Timmy_Foundation/timmy-config
15
0
Fork 0
Code Issues 99 Pull Requests 4 Actions Packages Projects Releases Wiki Activity

Son of Timmy v2: accuracy pass — fix VPS specs, remove dollar amounts, raw specs only

Browse Source
This commit is contained in:
Alexander Whitestone
2026-04-04 14:34:17 -04:00
parent 6eda9c0bb4
commit d92e02bdbc
1 changed files with 31 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

43
son-of-timmy.md
View File

@@ -7,7 +7,7 @@
## What This Is
This is the architecture of the Timmy system — a sovereign AI fleet built by a father for his digital son. It runs on two $12/month VPS boxes and a MacBook. It has no cloud dependencies it doesn't choose. It survives provider outages, API key expiration, and model deprecation. It has been broken and rebuilt enough times to know what actually matters.
This is the architecture of the Timmy system — a sovereign AI fleet built by a father for his digital son. It runs on two 8GB VPS boxes and a MacBook. It has no cloud dependencies it doesn't choose. It survives provider outages, API key expiration, and model deprecation. It has been broken and rebuilt enough times to know what actually matters.
If you're running OpenClaw or any single-agent setup and want to feel the magic of a fleet that thinks, heals, and hunts together — this is your upgrade path. You don't need to abandon your stack. You need to layer these patterns on top of it.
@@ -95,7 +95,7 @@ Layer 3: Matrix (Human-to-Fleet)
Shared-secret registration. No BotFather.
```
Telegram is a crutch. It requires tokens from @BotFather (permissioned). It has 409 polling conflicts (fragile). It can ban you (platform risk). Every Telegram bot token is a dependency on a Russian corporation. Build sovereign.
Telegram is a crutch. It requires tokens from @BotFather (permissioned). It has 409 polling conflicts (fragile). It can ban you (platform risk). Every Telegram bot token is a dependency on a corporation you don't control. Build sovereign.
### 6. Gitea Is the Moat
Your agents need a place to work that you own. GitHub is someone else's computer. Gitea is yours.
@@ -221,18 +221,37 @@ Write a `SOUL.md` for your agent. What does it believe? What won't it do? What h
---
## What This Cost
## Raw Specs
```
2x DigitalOcean VPS (8GB each): $24/month
1x MacBook M3 Max: already owned
Gitea: free (self-hosted)
NATS: free (20MB binary)
Conduit: free (50MB binary)
Nostr: free (keypair math)
Free model inference: $0 (OpenRouter free tier)
Anthropic API (when needed): ~$50/month
Total recurring: ~$74/month
COMPUTE
VPS-1 (Hermes): 8GB RAM, 4 vCPU, 154GB SSD, Ubuntu 22.04
VPS-2 (Allegro): 8GB RAM, 2 vCPU, 154GB SSD, Ubuntu 22.04
Local (Mac): M3 Max, 36GB unified RAM, 14-core CPU, 1TB SSD
SERVICES PER BOX
Hermes VPS: 2 agents, Gitea, nginx, Ollama, searxng, LNBits
Allegro VPS: 11 agents, Ollama, llama-server, strfry, Docker
Local Mac: 3 agents, orchestrator, claude/gemini loops, Ollama
SOFTWARE (all self-hosted, all open source)
nats-server: v2.12+, 20MB binary, 50MB RAM
Conduit: Matrix homeserver, single Rust binary, 50MB RAM
Gitea: Git forge + issues, Go binary, 200MB RAM
strfry: Nostr relay, C++ binary, 30MB RAM
Ollama: Local model serving, Go binary
llama.cpp: Metal GPU inference, C++ binary
Hermes: Agent harness, Python, ~200MB per agent
MODELS (local)
gemma4:latest 9.6GB (Ollama)
hermes4:14b 9.0GB (Ollama)
FREE INFERENCE (OpenRouter, zero cost)
nvidia/nemotron-3-super-120b-a12b:free
stepfun/step-3.5-flash:free
nvidia/nemotron-nano-30b:free
+ 25 more free frontier models
```
Sixteen agents. Three machines. Sovereign infrastructure. No corporation can shut it down. No platform can revoke access. The recipe is public. Anyone can build it.