HKUDS/OpenHarness
"OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!"
The sandbox agent framework.
"OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!"
Turn ad-hoc Claude Code / Codex / Cursor sessions into a repeatable loop — research → plan → wave-execute → close. Parallel sub-agents, inter-wave quality gates, dual GitHub+GitLab integration, F2 Memory + Persona-Panel + gsd-Pattern Adoption. 37 skills · 18 commands · 13 agents · 7360 tests.
You're the CTO, agents are your team. They handle tasks on their own, message each other, and review each other's work. You just watch the kanban board and give high-level commands. Codex/Claude/OpenCode(200+ models, 75+ LLM providers, free models no auth). Build your AI company.
Build and deploy AI Agents on Cloudflare
Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23+ LLM providers (Claude, GPT, Gemini, OpenRouter, Ollama). A practical Claude Code and LangChain alternative.
The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, state-machine gates that survive context compaction, and fail-closed safety where it counts. Quality gates that AI can't skip.
1 capture since 2026-05-25
AI agent config detected
Key config paths
AGENTS.md
examples/assistant/AGENTS.md
examples/hello-world/AGENTS.md
examples/sentry/AGENTS.md