A curated collection of ready-to-run automation prompts for real-world workflows.

Keeping your agents out of trouble with sandboxed coding agent automation

Multi-Agent + Automation: Workflows, Automation, Self-Improving Agents

Persistent memory for AI coding agents: automatic capture, explainable recall, knowledge consolidation, privacy controls, and portable offline storage. One Python file, zero dependencies.

AI-powered annotations for localhost development. Create visual feedback on your apps and let AI coding agents automatically implement fixes via MCP integration.

Build agentic systems. Run them with confidence. Orchestrate agents, automate business processes, inspect every execution, and keep humans in control. Deploy Heym on your own infrastructure.

My personal agent skills

Open source software factory infrastructure for advanced AI coding workflows

Curated collection of AI agent skills for Hermes and other agent frameworks

🔒 MCP gateway with a built-in skill library.

LLM agents as your hyperparameter optimizer.

Open-source desktop AI agent for tools, files, knowledge, workflows, and real deliverables.

An autonomous agent that conducts deep research on any data using any LLM providers

A library of practical AI-agent loops and an installable skill for finding, adapting, and designing repeatable agent workflows.

Connect your agent to the apps you already use - with or without Zapier.

General-purpose Playwright automation for coding agents

Installable agent skills for browser automation, local knowledge, skill management, external CLI workflows, and session handoffs.

Secure MCP runtime for AI agents to operate local machines, servers, and containers with multi-device orchestration.

Open-source AI coworker, with memory

The open-source company brain. Run your entire company with AI agents, skills, and a self-improving context.

A configurable Bash/PowerShell loop that runs an AI coding CLI with a fresh session each iteration

Turn slide screenshots and generated images into editable PowerPoint decks with visual-layer splitting, OCR evidence, and QA.

Better subagent experience for Codex and Claude users

The IM for agents. Shared Agent Context & Memory, supervised execution, and cross-agent audit across AI providers.