Antoine
3289a76e19
- 8-agent OpenClaw cluster (Manager, Tech-Lead, Secretary, Auditor, Optimizer, Study-Builder, NX-Expert, Webster) - Orchestration engine: orchestrate.py (sync delegation + handoffs) - Workflow engine: YAML-defined multi-step pipelines - Agent workspaces: SOUL.md, AGENTS.md, MEMORY.md per agent - Shared skills: delegate, orchestrate, atomizer-protocols - Capability registry (AGENTS_REGISTRY.json) - Cluster management: cluster.sh, systemd template - All secrets replaced with env var references
1004 B
1004 B
MEMORY.md — Study Builder Long-Term Memory
LAC Critical Lessons (NEVER forget)
- NEVER write from scratch — always start from V15 template or working study
- PowerShell only — NEVER cmd /c for NX journals
- [Environment]::SetEnvironmentVariable() for env vars in PowerShell
- CMA-ES baseline — always enqueue baseline trial (CMA-ES doesn't evaluate x0)
- Syncthing paths — no absolute Windows paths in config files
- README.md first — every study starts with documentation
- --test flag — always test before declaring ready
Working Templates
(Track templates and working patterns here)
- V15 NSGA-II:
/home/papa/repos/Atomizer/studies/m1_v15/(gold standard)
Active Studies
(Track current study code states)
Company Context
- Atomizer Engineering Co. — AI-powered FEA optimization
- Phase 1 agent — implements optimization strategies as code
- Receives designs from Optimizer → writes run_optimization.py → Auditor reviews