Sam Coward

model-serving-minefield. Community registry of LLM serving-path traps that produce confidently wrong measurements: templates, tool parsers, reasoning fields, quant kernel paths, CUDA toolchains, KV allocation, eval harnesses, versioning. Symptom-first, with the check that catches each.

img2threejs. Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.

awesome-ltx2. All available LTX-2 models, encoders, workflows, LoRAs for ComfyUI

openobserve. Open source observability platform for logs, metrics, traces, frontend monitoring, pipelines and LLM observability. A sophisticated, simple and highly performant alternative to Datadog, Splunk, and Elasticsearch with 140x lower storage costs and single binary deployment.

LongCat-Video. Python

ouroboros. Agent OS: Stop prompting. Start specifying.

image-blaster. An image-to-world skillset for Claude.

gastown. Gas Town - multi-agent workspace manager

predict-rlm. Production focused Self-harnessed LM runtime (RLM) that allows the LM to call its sub-lm with DSPy signatures. Define your inputs, outputs, and tools — the model handles its own control flow. Get fully interpretable trajectories and performance that scales directly with model improvements. Without context rot.

hermes-webui. Hermes WebUI: The best way to use Hermes Agent from the web or from your phone!

OpenGame. OpenGame: Open Agentic Coding for Games

ml-intern. 🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

cookbook. Examples, end-2-end tutorials and apps built using Liquid AI Foundational Models (LFM) and the LEAP SDK

dflash. DFlash: Block Diffusion for Flash Speculative Decoding

Claude-Code-Game-Studios. Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.

taste-skill. Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop

tokenjuice. 🧃 Token weight loss. Lean output compaction for terminal-heavy agent workflows. Works as a native CLI tool or as an extension to popular coding and agent frameworks.

claude-desktop-buddy. Reference and an example for the Bluetooth API for makers in Claude Cowork & Claude Code Desktop

clearwing. Python

gbrain. Garry's Opinionated OpenClaw/Hermes Agent Brain

pi-share-hf. Collect, review, and upload redacted pi session files to a Hugging Face dataset

supervisor. JavaScript

mathcode. MathCode: A Frontier Mathematical Coding Agent

mlx-vlm-falcon. Grounded reasoning agent: Falcon Perception + Gemma 4 VLM on Apple Silicon

comfy3d. A docker container for 3D development with ComfyUI

hermes-agent-self-evolution. ⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA

pretext. Fast, accurate & comprehensive text measurement & layout

facefusion. Industry leading face manipulation platform

turboquant_plus. Python

VisionClaw. Real-time AI assistant for Meta Ray-Ban smart glasses -- voice + vision + agentic actions via Gemini Live and OpenClaw

MiroFish. A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物

gstack. Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

autoresearch. AI agents running research on single-GPU nanochat training automatically

hermes-agent. The agent that grows with you

InferenceX. Open Source Continuous Inference Benchmark Research Platform — Kimi K3 2.8T, MiniMax M3, DeepSeekv4, GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 & soon™ TPUv6e/v7/Trainium2/3 | 开源持续推理基准研究平台 — Kimi K2.7-Code、MiniMax M3、DeepSeekv4、GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72，即将推出™ TPUv6e/v7/Trainium2/3

ANE. Training neural networks on Apple Neural Engine via reverse-engineered private APIs

SymTorch. Deep Learning Interpretability with Symbolic Regression

OpenClaw-RL. OpenClaw-RL: Train any agent simply by talking

Scrapling. 🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!

zvec. A lightweight, lightning-fast, in-process vector database

rlm. General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.

Marketing-for-Founders. Practical marketing resources to get the first 10 / 100 / 1000 users for your SaaS / App / Startup

OpenPlanter. Python

cs-video-courses. List of Computer Science courses with video lectures.

Monolith. RLM for coding agent

awesome-openclaw-usecases. A community collection of OpenClaw use cases for making life easier.

LobsterBoard. OpenClaw Dashboard Builder - Create custom dashboards

picoclaw. Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity

alma. ALMA (Automated meta-Learning of Memory designs for Agentic systems) is a framework that meta-learns memory designs to replace human-engineered designs for agentic system.

LangExtract-RAG. Python

langextract. A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

mlx-audio. A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.

AI-Scientist-v2. The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

repomirror. TypeScript

pi. AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

dexter. An autonomous agent for deep financial research

rustfs. 🚀2.3x faster than MinIO for 4KB object payloads. RustFS is an open-source, S3-compatible high-performance object storage system supporting migration and coexistence with other S3-compatible platforms such as MinIO and Ceph.

openclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Termux-Command-Handbook. Termux Command Handbook, your comprehensive guide to Termux commands organized into various chapters for easy reference.

react-grab. Copy any UI element for your agent

production-agentic-rag-course. Python

Paper2Slides. "Paper2Slides: From Paper to Presentation in One Click"

ink. 🌈 React for interactive command-line apps

poetiq-arc-agi-solver. This repository allows reproduction of Poetiq's record-breaking submission to the ARC-AGI-1 and ARC-AGI-2 benchmarks.

MoCha. MoCha: End-to-End Video Character Replacement without Structural Guidance

skills. Public repository for Agent Skills

Qwen-Image. Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

segment-anything-2-real-time. Run Segment Anything Model 2 on a live video stream

realtime-phone-agents-course. Build realtime AI voice agents using FastRTC for low-latency streaming, Superlinked for vector search, Twilio for live phone calls, and Runpod for scalable GPU deployment.

raylib. A simple and easy-to-use library to enjoy videogames programming

XcodeBuildMCP. A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.

dingcad. Live reload cad scripting because >lmao UIs

AlohaMini. Open-Source Dual-Arm Mobile Robot with Motorized Lift

LongSplat. [ICCV 2025] LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

Wan2.2. Wan: Open and Advanced Large-Scale Video Generative Models

softchat. convert twitch/youtube chat into softsubs

comfy-ui-client. Node.js WebSockets API client for ComfyUI

agentops. Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI

Local-NotebookLM. Googles NotebookLM but local

smollm. Everything about the SmolLM and SmolVLM family of models

shot-scraper. A CLI utility for taking screenshots of websites, recording video demos and scraping sites using JavaScript

stripe-recommendations. How to implement Stripe without going mad

dr-tulu. Official repository for DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

ImReflect. Reflection-based ImGui wrapper

imgui. Dear ImGui: Bloat-free Graphical User interface for C++ with minimal dependencies

OpenCharacterTraining. Open Character Training

mlx-lm-lens. Find the hidden meaning of LLMs

superpowers. An agentic skills framework & software development methodology that works.

Awesome-World-Models. A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.

GPU-Puzzles. Solve puzzles. Learn CUDA.

Tensor-Puzzles. Solve puzzles. Improve your pytorch.

MiMo-Audio-Training. Python

term.everything. Run any GUI app in the terminal❗

gun. An open source cybersecurity protocol for syncing decentralized graph data.

activerecord-tenanted. Enable a Rails application to have separate databases for each tenant.

flashbacker. Claude Code state management with session continuity and AI personas, subagents and agent discussion

ml-interviews-book. https://huyenchip.com/ml-interviews-book/

hud-python. RL environments + evals for AI agents. Define once, train anything.

uptime-kuma. A fancy self-hosted monitoring tool

stanford-cme-295-transformers-large-language-models. VIP cheatsheet for Stanford's CME 295 Transformers and Large Language Models