harness-design

better-harness

JavaScript

95

An open-source Harness Engineering platform for coding agents—define harnesses as code, run controlled experiments, inspect evidence, and compare outcomes.

deepsec

TypeScript

90

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

ORG2

TypeScript

90

System of record for how agents build software: Built-in rust harness & 20+ CLIs.

harness-engineering

Python

75

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

harness

Swift

72

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.

deepseek-harness

TypeScript

95

DeepSeek Harness: Everything is a Plugin.

macos-harness

Python

77

The simplest, thinnest harness that gives an LLM complete freedom to control a Mac.

trueforge

TypeScript

90

The open-source agent harness - the runtime layer that turns an LLM into a working agent.

skills

Python

75

Codebase harness + loop engineer

ECC

JavaScript

100

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

85

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

devspace

TypeScript

85

Minimal Coding Agent Harness over MCP for ChatGPT, Claude, Hermes, Grok Bot, OpenClaw

loopkit

Shell

70

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

Jixu

TypeScript

68

Durable single-Agent Harness for TypeScript: recoverable Threads, context continuity, explicit side effects, and a native TUI.

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.

waggle

Rust

67

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.

llm-space

TypeScript

95

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

90

Waku Waku! Waku Agent is a local-first AI agent harness you actually own, including loop, memory, eval, all in code built to stay legible as it grows.

eve

TypeScript

85

The Open Framework for Building Agents

fablize

Python

75

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.

FrontierAgent

Python

90

🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency.

ai-trains-ai

Python

67

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

ragflow

Go

95

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

ratel

TypeScript

77

Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.