openclaw-multi-brainRuns Kimi K2.5 and GPT 5.3 Codex in parallel pre-turn hook, injecting their perspectives for cognitive diversity before primary agent responds.
engramLocal associative memory graph for an OpenClaw workspace, shipped as a set of CLI scripts: engram.py (store/recall/msgctx/task ledger over SQLite+FTS+embeddings), engram-migrate.py (markdown to nodes), engram-serve.py and bq.py (optional warm daemon over a Unix socket), embeddings.py (ONNX e5 vectors), engram-backup.py (nightly SQLite backup with retention), engram-sleep.py (nightly consolidation, optional local-Ollama distillation), engram-maintenance.py and engram-hygiene.py (dedupe/orphan/archive tiering), engram-aliases.py (alias curation), engram-rewire.py (opt-in: slims MEMORY.md, adds marked cron lines, asks first), engram-uninstall.py (full revert). Task evidence strings run through the shell. No network calls except to localhost Ollama, and only if you enable it.