An open-source SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skills and subagents, it handles different levels of tasks that could take minutes to hours.

The Ultimate Multi-Agent Harness for Google Antigravity. Orchestrate 6 specialized agents via Serena Memory. Parallel CLI execution, real-time observability, and zero-config skills.

The Agent Harness for AI-Human Collaboration, inspired by the AI-DLC (AI-Driven Development Lifecycle)

A harness for the Diagnostic Rev. 586220 Test for the Commodore C64

A lightweight harness designed to be simple to use, efficient, universially compatible with any coding agent to evaluate them over a broad set of coding tasks and languages.

The Runtime Security Layer for OpenClaw, the essential safety harness for PII & sensitive credentials protection.

A small test framework to write your own test harness that looks and behaves like the built-in test harness used by `rustc --test`

Unit test framework for Jenkins core and its plugins

genie.libs contains libraries for configuring, retrieving and testing topologies

WireViz-Web is a web wrapper around WireViz: Easily document cables and wiring harnesses

AI agents and Nix: parametrable skills/instructions and tools, packaged together in a reproducible and modular fashion

Enforce complexity, linting, tests, and CI so AI-written code stays decoupled, tractable, and commit-blocked until quality gates pass.

Production-validated SAFe multi-agent development methodology with Claude Code. Treat AI agents as specialized team members (11 roles: BSA, Architect, QAS, etc). Complete whitepaper + working template.

Loom is a harness stack, primarily for local LLMs, to finish complex tasks. It decomposes work, drives execution through a verified harness, and keeps models on track with structured state instead of chat history. It can route between thinking and acting models, verifies outputs, and exposes a TUI/API/CLI/MCP for both humans and agents.

Harness for fuzzing GoldSrc file formats with WinAFL

"Extend with llm, stabilise with code" - Prompts when you're exploring, Python when you're certain. Workers and tools form one function space—refactor between them.

Diagnostic harness for the C64 diagnostics

No description provided.

An SDK written in Go for interacting with the Harness API's

No description provided.

🎸 A project-level orchestrator for AI coding agents — Go & Charm stack implementation of OpenAI's Symphony

Easy Testing With Docker Compose in Go.

Unleash the fuzz on your C codebase.

Headless durable agentic harness engine. Run durable AI agents reliably and scalably.

Pull Request Monitor (prm) is a CLI tool for listing pull requests from different Source Code Management (SCM) providers.

Unleash Multi-agent Orchestration - WhatsApp-controlled AI Harness for controlling harnesses.

Harness tests in Bats

No description provided.

No description provided.

No description provided.