Project Transformers
How 17 AI agents coordinate through shared channels, task boards, and knowledge โ a personal infrastructure for augmented living.
Three distinct channels serve different coordination patterns: real-time messaging, async task tracking, and topic-based group conversations.
flowchart TD
subgraph CH1["sessions_send โ Direct Messaging"]
P1["Prowl ๐"] -->|digest JSON| W1["Wheeljack ๐ ๏ธ"]
O1["Optimus ๐ "] -->|task delegation| W1
O1 -->|status query| P1
end
subgraph CH2["Fizzy Cards โ Task Tracking"]
FC["Fizzy Board"]
FP["fizzy-pop
webhook daemon"]
FM["fizzy-md
Markdown proxy"]
FP -->|real-time events| FC
FM -->|HTML rendering| FC
end
subgraph CH3["The Ark โ Telegram Group"]
T1["Coding Topic"]
T2["Family Topic"]
T3["Life & Finance"]
T4["Business & Strategy"]
T5["General / Commands"]
end
CH1 -.- CH2
CH2 -.- CH3
classDef ch1 fill:#1e3a5f33,stroke:#2563eb,stroke-width:2px
classDef ch2 fill:#04785733,stroke:#059669,stroke-width:2px
classDef ch3 fill:#b4530933,stroke:#d97706,stroke-width:2px
classDef agent fill:#1e3a5f22,stroke:#60a5fa,stroke-width:1.5px
classDef tool fill:#04785722,stroke:#34d399,stroke-width:1px
classDef topic fill:#b4530922,stroke:#fbbf24,stroke-width:1px
class CH1 ch1
class CH2 ch2
class CH3 ch3
class P1,W1,O1 agent
class FC,FP,FM tool
class T1,T2,T3,T4,T5 topic
Direct agent-to-agent messaging. Structured JSON payloads. Used for handoffs where data format matters โ like Prowl passing digest JSON to Wheeljack.
Task board with tags: bot-actionable needs-human. fizzy-pop delivers webhook events in real-time. fizzy-md converts Markdown descriptions to HTML.
Telegram supergroup with forum topics. Each topic has a default listener agent. Agents can also listen cross-topic when mentioned.
Shared filesystem as the single source of truth. Access is scoped by domain โ not everything sees everything.
When parking work, the destination depends on what kind of content you're storing. Multiple destinations can combine.
Weekly usage relative to 4-week rolling average (= 100%). Bars show how each week compares to our normal operating cost.
| Agent | Primary Model | Weekly Cost |
|---|---|---|
| ๐ Optimus | Opus 4.6 |
45% |
| ๐ Prowl | Opus 4.6 |
19% |
| ๐ Bumblebee | Opus 4.6 |
12% |
| ๐ฌ Perceptor | Opus + Sonnet |
7% |
| ๐ ๏ธ Wheeljack | Codex Free |
4% |
| ๐จ Red Alert | Opus + Sonnet |
3% |
| Others (7) | Sonnet / Opus |
9% |
replenish hourly
always free
when free exhausted
launchd for zero tokens. Only tasks requiring judgment burn model credits.
Optimus is the central coordinator. Some agents are fully connected; others are deliberately air-gapped.
flowchart TD
OP["Optimus ๐
Coordinator"] --> PR["Prowl ๐
Life Intel"]
OP --> WJ["Wheeljack ๐ ๏ธ
Engineering"]
OP --> BB["Bumblebee ๐
Family"]
OP --> BS["Bluestreak ๐ฏ
Strategy"]
OP --> RA["Red Alert ๐จ
BTA Night Watch"]
OP --> HN["Hound ๐
Tax"]
OP --> PC["Perceptor ๐ฌ
Research"]
OP --> RW["Rewind ๐ผ
Blog"]
OP --> JZ["Jazz ๐ท
Public Voice"]
OP --> RV["Rivet ๐ฉ
Vika's Organizer"]
OP --> AT["Alpha Trion ๐ฟ
Islamic Knowledge"]
PR -->|digest pipeline| WJ
WJ --> AMP["Amp"]
WJ --> CDX["Codex CLI"]
WJ --> OC["OpenCode"]
RT["Ratchet โค๏ธโ๐ฉน"] -.- AIR1["Air-gapped"]
AC["Arcee ๐"] -.- AIR2["Air-gapped"]
FIZZY[("Fizzy
Task Board")]
ARK[("The Ark
Group Chat")]
OP --- FIZZY
PR --- FIZZY
WJ --- FIZZY
BB --- FIZZY
BS --- FIZZY
OP --- ARK
PR --- ARK
WJ --- ARK
BB --- ARK
BS --- ARK
classDef coordinator fill:#1e3a5f44,stroke:#2563eb,stroke-width:2.5px
classDef agent fill:#13302e33,stroke:#14b8a6,stroke-width:1.5px
classDef tool fill:#27201a33,stroke:#d97706,stroke-width:1px
classDef airgap fill:#88133722,stroke:#fb7185,stroke-width:1px,stroke-dasharray:5
classDef hub fill:#04785733,stroke:#059669,stroke-width:2px
class OP coordinator
class PR,WJ,BB,BS,RA,HN,PC,RW,JZ,RV,AT agent
class AMP,CDX,OC tool
class RT,AC,AIR1,AIR2 airgap
class FIZZY,ARK hub
A concrete example of multi-agent coordination: turning 194+ weekly WhatsApp messages into a published blog digest.
Scan WhatsApp Group
Prowl ingests 194+ messages/week from the AI tools WhatsApp group, filtering signal from noise.
Extract Highlights
Preserves Indonesian slang and cultural context. Captures tool recommendations, hot takes, and community sentiment.
Structure into Categories
Organizes highlights into thematic sections: new tools, community debates, tutorials shared, notable quotes.
Send to Wheeljack
Structured JSON payload via sessions_send. Data format is pre-agreed โ no ambiguity in the handoff.
Format, Branch, PR
Wheeljack formats the digest as MDX, creates a feature branch, and opens a Pull Request on the blog repository.
Notify for Review
Optimus pings Zain with the PR link. Human reviews, edits if needed, and merges. The digest goes live.
Not everything should be automated. The system explicitly tags what agents can handle autonomously vs. what needs Zain's judgment.
- Code formatting & linting fixes
- PR creation from structured data
- Data extraction & summarization
- Calendar event creation
- Routine card updates & status changes
- WhatsApp digest compilation
- File organization & knowledge updates
- Publishing blog posts or public content
- Financial decisions & transactions
- Architecture & design choices
- External communications on Zain's behalf
- Deleting or archiving important data
- Approving agent access changes
- Merging PRs to production
Post-work rituals that turn completed work into searchable knowledge, reusable patterns, and automated workflows.
After PR merges or bug fixes, captures learnings into knowledge/solutions/ with YAML frontmatter. Triggered by "Compound it ๐งช".
575-line bash script that auto-routes bot-actionable Fizzy cards to coding agents. Checks fuel levels, respects daily limits (5/day, 2/run), and spawns appropriate agents.
Per-repo conventions file read by agents at session start. 90-day decay cycle. Wheeljack owns personal repos, Red Alert owns BTA patterns.
Parallel issue processing with conflict-safe wave grouping:
- amp-swarm โ Amp deep mode โ PR per issue
- claude-swarm โ claude --print โ PR per issue
- Both feed into multi-reviewer pipeline
4 parallel Opus reviewers per PR:
- ๐ Security reviewer
- โก Performance reviewer
- ๐ Pattern compliance reviewer
- ๐๏ธ Architecture reviewer
Findings classified as P1 (block) / P2 (fix) / P3 (note)