Karpathy's framing for what we're really building. This page pulls forward BC's existing alignment work — three Karpathy primer docs, an active memory-dreaming workflow, and the brain/heart split — and maps it onto Joe's stack. The Made VPS already runs on this architecture; this page documents the alignment.
/01
Push knowledge out of weights and into retrievable memory. Use a smaller, cheaper, updatable model. Front-load structure into retrieval + skills. The transformer's job is reasoning, not knowing.
"Smaller model, bigger system. Better context, not bigger weights."
Joe's stack: Anthropic Claude (haiku-4-5 / sonnet-4-6 / opus-4-7). Different models for different tasks — haiku for cheap classification, sonnet for primary, opus for heavy reasoning.
BC's stack: Identical model family. Sonnet 4.6 default. Haiku for classification at $0.01/item. Opus for the council pattern.
Joe's stack: per-agent system_prompt + tool belt — well-defined in made-ai-os.agents. 40 distinct context recipes catalogued.
BC's stack: per-agent skills + retrieval + memories + citations, structured assembly. "Context is the new prompt."
Joe's stack: RAG Content DB (791,334 chunks, voyage-3 embeddings) + KG (10,426 entities · 11,849 relationships).
BC's stack: Two-tier disk extension — vector DB (semantic recall) + KG (relational recall) + Mem0 (episodic). Each query route uses a different mix.
Joe's stack: 25 skills · n8n agentic workflows · MCP via Claude Desktop · Edge Functions.
BC's stack: 127 skills · 3 Pydantic AI agents (Market Intel, Client Prep, Content) · 25 n8n workflows · MCP servers · Heart VPS cron.
/02
BC's extension of Karpathy's "disk." He describes disk as one thing — we split it into 5 tiers, each with different cost/recall trade-offs. Joe has tiers L1, L4, L5 strong. L2 + L3 are the gaps to close.
L1
Context window
Per-agent system_prompt + tools (well-defined in 40 agents)
Skills + retrieval + memories + citations · structured assembly via Cascade
L2
Session memory
Multi-user session memory profiles documented in design — runtime not yet wired
Mem0 user/session scoping on Hub DB · per-conversation persistence · agent_memory table
L3
Agent memory
agent_memory + agent_memory_index tables exist (188 rows) · auto_dream candidate staging exists · runtime not yet wired
agent_memory table on Hub DB · Cognee + Neo4j knowledge graph · 50K+ stored relationships · per-agent persistent state
L4
RAG + KG
791,334 chunks · voyage-3 (1024-dim) · rerank-2 · brain-router-v3 · 10,426 entities + 11,849 relationships · hierarchical chunking · quality scoring
17K embedded chunks · Gemini 768-dim · Cohere rerank-v3.5 · brain-router 8-layer pipeline · 50K+ KG nodes
L5
Structured DB
Transfer DB · made-ai-os · Reporting DB · 4 large Postgres instances all live · ai_health_pulse 66K rows
Hub DB (200+ tables) · Brain DB · Heart DB · per-client schemas · Cortex master_plans
/03
BC's extension of Karpathy's framing. He collapses scheduled I/O into the same "peripherals" box as tools. We separated them into two VPSes because scheduled sync jobs have different operational needs than per-query tool calls. Reused for Made.
LLM reasoning + RAG + agent runtime + memory. The thinker.
Scheduled syncs + cron jobs + n8n orchestration. The pump.
/04
The offline consolidation loop. Nightly background pass that summarizes high-volume facts, prunes stale, reinforces useful. BC has this running. Joe has CURATOR designed for it.
"Sleep on it. The brain doesn't compress at write-time."
Weekly Sunday workflow. Reads the past 7 days of agent_memory candidates, runs an LLM consolidation pass, promotes high-confidence learnings, prunes low-signal noise.
memory-dreaming.json — n8n workflow definitiondream-nightly.sh — KB VPS launchd jobdream-operator.sh — operator-triggered consolidationagent_memory + agent_memory_indexJoe's analog. Currently draft in made-ai-os.agents. Triggered weekly Sunday 04:00 ET. Reads agent_memory_candidates → consolidates → writes to agent_memory.
Tier 2.2 in 12_AGENT_PORTING_ROADMAP.md → "joint dream cycle" with BC.
BC's dreaming workflow already runs nightly. Joe's CURATOR is fully designed and waiting for the runtime. Plan: BC ports its memory-dreaming.json to call Joe's agent_memory_candidates table after the standalone Pydantic runtime stands up on the Made VPS. Cycle runs nightly across both sides. Each side keeps its own scope (BC's clients vs Made's commercial ops) but the consolidation logic is shared.
Closes the "joint dream cycle" gap from 10_GAPS_BOTH_SIDES.md.
/05
Frozen Sonnet → tight tool belt → ReAct loop (reason → call tool → observe → reason). This is Yao et al. 2022 executed in our stack. BC has 3 live Pydantic agents proving the pattern. Joe's 40 agents move through the same template.
"Software 3.0 — skills + agents + workflows attached to a constant LLM."
BC live · port template
Frozen Sonnet · 12 tools (search, classify, score, sync) · ReAct loop · writes to client_news_intelligence.
BC live · port template
Frozen Sonnet · meeting prep + briefing sheet generation · ReAct loop · MCP-exposed.
BC live · port template
Frozen Sonnet · brand voice + draft + publish · pairs with Marketing Director · 11 active scopes.
For Joe's fleet: the same Pydantic AI ReAct pattern. CHIEF goes first (orchestrator at apex of reports_to). Then MADE BRAIN (lift heavy reasoning out of n8n into Pydantic). Then the rest, fleet by fleet, agent by agent. See the Project Mgmt fleet map for the operationalization path.
/06
Karpathy's gist (April 2026) named what BC was already doing. Three layers: corpus, wiki, schema. Both Made and BC live this pattern.
Raw source material — what the LLM consumes.
Joe: 791,334 chunks across 15,210 docs in RAG Content DB. 69 Fellow.ai meeting transcripts.
BC: 17K chunks across Hub DB. Per-client research outputs. PubMed + grants + trials.
LLM-written, LLM-maintained markdown layer. Summaries, entity pages, concept pages, cross-references. "You read it; the LLM writes it."
Joe: per-agent SKILL.md cards · domain_rules · employee_profiles · department_profiles. Currently human-maintained.
BC: _shared/reference/*.md primers · _executive/*.md canon · per-department CLAUDE.md · per-client CLIENT_CONTEXT.md / OPPORTUNITY_SUMMARY.md. Currently human-maintained — LLM-driven write-back is the 2026-Q3 gap.
The disciplined-maintainer instruction set. CLAUDE.md / AGENTS.md. Tells the LLM how to run the wiki. Co-evolves with the wiki.
Joe: AGENTS.md adoption spike (rank 4 in build queue) · 25 SKILL.md files · 18 skill_gap_candidates · skill_links many-to-many.
BC: Root CLAUDE.md + per-department CLAUDE.md + _executive/soul.md + .windsurf/rules/*.md + skills index.
/07
The vision when the Made VPS is up, the agents are ported, and the memory hierarchy is fully wired.
Made VPS hosts BC-built agents today (Made-Ralph, Account Brief). Target: Pydantic FastAPI services for Tier 1 agents (CHIEF, MADE BRAIN). Mac mini keeps launchd. n8n + EFs stay.
L1-L5 fully wired. Per-user session memory. Per-agent persistent memory. Knowledge graph reasoning live.
Joint dream cycle nightly. Both sides consolidate. Stale facts pruned. High-signal learnings reinforced.
Every agent callable from Windsurf · Claude Desktop · Made App · Reporting UX. Same surface, multiple entry points.
ai_health_pulse already running (66K rows). Eyes Dashboard surfaces it. Joint observability — BC adopts Joe's schema.
Wiki (LLM-written, human-reviewed). Schema (CLAUDE.md / AGENTS.md). The corpus stays raw. The whole system co-evolves.
/08
All BC canon. Pull these forward — they're the substrate this page summarizes.
_shared/reference/KARPATHY_ALIGNMENT_BIOCREATIVE.md
_shared/reference/KARPATHY_KG_LLM_PRIMER.md
_shared/reference/KARPATHY_PHASE_2_ROADMAP.md
_shared/reference/KARPATHY_LLM_WIKI_AND_4_RULES.md
_executive/BIOCREATIVE_BRAIN_INTERNALS.md
_executive/BIOCREATIVE_HEART_AND_NERVOUS_SYSTEM.md
_executive/made-partnership/11_BRAIN_FOR_BRIAN_PHASE_PLAN.md
_executive/made-partnership/12_AGENT_PORTING_ROADMAP.md
_executive/made-partnership/15_BRAIN_FOR_MADE_PHASE_A1.md
_shared/reference/BRAIN_VSP_SCHEDULED_JOB_PATTERNS.md
departments/internal-ops/n8n-workflows/memory-dreaming.json
departments/agent-brain/deploy/brain/scripts/dream-nightly.sh
departments/agent-brain/deploy/brain/scripts/dream-operator.sh
_shared/brands/biocreative/diagrams/deep-dives/deepdive_memory_hierarchy.excalidraw