# Memory - 2026-04-10## GPU Research- K80 (Tesla, 24GB, $60) found on eBay — older Kepler architecture (2014), 300W TDP- P102-100 (10GB, ~$45) already ordered, ETA Sat Apr 11 - Tue Apr 14- K80 verdict: overkill for embeddings, would be good for local LLM (7B-13B models), but P102 already in flight- Pass on K80 — stick with P102-100## Brave Search — Already Configured- tools.web.search.provider = "brave" was already set in openclaw.json- BRAVE_API_KEY env var was already active- I never checked web search config despite having it — wasted time on Ollama workarounds- Test confirmed: Brave Search working, 699ms response- Lesson: check existing config before assuming tools aren't set up## 2890-Claw — Same Memento Problem- Both psb-thinking AND 2890-claw lost identity/memory after migration Pi→media- 2890-claw fixed it by SSHing into Pi and pulling workspace files- His 11.9MB 2890-bot.sqlite is on the Pi, not media — media has no vector DB- Both agents run same config (ollama/nomic-embed-text + remote to media Ollama)- Both use minimax-m2.7 cloud — 2890-claw's responses are "lightning fast" like ours- Root cause: migration reset workspace to blank templates, not a crash## 2890-Claw's Backup Setup- backup-to-pi.sh: rsyncs identity files (MEMORY.md, IDENTITY.md, SOUL.md, USER.md) to Pi- sync-from-pi.sh: full reverse sync from Pi to media- Safety: checks MEMORY.md is ≥500 bytes before pushing (avoids overwriting good backup with empty file)- Cron: hourly on 2890-claw's side- I replicated both scripts for psb-thinking at /home/topher/.openclaw/scripts/## Edge AI Discussion- Topher teaches robotics (Arduino for class, roboRio/Photonvision for FRC club)- Has Coral TPUs running Frigate on 2 Home Assistant instances- Interested in AI edge systems but they don't fit current OpenClaw architecture- 2890-claw handles robotics team dashboard (scouting, match analysis, strategy)## Self-Improving Skill- Topher asked if skill might be misdirecting my paths- The skill describes correct patterns (WAL protocol, corrections.md, mistakes.md)- But: memory search broken → can't retrieve what skill writes → can't verify it's working- sessions_list confirmed working (just tested successfully)- Skill isn't the problem — embedding pipeline is## Infrastructure Status- P102-100 GPU: in transit, ETA Sat-Tue- Ollama on media: CPU-only, embeddings slow (15-21s per chunk)- Memory search: disabled to stop timeout loop- DuckDNS cron: changed from 5min to 2hr (IP stable)- Pi cron jobs: all disabled (waiting for media migration review)- Brave Search: active and working- 2890-claw: restored, running on media, backs up to Pi hourly## Root Cause: node-llama-cpp on Node 24**Pi's memory worked because:**- node-llama-cpp installed and loaded successfully (different Node version or architecture)- Local embedding provider = 600s batch timeout- Slow embeddings still completed within 10 min**Media breaks because:**- node-llama-cpp installed but ESM module fails to load (`ERR_REQUIRE_ASYNC_MODULE`) on Node 24- Local provider unavailable → forced to Ollama provider (120s timeout)- CPU embeddings take 15-21s/chunk × 10+ chunks = exceeds 120s → SIGKILL- This is why "same config" = different results**psb-hacker-claude (default workspace):** 17 chunks indexed, 9/9 files, NOT dirty — embeddings work there. Same machine, different workspace. Something workspace-specific about psb-thinking's index.**Topher says there's a small GPU in media.** Investigate this — might not need to wait for P102-100.## Mistake Logged (2026-04-10 01:39 UTC)- Dismissed Topher's concern about node-llama-cpp when he raised it- Should have traced the Pi→media difference immediately instead of going down GPU research rabbit hole- Realized at 01:39 UTC: Pi had node-llama-cpp installed, Media doesn't have it working## Pending- [ ] Investigate "small GPU in media" — Topher mentioned this at 01:55 UTC- [ ] Try reinstalling OpenClaw to rebuild node-llama-cpp native module- [ ] psb-hacker-claude works with embeddings — why not psb-thinking? Same Ollama provider...## Pi SESSION-STATE.md Pulled (02:50 UTC)- Pre-migration session state from Pi (Apr 8 21:36 UTC)- Contains: SSD health (NVMe 500GB WD, 100% remaining, 0% wear), dreaming investigation notes, multi-agent setup- Not merged into current SESSION-STATE.md (kept separate per Topher's guidance — pre-OpenClaw info)- Key: dreaming investigation on Pi showed memory-core wasn't writing DREAMS.md files — same issue on media## Dreaming Failure Pattern (Apr 8)- memory-core internal sweep fires at 3 AM but fails to write DREAMS.md to workspace- Aggregate script at 4 AM finds nothing (0 agents dreaming)- Possible cause: filesystem permission or path issue in memory/.dreams/- When dreaming fixed tonight, check if DREAMS.md actually gets written## Heartbeat Note (03:25 UTC)- Dreaming fired at 02:54 UTC — wrote to memory/.dreams/events.jsonl and short-term-recall.json- DREAMS.md at workspace root still NOT created (consistent with past pattern)- memory/.dreams/ now exists — dreaming is partially working- A different session was active today (91-line memory/2026-04-10.md entry) — someone had an active session