firela-pa-pc

firela-pa PC — a Sovereign Personal AI FIRE advisor on your own device

firela-pa is a Sovereign Personal AI — a FIRE financial advisor that lives on your own device: your device decides what ever leaves, its memory of you never leaves home, and the cloud is used only when needed — with the question redacted, the provider swappable, and your identity never on the cloud side.

Sovereign Personal AI = personal service × three user-held rights × zero-tracking foundation

• Classification right — a router built from rules you can read, running on your device, decides what leaves — not an OS vendor
• Memory right — voice and agent memory never leave the device; transaction-level ledger data never goes to the cloud (aggregates only, under a field-level egress policy)
• Cloud-leg right — anything that goes to the cloud passes a redaction gateway first, and the provider is swappable at any time

What this is

The PC distribution of firela-pa. Its privacy router is rules you can read: a tiered rules-as-data engine (13 rules + a precedent table + word tables, shipped as plain JSON inside the app — open router_precedents.json and read exactly what gets classified where; three intents: ledger query / local chat / redacted-cloud; 370-question eval, all four gates green). The default install footprint is pure code — no model download required for routing.

What leaves your device is decided by rules you can read, not weights you can't; compute is borrowed — redacted first, returnable.

An optional 1.7B precision layer (task-fine-tuned Qwen3 LoRA merge, GGUF) is available via install.sh --router.

v1.22 capabilities (2026-10-09)

• Rules-based local routing — what leaves the device is decided by the rule engine on your device, not by an OS vendor. Chat and ledger questions stay local (ledger via your own vlt token); market quotes/history run through a deterministic relay leg; advice-type questions go to the cloud — redacted first.
• Redaction gateway — CN ID/phone/address/person names, SSN, US phone, Japan My Number and email are scrubbed from the question before any cloud call; the provider is swappable.
• Local agent memory — FIRE assumptions and goals in a local SQLite store (0600), saved only on explicit "remember this", never leaving your device.
• FIRE simulation engine — real-return compounding, withdrawal-rate sensitivity sweep, and historical stress-sequence replay (US stock/bond rolling windows 1928–2025, worst-start 1966, window survival rates) — in the free tier, not behind a paid SaaS.
• Proactive audit — overspend / large-expense / FIRE-milestone checks over your own ledger, rendered locally.
• Local-only telemetry — a local SQLite diary (0600) for your own instrument panel. It never uploads anything.

Install (macOS / Linux / WSL2)

bash <(curl -fsSL https://huggingface.co/firela-ai/firela-pa-pc/resolve/main/install.sh)

Automatically: downloads the app tarball from this repo (sha256-verified — the rules engine rides along, no model download) → installs/starts Ollama only if needed (generation model / precision layer) → pulls the generation model qwen2.5:3b-instruct (--no-gen to skip) → interactive 0600 config (vlt / relay credentials, may be left blank) → Time Machine exclusion → firela-pa command → smoke test (routing smoke runs with zero dependencies). Add --router to also install the optional precision layer, --voice for the fully-local voice chain.

Privacy boundary: the control plane never leaves home — routing, redaction, memory and credentials live on your device; the cloud is used only for borrowed compute, with the question redacted first and only aggregate ledger data attached (field-level egress policy — transaction details never go to the cloud).

Source code (Apache-2.0, snapshot + single-egress CI gate): https://github.com/firela-ai/firela-pa

License & attribution

Everything in this repo — pc-app.tar.gz, install.sh, router-merged-Q4_K_M.gguf, router-merged-Q8_0.gguf — is provided under Apache License 2.0.

The optional precision-layer model is a LoRA fine-tune merge derivative of Qwen3-1.7B (© 2024 Alibaba Cloud / Qwen team, Apache-2.0). Redistribution must include the LICENSE copy as per Apache-2.0 §4.

firela-pa is an AI tool, not a licensed financial advisor. Simulation results are historical scenario analyses, not predictions.