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.
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.
Teams-first Multi-agent orchestration for Claude Code
Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies.
One brain, many harnesses. Portable .agent/ folder (memory + skills + protocols) that plugs into Claude Code, Cursor, Windsurf, OpenCode, OpenClaw, Hermes, or DIY Python — and keeps its knowledge when you switch.
"OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!"
Use Claude to orchestrate agents like OpenClaw
1 capture since 2026-05-29
AI agent config detected
Key config paths
.claude
.cursor
.orchestrator/peers/AGENT.md
agents/AGENTS.md
CLAUDE.md
tests/fixtures/harness-audit/clean-repo/CLAUDE.md
1 more config path detected.
.claude
.claude/loop.md
.claude/rules
.claude/rules/ask-via-tool.md
.claude/rules/backend-data.md
.claude/rules/backend.md
.claude/rules/cli-design.md
.claude/rules/development.md
.claude/rules/frontend.md
.claude/rules/loop-and-monitor.md
.claude/rules/mvp-scope.md
.claude/rules/owner-persona.md
.claude/rules/parallel-sessions.md
.claude/rules/prompt-caching.md
.claude/rules/quality-gates-autofix.md
.claude/rules/receiving-review.md
.claude/rules/security-web.md
.claude/rules/security.md
.claude/rules/swift.md
.claude/rules/test-quality.md
.claude/rules/testing.md
.claude/rules/verification-before-completion.md
.claude/settings.json
.cursor
Showing the first 24 paths. 15 more detected.