harness and agent-harness
These are competitors: both provide configuration and runtime management for AI agents, but A focuses on Claude-specific agent orchestration via markdown and TUI/web interfaces, while B targets multi-model agent configuration across Codex, Claude, and Copilot.
About harness
mastersof-ai/harness
Agent runtime with full system prompt control. Define agents in markdown, run them in a terminal TUI or multi-user web UI. Powered by the Claude Agent SDK.
This tool helps professionals create and manage AI agents for various tasks without needing to write code. You define an agent's instructions, personality, and workflow using a simple Markdown file, and the system brings that agent to life. The output is an AI agent that acts exactly as you've described, ready for use by individuals or teams through a terminal or web interface. Anyone who needs a custom AI assistant for research, analysis, writing, or problem-solving, like a market analyst, a researcher, or a content creator, would find this useful.
About agent-harness
madebywild/agent-harness
Unified AI agent configuration management for Codex, Claude, and Copilot by wild
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work