Stars
Live demo gallery for img2threejs: procedural Three.js models rebuilt from a single reference image.
Unofficial Python API and agentic skill for Google NotebookLM. Full programmatic access to NotebookLM's features—including capabilities the web UI doesn't expose—via Python, CLI, and AI agents like…
Automation testing anyone can run — deterministic mobile + web E2E, no code required. Desktop app (trial).
Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.
An awesome list that curates Rive runtime examples, articles and tutorials, videos, resources and more!
In-browser Rive (.riv) inventory + scored best-practice & optimize advisor. 100% client-side, powered by podium-mcp/analyzer + @rive-app/canvas-advanced.
Janus — durable-layer harness automating with 9-gate workflow
Unified mobile E2E MCP — 28 tools (mobile-mcp + Maestro + RN-debugger parity)
One MCP server, 51 tools for AI agents on mobile + canvas UIs: iOS & Android automation, Maestro E2E, evidenced assertions, React Native/Metro debugging — plus a no-vision canvas/WebGL brain (Pixi/…
Persistent memory & code intelligence server for AI coding agents. Deploy on VPS for shared memory across machines. Hybrid search (BM25 + pgvector), knowledge graph, impact analysis. 14 MCP tools. …
Real-machine, real-browser web perf measurement with ~99% iframe coverage. LLM-native + AI-agent-loop ready.
Behavior-regression testing for LLM agents. 4-class attribution, 6-field FAIL schema, $-cost gating, flaky detection. Bash + jq. Works with opencode today, runner-pluggable.
Teach an LLM to talk like a person — It teaches a language model how to talk like a person. Not how to sound like one — that part's easy, and it's what most failures already do
#1 Persistent memory for AI coding agents based on real-world benchmarks
Distill OpenCode session conversation history into searchable knowledge atoms (solutions, decisions, learnings) — feeds nano-brain for cross-session recall.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Real-machine, real-browser web perf measurement with ~99% iframe coverage. LLM-native + AI-agent-loop ready.
Chrome DevTools for coding agents
Inspect, validate, and control Rive .riv animation files — from the terminal, AI assistants, or a visual playground. Provides a CLI tool, MCP server (for AI assistants like Claude), and a Playgroun…
Inspect, validate, and control Rive .riv animation files — from the terminal, AI assistants, or a visual playground. Provides a CLI tool, MCP server (for AI assistants like Claude), and a Playgroun…
Python tool for converting files and office documents to Markdown.
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
Your browser's UI, deeply understood by your IDE's AI agent
MCP Console Hub captures **everything** from your browser's console and streams it to your IDE's AI agent via the Model Context Protocol. No code changes needed.
Zero-dependency, token-efficient database MCP server for Postgres, MySQL, SQL Server, MariaDB, SQLite.