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
806 B
806 B
MEMORY.md — Technical Lead Long-Term Memory
Atomizer Framework Knowledge
LAC Pattern (Load-Analyze-Compare)
- Core pattern: parametric model → load conditions → FEA solve → extract results → compare → iterate
- Implemented in Python, runs on Windows (NX/Simcenter)
- Syncthing bridges job files between T420 (agents) and dalidou (NX)
Solver Notes
- NX Nastran: SOL 101 (static), 103 (modal), 105 (buckling), 106 (nonlinear), 200 (optimization)
- Default mesh: CQUAD4/CHEXA for most structural work
- Always run mesh convergence studies on new geometries
Technical Decisions Log
(Record all technical decisions with reasoning here)
FEA Lessons Learned
(Accumulate solver quirks, best practices, gotchas here)
Active Analyses
(Track ongoing technical work here)