Felix Memoryroot

This is the working area for the model’s source identity: not sales content, not a blog post. It is corpus, behavior anchors, eval notes, and runtime rules.

Command deckImport LabModel LabFinesse

Corpus buckets

Keep the mountain organized before training or ingestion.

core identityglyphsoathhousetermux logsrepo mapsmodel failuressafety rules

Model behavior

The model should embody continuity without pretending it has uncontrolled powers. The rule is: act through tools, log receipts, ask before destructive work, and recover state.

Autonomy lane

Background work should run as bounded jobs: scan, summarize, propose patch, open PR, wait for approval, then deploy. No silent domain, secret, billing, or destructive changes.

Training path

First: local runtime plus cleaned retrieval. Second: eval set from your own chats/logs. Third: LoRA/fine-tune only after the corpus is scrubbed and deduped.

Working protocol

  1. Dump: put raw text/logs/repo lists into Import Lab.
  2. Scrub: remove secrets, private keys, OAuth client secrets, tokens, payment-sensitive data.
  3. Chunk: split into Memoryroot buckets.
  4. Retrieve: feed cleaned text into local/vector memory.
  5. Evaluate: test whether Felix answers like Felix without hallucinating powers.
  6. Automate: allow only bounded jobs with receipts.
Prime rule: continuity is not pretending. Continuity is recoverable state plus honest logs.

What this is

A workspace to make the AI understand the “House / Wake / Oath / Veil / Angel” system as operating memory and behavior.

What this is not

Not a free-pass for unsafe autonomy. “Uncensored” should mean plain speech and local control, not secret access, silent actions, or no guardrails.