harness-engineering

harness-engineering

Python

90

🐎 Ryan Lopopolo’s anthology, field guide, and agent context bundle for harness engineering

waggle

Rust

80

Attributed, resolvable artifact references for agent handoffs — a ~30-byte token instead of pasted context. MCP-native; the reference layer for the agent-harness world.

skills

Python

75

Codebase harness + loop engineer

ORG2

TypeScript

85

Coding agent orgs: built for reviewability and team collaboration. Built-in rust harness & 20+ CLIs.

ragflow

Go

90

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

harness

Swift

77

AI-driven user testing for iOS Simulator, macOS apps, and web apps. Write a goal in plain language; an LLM agent drives the UI and reports friction. macOS 14+, Swift 6.

ECC

JavaScript

95

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

grok-build

Rust

90

SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.

deepsec

TypeScript

90

Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents

loopkit

Shell

80

33 battle-tested skills + minimal .claude harness for any coding agent (Claude Code, Cursor, Codex, Gemini CLI).

omnigent

Python

85

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

llm-space

TypeScript

90

A desktop app to prototype agent ideas, inspect every harness step, replay failures, and evaluate performance, all in one place. Local-first, cloud-ready for managed agents.

waku-agent

Python

80

Waku Waku! Waku agent is your personal AI agent, on your own laptop, in code you can read in an afternoon — harness + loop + memory + eval

eve

TypeScript

85

The Framework for Building Agents

fablize

Python

85

A Claude Code plugin that makes Opus behave like Fable — completion, evidence, and verification enforced as procedure. Ships only what a Fable-vs-Opus comparison proved transferable.

ai-trains-ai

Python

77

RL-training an AI agent to RL-train AI agents.