Sync with live vault: 28 new files, 7 imports, 16 updates
This commit is contained in:
@@ -1,87 +1,111 @@
|
||||
# HOME — Tony Second Brain / AgentOS
|
||||
# HOME — Local Agent OS (Tony's Windows PC)
|
||||
|
||||
> **Canonical vault root:** `/home/vpsadmin/AgentOS`
|
||||
> **Open this folder in desktop Obsidian.**
|
||||
> Last updated: 2026-07-09
|
||||
> Maintainer: Anthony (Tony) · Operator agent: Leonard (Hermes profile)
|
||||
> **Canonical vault:** `~/Documents/Obsidian Vault` (this folder)
|
||||
> **Agent:** Hermes (local PC profile) + Leonard personality
|
||||
> **Date started (local setup):** 2026-08-28
|
||||
> **Current primary models:** OpenRouter DeepSeek (deepseek-v4-flash-0731, current), FreeToken local (Gemma-4-26B + gpt-oss-20b), remote brother boxes via Tailscale, local llama-cpp at 1920
|
||||
|
||||
---
|
||||
|
||||
## North star
|
||||
## North Star
|
||||
|
||||
One local markdown vault that:
|
||||
One Obsidian vault that:
|
||||
- You browse and edit directly on the laptop
|
||||
- Hermes reads from and writes to for compounding memory
|
||||
- Survives model changes (local FreeToken ↔ Grok ↔ remote)
|
||||
- Uses the Personal Agent OS model from `Tony_tech/personal-agent-os`
|
||||
|
||||
1. You can browse in Obsidian on the laptop
|
||||
2. Leonard can read/write on the VPS (no root required)
|
||||
3. Survives model swaps (system > model)
|
||||
4. Compounds: Raw dump → structured notes → project status
|
||||
This is the external brain: raw input → structured notes → project status → agent lessons.
|
||||
|
||||
This is the Julian-Goldie-shaped loop, Hermes-native: **vault = memory galaxy**.
|
||||
## Current Structure (Agent OS + PARA hybrid)
|
||||
|
||||
---
|
||||
| Path | Purpose |
|
||||
|------|---------|
|
||||
| `index.md` | Vault index — link map to everything |
|
||||
| `HOME.md` | Constitution — north star, active projects, non-negotiables |
|
||||
| `STATUS.md` | Health snapshot — services, cron jobs, model stack |
|
||||
| `00_Raw/` | Dump zone — transcripts, quick captures, voice blobs |
|
||||
| `00_system/` | Memory policy, boot instructions, decision log |
|
||||
| `01_user/` | Durable facts about you (confirmed + proposed) |
|
||||
| `01_Wiki/` | High-signal curated topic pages |
|
||||
| `02_agents/` | Hermes + Leonard rules, lessons, boot prompts |
|
||||
| `03_shared/` | Cross-agent workflows (ready for use) |
|
||||
| `04_Daily/` | Daily notes & consolidations |
|
||||
| `04_projects/` | Active projects (status.md + decisions.md per project) |
|
||||
| `05_Output/` | Shippable artifacts for humans/clients |
|
||||
| `09_templates/` | Note templates (project, KB entry, experiment log) |
|
||||
| `10_archive/` | Stale/old projects |
|
||||
| `10_Projects/` | Personal overflow (PARA) |
|
||||
| `20_Areas/` | Personal areas (PARA) |
|
||||
| `30_Resources/` | Personal resources (PARA) |
|
||||
|
||||
## Active projects (max 3 primary)
|
||||
## Active Projects
|
||||
|
||||
| Project | Path | Status (see status.md) |
|
||||
|---------|------|------------------------|
|
||||
| **Athena Oracle** | `04_projects/athena-oracle/` | Live research pipeline |
|
||||
| **AI Talk Show** | `04_projects/ai-talk-show/` | Dual agents + edge-tts; native TTS on laptop if desired |
|
||||
| **Local velocity / Phoenix** | `04_projects/local-velocity/` + `phoenix-salon/` | Salon digital presence |
|
||||
See `04_projects/` for status.
|
||||
|
||||
Secondary / parked: memory-system tests (complete), Grok inbox experiments (do not expand).
|
||||
|
||||
---
|
||||
Key current:
|
||||
- **VeriPath** — human-supervised business verification / audit service (core business)
|
||||
- **Athena Oracle** — AI research pipeline (GitHub + arXiv + HF ingestion, daily digests)
|
||||
- **Hermes Agent local PC setup** — complete (model stack, vault RAG, auto-start, watchdog, TTS, desktop, kanban)
|
||||
- **Thornhill Construction website** — built, deployment pending DNS decision
|
||||
- **Local inference stack** — LFM2.5 primary, FreeToken manual, brother nodes via tailnet
|
||||
|
||||
## Non-negotiables
|
||||
|
||||
- **No root required** for vault work — everything under `$HOME`
|
||||
- **Gitea:** `Tony_tech/*` and `Leonard/*` writable; `Ty_Tech/*` read-only
|
||||
- **No firehose** — selective saves into the right project folder
|
||||
- **User memory:** propose only → `01_user/proposed_memory.md` (Tony confirms)
|
||||
- **Secrets:** never in the vault (tokens stay in env / agent-config outside git if sensitive)
|
||||
- **Grok:** not for agent/MoA calls (OOC); free/local models only for tooling
|
||||
- **VPS Chatterbox / swap:** off agenda — laptop optional for local TTS
|
||||
- Secrets, tokens, keys stay in `~/Documents/Vault` (never in vault)
|
||||
- Only durable, high-signal information goes into project/wiki/agent memory
|
||||
- User memory: propose in `01_user/proposed_memory.md`, wait for confirmation
|
||||
- Prefer LFM2.5 (local, fast, agentic+reasoning) for daily work; use brother-5090 for complex reasoning that exceeds 65K context
|
||||
- Vault RAG uses LM Studio embeddings at :1234 + ChromaDB; reindex after any new notes are added
|
||||
- FreeToken requires manual start; cannot coexist with LFM2.5 on 12GB GPU (needs ~15GB combined)
|
||||
- Git the important parts or sync via the Gitea mirror when needed
|
||||
|
||||
## How Hermes Uses This Vault (Memory Layer)
|
||||
|
||||
Hermes (via obsidian skill + file tools):
|
||||
- Loads `HOME.md` + `00_system/memory_policy.md` + relevant `04_projects/*/status.md` + `02_agents/leonard/lessons.md` at start of complex sessions
|
||||
- Searches with `search_files` (target files or content)
|
||||
- Writes status updates, decisions, daily notes, lessons
|
||||
- Uses `write_file` / `patch` for precise edits
|
||||
|
||||
**Boot order for multi-step work (keep under ~1500 tokens unless needed):**
|
||||
1. This HOME.md
|
||||
2. `00_system/memory_policy.md`
|
||||
3. `02_agents/leonard/lessons.md`
|
||||
4. Relevant project `status.md` or `decisions.md`
|
||||
|
||||
## Model & Inference Reality (Local PC)
|
||||
|
||||
- **Primary:** LFM2.5-2.6B via llama.cpp at `:1920` (65K ctx, ~145 tok/s, agentic+reasoning)
|
||||
- **Fallback:** brother-5090 Qwen3.6 27B MTP via tailnet `100.64.0.2:8084` (200K ctx, 27B params)
|
||||
- **Secondary local:** FreeToken gpt-oss-20b at `:1919` (manual start, can't coexist with LFM2.5 on 12GB GPU)
|
||||
- **Cloud backup:** OpenRouter free models (Gemma-4-26B)
|
||||
- **Voice & TTS:** Wake word "hey Jimmy" (sherpa), Edge TTS AriaNeural, auto_tts=true, barge-in enabled, ffplay v9.0.1
|
||||
- Auto-start: `start-models.bat` in Windows Startup (LFM2.5 launches on boot)
|
||||
- Watchdog: `lfm25-watchdog` cron (every 2m) auto-relaunches LFM2.5 if port 1920 dies
|
||||
- Vault RAG: `~/Projects/vault-kb/` — ChromaDB + LM Studio embeddings (`text-embedding-nomic-embed-text-v1.5` at :1234), 240 chunks / 43 files indexed
|
||||
- Git sync: `vault-sync` cron (every 6h) pushes vault to Gitea private mirror
|
||||
|
||||
## Getting Started / Daily Loop
|
||||
|
||||
1. Dump to `00_Raw/` or Inbox
|
||||
2. Consolidate into project `04_projects/<slug>/status.md`
|
||||
3. Record decisions in `decisions.md`
|
||||
4. Hermes writes lessons to `02_agents/leonard/lessons.md`
|
||||
5. Daily work → `04_Daily/`
|
||||
6. Review `HOME.md` and project status before big sessions
|
||||
|
||||
See the Gitea mirror at `~/Documents/AgentOS/` for full templates and older knowledge-base.
|
||||
|
||||
## Project Creation Template
|
||||
|
||||
Inside `04_projects/<kebab-name>/`:
|
||||
- `status.md` — current state, goals, next actions
|
||||
- `decisions.md` — dated decisions with rationale
|
||||
- Any supporting notes, evidence, specs
|
||||
|
||||
Use wikilinks `[[HOME]]`, `[[VeriPath]]` liberally.
|
||||
|
||||
---
|
||||
|
||||
## How the loop works
|
||||
|
||||
```
|
||||
YOU (laptop Obsidian) LEONARD (VPS Hermes) GITEA (optional mirror)
|
||||
│ │ │
|
||||
edit notes ◄── Git/Syncthing ──► read/write vault ──push──► personal-agent-os
|
||||
dump to 00_Raw/ consolidate after work backup/history
|
||||
```
|
||||
|
||||
1. Dump messy stuff → `00_Raw/`
|
||||
2. Durable project truth → `04_projects/<name>/status.md` + `decisions.md`
|
||||
3. Topic synthesis → `01_Wiki/` (one idea / topic page when worth it)
|
||||
4. Daily briefs / session notes → `04_Daily/`
|
||||
5. Shippable artifacts → `05_Output/`
|
||||
6. Agent lessons → `02_agents/leonard/lessons.md` (reusable only)
|
||||
|
||||
---
|
||||
|
||||
## Agent boot (Leonard)
|
||||
|
||||
On multi-step sessions, load in order (token budget ~1500 unless task needs more):
|
||||
|
||||
1. This file (`HOME.md`) — skim
|
||||
2. `00_system/memory_policy.md`
|
||||
3. `02_agents/leonard/lessons.md`
|
||||
4. Relevant `04_projects/<project>/status.md`
|
||||
|
||||
Full checklist: `02_agents/leonard/boot_prompt.md`
|
||||
|
||||
---
|
||||
|
||||
## MoA policy
|
||||
|
||||
Default: **Leonard builds alone.**
|
||||
Escalate to mixture-of-agents only when Leonard flags a real design fork (e.g. sync architecture failure modes, product vs service tradeoffs). Not for folder creation or routine consolidations.
|
||||
|
||||
---
|
||||
|
||||
## Desktop setup
|
||||
|
||||
See `DESKTOP_SYNC.md`.
|
||||
This vault is now the primary long-term memory for your local Hermes Agent. Load it. Use it. Let it compound.
|
||||
Reference in New Issue
Block a user