harness and oh-my-harness

These are complements: A provides the agent runtime environment while B generates the guardrails and configuration files (CLAUDE.md, hooks, settings) that constrain and configure agents running within that environment.

harness
52
Established
oh-my-harness
33
Emerging
Maintenance 13/25
Adoption 7/25
Maturity 20/25
Community 12/25
Maintenance 13/25
Adoption 2/25
Maturity 18/25
Community 0/25
Stars: 27
Forks: 4
Downloads:
Commits (30d): 0
Language: TypeScript
License: MIT
Stars: 2
Forks:
Downloads:
Commits (30d): 0
Language: TypeScript
License: MIT
No risk flags
No risk flags

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.

AI-assistant-customization AI-workflow-automation content-generation market-research data-analysis

About oh-my-harness

kyu1204/oh-my-harness

Tame your AI coding agents with natural language. Generate enforced guardrails (CLAUDE.md, hooks, settings) from a single command.

Generates project-specific guardrails via Claude AI prompt engineering and an auto-detecting project analyzer covering 14 languages and frameworks. Enforces rules through git hooks, file-system guards, and command-blocking shells with state tracking in JSONL event logs for audit trails. Uses `harness.yaml` as a single source of truth that regenerates `CLAUDE.md`, hook scripts, and `settings.json`—integrating with Claude Code, Cursor, and the standard git pre-commit ecosystem.

Scores updated daily from GitHub, PyPI, and npm data. How scores work