graphrag-toolkit
Python toolkit for building graph-enhanced GenAI applications
Python toolkit for building graph-enhanced GenAI applications
Your toolkit for autonomous, evolving agent ecosystems. Create, execute, govern, and evolve agents that learn from experience, collaborate, build new capabilities, and operate safely within defined guardrails.
A virtual AI-based pit crew for Sim Racing. Use the latest GPT technology to create a real life like experience when out on the track.
Official plugin distribution for the hosted Zapier MCP server. Install it in your AI client and connect to thousands of apps.
Built on **Agentic RAG** (Agent-driven Retrieval-Augmented Generation) technology, it not only accurately answers pre-sales and after-sales questions but also generates personalized usage reports and optimization suggestions by deeply analyzing device data.
LightningRAG is a full-stack Vue + Gin starter with a decoupled frontend and backend, plus built-in, extensible RAG (retrieval-augmented generation): knowledge bases, vector search, and integrations with many LLM and vector-store providers
Autonomous AI dev agent in pure Go built on empirical research. Enforced ephemeral subagents prevent context degradation. Get real work done on consumer hardware.
Marketing frameworks that AI actually executes. Designed for Claude Code, but could be used for OpenClaw, etc.
AI-powered modular Active Directory red-team framework for authorized penetration testing, AD enumeration, attack-path analysis, Kerberos/ADCS workflows, reporting, operator automation, and MCP server integration.
Local-first game design OS for AI agents: turn sessions into evidence, experiments, reviewable decisions, and durable project memory—Human Gates and rollback.
Explain & debug any blackbox machine learning model with a single line of code.
Realtime speech to presentation. Let the whiteboard whiteboard itself.
🍊 New Yorker-style minimalist editorial illustration skill for AI agents — one idea, one accent, lots of silence. Free for open-source use; commercial license for closed-source.
Deterministic safety solutions for probabilistic AI agents
A workspace where people and multiple AI agents work together.
Team of marketing agents built on eve.
Open-source GEO AI-employee solution (MIT): a GEO Skills package plus curated lists of agents and office CLIs that make up the AI-employee stack.
Run AI agents isolated in a macOS user account and sandbox-exec. Configured to run Claude Code, OpenAI Codex, Cursor Agent, Google Gemini.
Your First LLM-Wiki Conversation Knowledge Base
The operations layer for agentic engineering — portable skills and contracts connecting intent, agents, software factories, and independent judgment.
Harness coding workflow for codex, claude, github copilot
Run Claude Code, Codex & Gemini in parallel on Windows & macOS — git worktree fan-out with atomic hunk adoption, approval gates, reboot-surviving sessions
24 cross-platform agent skills for Claude Code, Cursor, Codex & Gemini CLI — databases, messaging, research, TTS, DevOps, and Google Workspace
Open-source, local-first 3D parametric CAD that runs in the browser for people and permissioned typed agents, powered by OpenCascade WASM.