Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval/inspect-ai.
★not rated 96▲
+2 14d agoA
tokens not measured
originalMIT
Local-first ComfyUI for Claude Code: drive a local ComfyUI (your GPU, no account) end to end - 75 model prompt recipes, hardware-aware model selection, workflow building, multi-shot video, ControlNet/HDR, the local comfyui-mcp driver. The local-first counterpart to the Comfy Cloud MCP.
★not rated 96▲
+3 9d agoA
tokens not measured
originalApache-2.0
Karpathy-style LLM wiki for research papers. Ingest a URL / arXiv ID / DOI / PDF, write a structured summary into a local Obsidian vault, and maintain a finding-level knowledge graph via wikilinks + Dataview.
★not rated 95 4mo agoA
tokens not measured
originalApache-2.0
evsys-sdk usage skills for the autoresearch loop: read a project's goal and experiment history, decide the next experiment, scaffold and launch it, and read/write experiments, datasets, benchmarks, and metrics via the SDK.
Transforms AI code generation into award-winning web design. Injects real design thinking, creative patterns, and anti-AI-aesthetic techniques extracted from 38 of the world's best-designed websites.
★not rated 95▲
+3 3mo agoA
tokens not measured
originalMIT
Design comprehensive test cases using PICT (Pairwise Independent Combinatorial Testing) for any piece of requirements or code. Analyzes inputs, generates PICT models with parameters, values, and constraints for valid scenarios using pairwise testing. Outputs the PICT model, markdown table of test cases, and expected…
Declarative 60fps kinetic architecture diagrams as code. Design animated cloud, microservices, and system diagrams directly with MarkdyScript and AI agents.
Native Claude Code integration for PyWry — MCP tools for generating and rendering HTML components, chat artifacts, and building native, web, or Jupyter applications with live preview. Built-in support for AgGrid, Plotly, TradingView, and more.
You already have the agent. This is everything around it. greatcto runs Claude Code as a pipeline of 70 specialist agents — an independent model checks each stage before the next builds on it, spending caps refuse rather than warn, and three decisions stay yours: what gets built, how, and whether it ships.
★not rated 93▲
+4
changed todayC
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: