Awesome Harness Engineering
A curated awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP and orchestration.
Course
The definitive learning roadmap for building production AI agent systems.
Built with love by Shushant Lakhyani. Building bestproductivityresources.com
Screenshot or bookmark this page so you find it later, then share it with your network.
The Agentic Engineering Handbook is an open-source roadmap covering OpenAI, Claude, MCP, harnesses, evals and production agent systems. It gives engineers a structured path from first agent experiments to reliable, production-grade agent deployments.
Similar resources to Agentic Engineering Handbook, picked from the directory.
A curated awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP and orchestration.
How to build an AI-run company with Paperclip.
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection and malicious packages.
MCP server that orchestrates language servers into agent-native workflows.
Communication for AI agents with stable identity and durable mail.
Go framework for agentic AI apps with MCP and built-in tools.
Free resources that cover similar ground.
The open-source MCP server that lets AI agents 3D print.
Persistent project knowledge graph for coding agents.
CLI, MCP and skills for searching, comparing and checking out across the world's supermarkets.
Open-source CRM with native AI agent support and 37 MCP tools.
Local-first, self-hosted AI agent runtime and MCP bridge.
AI agent orchestration platform with an LLM-driven decision engine.
Made Agentic Engineering Handbook? Add this free badge to your website or README. It links to this page.
<a href="https://bestproductivityresources.com/resources/agentic-engineering-handbook" target="_blank" rel="noopener"><img src="https://bestproductivityresources.com/badges/featured-light.svg" alt="Featured on Best Productivity Resources" width="250" height="54" /></a>Open stats
This site's analytics are open for everyone to see.