Skip to content

benikigai/elias

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 

Repository files navigation

elias

autonomous AI assistant built on OpenClaw, running 24/7 on a home compute cluster in San Francisco.

7 specialized agents. 5 messaging channels. 27 knowledge schemas. local inference. persistent memory. self-healing infrastructure.

this isn't a chatbot. it's an operating system for my life and businesses.


what elias does

elias is my personal chief of staff. he triages incoming messages across WhatsApp, SMS, Telegram, Discord, and LINE, delegates to specialized agents, manages a short-term rental portfolio, monitors infrastructure, tracks finances, runs research, and writes code autonomously overnight.

the system processes thousands of messages per week, manages guest communications for 5 properties, monitors 8 machines, and coordinates a team of 4 assistants via Slack.


agent fleet

every agent owns one domain. elias orchestrates, delegates, and escalates.

agent role model where it runs
elias orchestrator, personal chief of staff GPT-5.4 Codex Mac Mini (gateway)
cleo guest relations, property operations Gemini Flash Hetzner VPS
atlas fleet monitoring, infrastructure ops Hermes3 70B (local) Studio A
sterling personal CFO, financial analysis Palmyra-Fin 70B (local) Studio A Docker
orion research, competitive intelligence Qwen3.5 35B (local) Studio A Docker
codex autonomous development, CI/CD GPT-5.4 Codex Studio A Docker
kai team management via Slack Qwen3.5 35B (local) Hetzner VPS

agents on VPS (cleo, kai) survive home fleet outages. guest comms and team management never go down.


model cascade

every request falls through a 7-tier model cascade. fast and free first, expensive last.

GPT-5.4 Codex (primary)
  -> GPT-5-mini
    -> Gemini 3 Flash
      -> Claude Sonnet 4.6
        -> Gemini 3.1 Pro
          -> Qwen3.5:35b local (free)
            -> OpenRouter (fallback)

subagents use a separate cascade starting with local models to keep costs near zero for routine tasks.


triage routing

elias classifies every incoming message and routes it to the right speed tier.

tier when model latency cost
fast greetings, status, memory lookups Flash / Qwen 9B <1s ~free
deep analysis, drafting, multi-tool Sonnet 4.6 3-5s ~$0.05
analysis research, forensics, critical decisions Opus 4.6 5-10s ~$0.50
local quick tech questions, config Qwen3.5 35B 2-3s $0
war room collaborative multi-persona 2-3 Sonnet instances ~15s ~$0.25
council strategic synthesis 7 Sonnet instances ~30s ~$0.40

channel architecture

WhatsApp (Twilio API)  ──→  relay :18796  ──→  gateway :18789  ──→  elias
SMS (Twilio)           ──→  relay :18792  ──→  sms agent
LINE                   ──→  relay :18790  ──→  line-translate (Gemma3 27B)
Telegram               ──→  direct API   ──→  elias + cleo + kai
Discord (35 channels)  ──→  direct API   ──→  elias + all agents
Voice (Twilio)         ──→  relay :18795  ──→  Deepgram STT → LLM → ElevenLabs TTS

Discord serves as the ops dashboard with 35 channels across 8 categories: personal, guests, finance, research, development, business, briefings, and approvals.


compute cluster

all machines wired through a 10G switch. no Wi-Fi. sub-millisecond LAN latency.

machine role hardware memory
Mac Mini gateway, relays, cron M4 16 GB
Studio A agent runtime, fast local models M4 Max 128 GB
Studio B heavy inference, model palace M3 Ultra 512 GB
Studio C RDMA partner (TB5 link to B) M3 Ultra 512 GB
Spark A-D GPU inference, fine-tuning 4x NVIDIA GB10 512 GB total

Studio B + C form a 1 TB unified memory pool over Thunderbolt 5 RDMA, capable of running 400B+ parameter models.

total: 1,280 GB Apple Silicon + 512 GB CUDA. ~28 TB storage.


memory and knowledge

3-layer memory

  1. index (<=150 lines) read every session. structural overview of the entire system.
  2. topics (12 files) read on-demand. deep references on infrastructure, channels, agents, security, cron, guests, projects.
  3. changelog (monthly files) append-only audit trail. never read by agents, exists for forensics.

ontology

27 YAML schemas define a structured knowledge graph with ~4,800 objects:

guests, reservations, properties, transactions, payouts, reviews, competitors, market intel, devices, health records, calendar events, conversations, pricing data, cleaning schedules, and more.

dual search: Qdrant (semantic, Gemini Embedding 2) + LanceDB (backup). both maintained via cron.


agent deep dives

cleo (guest relations)

cleo owns the entire guest lifecycle across 5 properties. she runs on a VPS so guest comms survive home outages.

  • 6-touch automated cadence: booking confirmation, pre-arrival, check-in, mid-stay check, checkout, review request
  • AI reply drafts: classify intent, debounce rapid messages, generate via Gemini Flash, queue for approval
  • cleaner notifications: morning schedules, day-before alerts, weekly summaries
  • smart lock management via Seam API: access codes, lock status, guest-specific codes
  • Beds24 + PriceLabs integration for availability and dynamic pricing

atlas (fleet operations)

atlas watches 8 machines and self-heals when things break.

  • continuous monitoring: CPU, memory, disk, GPU utilization, model serving status
  • VRAM tracking across the cluster with swap commands
  • self-healing: 2 automatic repair attempts before escalating to me
  • alert pipeline: green (Discord log) -> yellow (Discord + Telegram + auto-heal) -> red (Telegram + pause + wait for human)
  • SSH access to every machine in the fleet

sterling (personal CFO)

sterling runs on Palmyra-Fin 70B locally for financial data privacy.

  • daily: net worth snapshot, expense anomaly detection, API cost tracking
  • weekly: per-property P&L, portfolio performance, market digest, competitor pricing analysis
  • monthly: full P&L generation, tax prep data, investment rebalancing recommendations
  • investment analysis: Sharpe ratio, alpha, sector exposure, correlation matrices, stress scenarios
  • data pipeline: Monarch pull (5:30 AM) -> ontology ingest -> Sterling reads (5:40 AM) -> briefing (5:55 AM) -> #sterling Discord

orion (research and intelligence)

  • 4 search tools: Exa (semantic), Tavily (quick), Firecrawl (deep extraction), Perplexity (conversational)
  • 4 depth levels: scan (30s), brief (2 min), deep (10 min), report (30 min)
  • scheduled research: AI ecosystem radar (every 6 hours), market news (daily), STR intel (weekly)
  • 10 Playwright scrapers running daily for competitive short-term rental intelligence

codex (autonomous development)

  • generate + review pattern: GPT-5.4 Codex generates, DeepSeek-R1 32B reviews, loop until clean
  • overnight autonomous builds on feature branches
  • creates branches, opens PRs, deploys to Vercel preview. never merges to main without approval
  • codebase health checks and dependency audits

kai (team management)

kai manages a team of 4 assistants via Slack with structured accountability.

  • AM standups (9 AM local) + PM check-ins (5 PM local)
  • LLM-powered hour estimation for task planning
  • Asana integration: contextual task weaving, stall detection, smart assessment scoring
  • weekly strategic review + monthly deep review
  • per-workspace context isolation so assistant data stays separated

infrastructure

11 always-on services (Mac Mini)

gateway websocket, LINE/Twilio/Stripe/Voice/Location webhook relays, canvas HTTP server, Syncthing for Obsidian vault sync, cleaner calendar service, arena LLM dashboard, Cloudflare tunnel.

~50 cron jobs

  • email triage (every 30 min): 3-tier archival with 55+ auto-archive rules
  • guest messaging (every 15 min): Beds24 monitor + 6-touch cadence
  • financial data (daily): Monarch pull, expense tracking, API cost rollup
  • STR intelligence (daily): 10 Playwright scrapers for competitor pricing and availability
  • morning digest (6 AM): parallel assembly of schedule, weather, alerts, finance, health, agent status -> Discord + Telegram
  • model health checks, NFS self-healing mounts, config watchdog, memory sync

config lockdown

the main config file is root-owned, chmod 444, with macOS immutable flag. edits go through an unlock/edit/lock wrapper script. a watchdog re-locks every 2 minutes and auto-repairs known patches.

smart alert system

all system alerts flow through a classification and deduplication pipeline before dispatch. property alerts suppress during active guest stays. system alerts have a 6-hour cooldown with 24-hour escalation. no alert fatigue.


what i learned building this

  1. specialization beats generalization. one agent per domain with clear boundaries works better than one agent trying to do everything.

  2. local inference changes the economics. running 35B-70B models on Apple Silicon means most routine tasks cost nothing. the API cascade is a safety net, not the default.

  3. VPS for critical paths. anything that can't go down (guest comms, team management) runs on a VPS separate from the home cluster.

  4. memory needs structure. free-form context windows aren't memory. a 3-layer system with schemas, indexes, and changelogs gives agents real continuity across sessions.

  5. self-healing saves sleep. atlas auto-repairs most infrastructure issues. i get paged only when two automatic fixes fail.

  6. config lockdown prevents disasters. after a few incidents with accidental config overwrites, the immutable flag + watchdog pattern has been bulletproof.

  7. model cascades are essential. no single model is reliable enough for 24/7 operation. a 7-tier fallback chain means the system stays up even when APIs go down.


built with

OpenClaw · TypeScript · Python · Next.js · FastAPI · PostgreSQL · Prisma · Qdrant · Playwright · Tailscale · Docker · Cloudflare · Twilio · ElevenLabs · Deepgram · Stripe · 1Password · Obsidian · Apple Silicon · NVIDIA


about me

i'm ben. hardware TPM at Apple and Meta for a decade, now building AI systems that operate in the physical world. more at github.com/benikigai.

About

autonomous ai assistant running on openclaw. 7 agents, 5 channels, persistent memory, home inference cluster.

Resources

Stars

1 star

Watchers

0 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors