidoverse-video toolkit. Two planes: an append-only world log + lossy presence.
-
Proofs for Erlang/Elixir programs through LEAN (via automatic translation of Core Erlang)
-
ENPIRE is an agentic framework that allows AI coding agents to autonomously self-improve real-world robot policies through closed-loop physical trial, error, and evolution
-
Official Implementation for WorldSculpt: Generating Compositional Worlds from Grounded Videos
-
MCP server for Substack: rich drafts, Notes, analytics, and consented subscriber management across publications. Long-form posts stay draft-only; Notes publish immediately. Used regularly by multiple newsletters, includes a CLI.
-
AM-Bench: a modular simulation suite and benchmark for aerial manipulation policy learning (CoRL 2026)
-
Paste any GitHub URL → interactive architecture map. See how files connect, find what breaks if you change something. No install, no accounts — runs entirely in your browser.
-
A Pure JAX AsyncRL stack
-
Autoresearcher + wandb + datadog + overleaf + claude code. All local, all free. Boot a node, git clone, fill the form, let it rip.
-
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
-
Minimal RLM harness
-
RL training environments for Microduck (mjlab)
-
Speculative programmatic tool calling (sPTC) for harnesses like RLM, CodeAct, etc.
-
RL training environments for Microduck (mjlab)
-
OpenTelemetry instrumentation for Erlang & Elixir
-
OpenTelemetry Erlang SDK
-
Game Env for RL training/self-play/curriculum learning
-
Blazingly fast world manipulation for artists, builders and everyone else.
-
A live 3D world map built on flutter_scene: streaming terrain, OSM buildings, a physical sky, and a globe