Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.
Agentic game development taken to the next level: plan, build and test across major engines with any coding agent🤖
Playwright for coding agents. Benchmark Claude Code, Codex, Gemini, and OpenCode on your own tasks - and test that your skills, MCP servers, and CLIs work when an agent uses them. Sandboxed YAML suites, activation checks, A/B experiments, CI gates.
Agentic coding framework powered by AGENTS.md: systematic, test-first workflows with quality gates for Cursor, Codex, Gemini CLI, and AI coding agents.
Self-hosted AI agent harness in a single Go binary — writes, sandbox-tests and repairs its own tools, and lets Claude Code, Codex and any MCP client build and share them.
Self-evolving SDLC enforcement for AI coding agents — hooks, skills, and one-command setup for Claude Code. Plan before coding, test before shipping, escalate when uncertain. Measures itself getting better over time.
VexJoy AI Agent with Intelligent Routing - /do routes plain-English requests to the right specialist agent and gates the work with reviews, tests, and a learning loop.
MCP Server Security Standard (MSSS): an open, testable security control standard for certifying MCP servers, with levels, evidence requirements, and reporting schemas.
Comprehensive sets of standards and practices designed to elevate the capabilities of AI coding agents.
Create production-ready skills and agents for OpenClaw. 4-level memory, auto-improvement, 22 battle-tested pitfalls.
Skills for controlling Android, iOS and cloud phones
The most RAM efficient harness
Open source software factory infrastructure for advanced AI coding workflows
One prompt. Full delivery.
Agent Skill evaluation harness for paired variants, trace artifacts, and runner adapters
A provider-agnostic scaffolding kit for running structured multi-agent workflows in your codebase.
A kit for building with AI agents and also the engineering patterns around it.
Multi-Agent Harness for Production AI
Prismer Cloud
Public results and task definitions for FrontierHarness Eval
Complete AI Agent System for OpenClaw — memory, self-healing, self-improvement, voice, automation
The Agent Harness for AI-Human Collaboration, inspired by the AI-DLC (AI-Driven Development Lifecycle)
Multi-agent orchestration for Claude Code. Persistent memory, tasks, rules, and skills that make AI agents actually coordinate.
14MB ACP-Rust Agent, Claude Code Plugin compatible, Dynamic Workflow, Goal, Artifacts, Free Web Search, full feature and better support!