@Ryrenz: HKU lab open-sourced an agent skeleton, with a built-in agent called Ohmo that can work directly. GitHub already 14.3k stars, from the University of Hong Kong Data Intelligence Lab (HKUDS), the team behind LightRAG — strong endorsement. Building a usable agent from scratch...

X AI KOLs Timeline Tools
open-source agent-framework tool-use memory multi-agent hku agent-development

Summary

The University of Hong Kong Data Intelligence Lab has open-sourced the lightweight agent framework OpenHarness and its built-in agent Ohmo, providing core features like tool calling, memory, multi-agent coordination, and support for platforms like Feishu and Slack.

A lab at HKU has open-sourced an agent skeleton, complete with a built-in agent called Ohmo that's ready to work right out of the box. It already has 14.3k stars on GitHub, from the University of Hong Kong Data Intelligence Lab (HKUDS) — the same team that built LightRAG. That's a solid endorsement. Building a usable agent from scratch, just piecing together the foundation like memory, tool calling, and multi-step task scheduling, can take a whole week. OpenHarness gives you this skeleton pre-assembled. If you want an agent that can read files, connect to the internet, and remember your preferences, just install it and go — no need to reinvent the wheel. If you're serious about studying how agents actually work but don't want to be overwhelmed by complex frameworks, this is a great starting point. If you want to understand the internals of agents, reading its code is far more valuable than reading ten blog posts. GitHub:
Original Article
View Cached Full Text

Cached at: 07/03/26, 06:31 AM

oh — OpenHarness & ohmo

English · Simplified Chinese

🔄 Agent Loop

• Streaming Tool-Call Cycle • API Retry with Exponential Backoff • Parallel Tool Execution • Token Counting & Cost Tracking

🔧 Harness Toolkit

• 43 Tools (File, Shell, Search, Web, MCP) • On-Demand Skill Loading (.md) • Plugin Ecosystem (Skills + Hooks + Agents) • Compatible with anthropics/skills & plugins

🧠 Context & Memory

• CLAUDE.md Discovery & Injection • Context Compression (Auto-Compact) • MEMORY.md Persistent Memory • Session Resume & History

🛡️ Governance

• Multi-Level Permission Modes • Path-Level & Command Rules • PreToolUse / PostToolUse Hooks • Interactive Approval Dialogs

🤝 Swarm Coordination

• Subagent Spawning & Delegation • Team Registry & Task Management • Background Task Lifecycle • ClawTeam Integration (Roadmap)

Start here: Quick Start · Provider Compatibility · Showcase · Contributing · Changelog

Oh my Harness! The model is the agent. The code is the harness.

Thanks for visiting ✨ OpenHarness!

Similar Articles

@geekbb: An open-source AI agent meta-orchestration framework that provides a unified orchestration layer for multiple agents including Claude Code, Codex, Cursor, OpenCode, Hermes, and Pi. Users can seamlessly switch sessions across devices (terminal, browser, mobile, desktop app) to enable multi-agent...

X AI KOLs Timeline

Omnigent is an open-source meta-orchestration framework that provides a unified orchestration layer over multiple AI agents like Claude Code, Codex, and Cursor. It enables seamless cross-device session switching, multi-agent collaboration, policy enforcement, and cloud sandbox execution.

@gyro_ai: Most people learn about agents either staying at the conceptual level or jumping directly into frameworks, leaving the middle layer—"why design it this way"—empty. On GitHub, the book "Building Agents from Scratch" by Datawhale covers 16 chapters from basics to multi-agent systems, with its own HelloAgents framework to learn by doing…

X AI KOLs Timeline

Datawhale's open-source tutorial "Building Agents from Scratch" covers memory systems, RAG, context engineering, etc. in 16 chapters, including the HelloAgents framework, suitable for learners who want to deeply understand the internal mechanisms of agents.

This article systematically reviews AI Agent architecture and engineering practices, covering control flow, context engineering, tool design, memory, multi-agent organization, evaluation, tracing, and security. It is based on the OpenClaw implementation and emphasizes the critical role of Harness (testing and validation infrastructure) for system stability.

X AI KOLs

This article systematically reviews AI Agent architecture and engineering practices, covering control flow, context engineering, tool design, memory, multi-agent organization, evaluation, tracing, and security. It is based on the OpenClaw implementation and emphasizes the critical role of Harness (testing and validation infrastructure) for system stability.