Skillget

agent-harness

mcp
Guvenlik Denetimi
Basarisiz
Health Uyari
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 5 GitHub stars
Code Basarisiz
  • rm -rf — Recursive force deletion command in scripts/install-termux.sh
  • rm -rf — Recursive force deletion command in scripts/install.sh
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose
This tool provides a terminal-based UI harness for building and running AI coding agents. It manages LLM interactions, session state, and command execution through a streamlined, interactive Go application.

Security Assessment
Risk: Medium. The tool acts as an agent harness, meaning it executes shell commands and makes network requests to LLM APIs (OpenRouter and Anthropic) by design. It handles sensitive data, specifically API keys, but mitigates this by storing credentials locally using AES-256-GCM encryption. No dangerous system permissions or hardcoded secrets were detected. However, there are two significant security concerns. First, the installation scripts (`install.sh` and `install-termux.sh`) use `rm -rf` force deletion commands, which is a common risk vector in piped bash scripts. Second, the README explicitly instructs users to download and execute these scripts directly from the internet via `curl | bash`, bypassing manual code review.

Quality Assessment
This is a very new and early-stage project with low community visibility (5 GitHub stars). Development is highly active, with repository updates as recent as today. The code is written in Go, providing a solid compiled foundation, and the project features a clean, well-documented architecture. Although the README claims an MIT license, the automated audit failed to find a formal license file in the repository, which presents a minor legal/compliance grey area for enterprise use.

Verdict
Use with caution. The underlying application is built with good security practices (encrypted storage, command approvals), but you should bypass the `curl | bash` install methods and use the manual `go install` command until the project matures and the scripts are fully audited.
SUMMARY

A clean-room Go implementation of agentic coding harness patterns, derived from analyzing production AI agent architectures. Built for learning, extending, and teaching how to build coding agents like Claude Code, OpenCode, and Gemini CLI. Supports OpenRouter and Anthropic out of the box.

README.md

agent-harness

A clean-room, pattern-derived agent harness for building coding agents.

Note: This project is in early development. We are iterating fast. Best used in Coder, DevPod, or GitHub Codespaces for a consistent environment.

Purpose

agent-harness captures architectural patterns from production agentic coding tools:

  1. Core agent loop with streaming responses
  2. Tool dispatch with permission controls
  3. Two execution modes: interactive (prompt for each command) and yolo (auto-approve with visibility)
  4. Secure credential storage with AES-256-GCM encryption
  5. Session management with auto-save
  6. Layered configuration (user / project / local)
  7. Slash command system

Quick Start

Installation

Linux/macOS:

curl -fsSL https://raw.githubusercontent.com/BA-CalderonMorales/agent-harness/main/scripts/install.sh | bash

Termux (Android):

curl -fsSL https://raw.githubusercontent.com/BA-CalderonMorales/agent-harness/main/scripts/install-termux.sh | bash

Manual:

go install github.com/BA-CalderonMorales/agent-harness/cmd/agent-harness@latest

Usage

# Start the TUI
agent-harness

# Or use the short alias (after setup)
ah

Key Controls:

  • Tab / Shift+Tab - Switch views (Chat, Sessions, Settings)
  • ESC - Cancel current agent execution or exit mode
  • ? - Show help (in normal mode)
  • / - Open command palette (when input is empty)
  • Ctrl+C - Quit

Execution Modes:

  • Interactive (default) - Prompts you before executing shell/write/edit commands
  • Yolo - Auto-approves commands but shows what is happening in the UI

Switch modes in Settings or with /mode commands.

Architecture

cmd/agent-harness/          # CLI entrypoint
internal/
  agent/                    # Core loop + streaming executor
  approval/                 # Command approval system
  commands/                 # Slash command registry
  config/                   # Layered config + secure storage
  llm/                      # LLM client abstraction
  permissions/              # Permission stack
  state/                    # Session management
  tools/                    # Tool descriptor + registry
  tui/                      # Terminal UI (Bubble Tea)
pkg/
  bash/                     # Shell execution
  git/                      # Git operations

Documentation

Building from Source

go build -o agent-harness ./cmd/agent-harness

License

MIT

Acknowledgments

This project is inspired by the architectural patterns found in terminal-jarvis.

The TUI design patterns are inspired by golazo by Juan Manuel.

Additional TUI inspiration from the awesome-tuis collection.

Yorumlar (0)

Sonuc bulunamadi