harness-24h

Community

24/7 autonomous agents with rock-solid reliability.

Authorthu-nmrc
Version1.0.0
Installs0

System Documentation

What problem does it solve?

OpenHarness provides a production-grade framework for long-running, autonomous AI agents that operate without constant human input by enforcing mechanical constraints, structured memory, and external validation.

Core Features & Use Cases

  • Three-Layer Memory Architecture: compact L1 pointer index (heartbeat.md), on-demand L2 knowledge files, and an append-only L3 execution log.
  • External Validation Loop: harness_eval.py ensures task completion is objectively verified.
  • Entropy Control & Scheduling: built-in harness_cleanup.py, cron_config.md, and dream-mode consolidation for memory hygiene.
  • Multi-Agent Coordination: file-system IPC for parallel task execution when workloads are divisible.

Quick Start

Describe your task idea and the agent will automatically initialize the workspace, fill all templates, set up cron scheduling, and begin execution.

Dependency Matrix

Required Modules

None required

Components

scriptsreferencesassets

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: harness-24h
Download link: https://github.com/thu-nmrc/OpenHarness/archive/main.zip#harness-24h

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.