--- title: README emoji: πŸ§ͺ colorFrom: indigo colorTo: purple sdk: static pinned: false --- # Qovaryx **Sovereign-trained compact AI for trading and finance.** Random-init scratch substrates. Audited compact specialists. Local-first deployment. No borrowed foundation weights, no closed APIs in the inference path. A research project building toward a frontier-grade decision system that runs on hardware a single person can own. --- ## πŸ† 2026-07-20 β€” Qovaryx 3.0 milestone shipped A 5-year full-pipeline backtest (2021–2026, $500 starting capital, real + synthetic option corpus, all wired safety gates engaged) on the four public risk tiers: | Tier | Total return (5 yrs) | Positive every year? | |---|---|---| | Conservative | +523% | βœ… | | Standard | +1,793% | βœ… | | Aggressive | +22,785% | βœ… | | Extreme | +47,326% | βœ… | Every profile positive every year β€” including 2022 (bear), 2020-style vol shocks in the corpus, and 2025 chop. Aggressive and Extreme require typed operator acknowledgement and enforce mandatory milestone profit-pulling. Universal circuit breakers active on every tier: daily loss halt, correlation cap, drawdown ack, slippage governor. Numbers describe the backtest; live paper begins Q3 2026. **What actually changed in 3.0:** - **Four-tier execution-authority taxonomy on every specialist head.** `REAL_VALIDATED_SCOPED` heads can influence a named consumer strategy. `SYNTH_VALIDATED_SHADOW` runs alongside live decisions, logged, never mutating. `VERIFIED_FORECAST_CONTEXT` heads are feature-input only. `OFFLINE_FORECAST_ADVISORY` is research-only. Nothing overrides an order without a signed headβ†’consumerβ†’mutation contract. Full write-up: [Head Architecture Advances](https://github.com/thron-j/qovaryx-ai-research/blob/main/research/head_architecture_advances_20260720.md). - **A proprietary data moat.** Multi-decade daily equity coverage (thousands of tickers), multi-year real options-chain snapshots for the highly liquid names, app-faithful multi-symbol option-PnL labels, calibrated synthetic bridges with label-bridging validation, intraday minute-bar snapshots, and a privacy-preserving decision-outcome corpus. Full write-up: [The Data Moat](https://github.com/thron-j/qovaryx-ai-research/blob/main/research/the_data_moat_20260720.md). - **BYO-AI chat with 7 providers.** OpenAI, Anthropic, Google, xAI, OpenRouter, Ollama (local), and custom OpenAI-compatible. Keys encrypted via OS keychain. Per-context opt-in for what the AI can see. **BYO-AI is for chart analysis and position review β€” it is not on the order-execution path.** The trending "ChatGPT / Claude will trade for you" wrappers are not consistently profitable when benchmarked out-of-sample; general-purpose LLMs weren't trained to price options or size risk. Different job, different tool. - **CPU-only inference. No GPU, no cloud round-trip.** The full trading cluster runs on any x86-64 from 2018 or newer with 8 GB RAM. - **13 shipping options strategies** dispatched under the same risk gate: iron condors, credit spreads (both directional variants), PEAD drift (30-DTE and 45-DTE), breakouts, VPA long calls/puts, tactical allocator, VIX-crush credit spread, tail hedges. - **Deep cleanup.** 22 previously-dormant safety features wired end-to-end and ~1,750 lines of dead code removed. 80/80 focused test suite. Codex ship audit: APPROVE / HIGH CONFIDENCE. Implementation specifics β€” exact training recipes, routing heuristics, sizing math, gate thresholds, corpus labeling functions β€” are intentionally withheld. The framings publish; the recipes do not. *Trading options involves substantial risk of loss. Backtest results are historical simulation, not a forecast. Not financial advice.* --- ## What lives here This organization is the home for the **Qovaryx model lineage** β€” the published artifacts of a project arguing that compact, locally-trainable AI is a distinct research target, not a smaller version of frontier scaling. ### Scratch-base substrates *(random-init β€” designed to be trained, not chatted with)* These are directed blanks: the architecture, the decision surfaces, and the design choices are baked in; the weights are random. They exist so a single researcher on a single consumer GPU can train a specialist model end-to-end without renting a datacenter. - **[qovaryx-1b-scratch-base](https://huggingface.co/tjarvis91/qovaryx-1b-scratch-base)** β€” 1B parameter own-base decoder. Fits on a 16 GB consumer card under QLoRA NF4. The publication target of the substrate line. - **[qovaryx-350m-scratch-base](https://huggingface.co/tjarvis91/qovaryx-350m-scratch-base)** β€” 350M parameter mid-size substrate. Fits on a 12 GB card. The deployment-friendly size. - **[qovaryx-50m-scratch-base](https://huggingface.co/tjarvis91/qovaryx-50m-scratch-base)** β€” 50M parameter proxy substrate. Fits anywhere. Used for pipeline validation before the larger sizes commit to training time. - **[qovaryx-3b-scratch-base](https://huggingface.co/tjarvis91/qovaryx-3b-scratch-base)** β€” 3B parameter scratch-base extension of the same lineage. All four share a modern compact stack: Grouped-Query Attention (GQA), Rotary Position Embeddings (RoPE), pre-norm RMSNorm, SwiGLU feed-forward, tied embeddings, native multi-token-prediction (MTP) heads, a four-class decision head, optional chart-patch encoder for vision input. Apache-2.0 weights, Apache-2.0 reference trainer. ### Trading-application lineage *(trained, working, local-first deployable)* The 9B chart-reading lineage that operationalized the same disciplines on a larger backbone before the current Qovaryx app surface: - **[vfai-x-3.5-9b-options](https://huggingface.co/tjarvis91/vfai-x-3.5-9b-options)** β€” legacy VFAi-X lineage page retained for reproducibility and research. - **[vfaix-vpa-options-trader](https://huggingface.co/tjarvis91/vfaix-vpa-options-trader)** β€” VPA-flavored legacy variant. ### Deployed: Q-Chat router The first **operational** artifact in the lineage β€” a sovereign-trained compact specialist intent router, audited and deployed live on free Hugging Face CPU infrastructure, serving a real community Discord. Read more in the [public devlog entry](https://github.com/thron-j/qovaryx-ai-research/blob/main/research/sovereign_compact_cognition_deployed.md) on the deployment. You can interact with it directly through the project's Discord community β€” `/qchat ask ` β€” and the model will route, retrieve, and respond. No closed model anywhere in the loop. --- ## Discipline This project is built under six explicit commitments: - **Local sovereign AI** β€” the deployed system runs on hardware the operator owns. No silent dependency on a remote API. - **Compact cognition** β€” small is not the apology. Density per stored bit, routing per active parameter, structure per training row. - **Verifier-governed inference** β€” the wrapper around the model is part of the architecture, not a deployment afterthought. - **Adaptive compute** β€” the model thinks harder on the inputs that deserve it and cheaper on the inputs that do not. - **Execution-aware intelligence** β€” gross alpha is not a result. Numbers must survive realistic costs. - **Intelligence per watt** β€” the only honest unit of progress under a power-, memory-, and bit-constrained budget. These are first-class architectural decisions made at the very first commit. They are not deployment optimizations. --- ## Where to go next | Surface | Link | |---|---| | Website | [qovaryx.jehorizon.com](https://qovaryx.jehorizon.com/) | | πŸ“œ **Public research devlog** | [github.com/thron-j/qovaryx-ai-research](https://github.com/thron-j/qovaryx-ai-research) | | 🎫 **Community Discord** (builders training their own trading/finance models, no signals) | [discord.gg/PtuHZDv5ju](https://discord.gg/PtuHZDv5ju) | | πŸ§ͺ **Deployed Q-Chat router** | type `/qchat ask ` in the Discord | | πŸ€— **Founder profile** | [huggingface.co/tjarvis91](https://huggingface.co/tjarvis91) | | πŸ“¦ **VFAi-X desktop releases** | [github.com/thron-j/vfai-x-releases](https://github.com/thron-j/vfai-x-releases) | | β˜• **Support the next training run** | [ko-fi.com/tjarvis91](https://ko-fi.com/tjarvis91) | | πŸ“§ **Contact** | thomasjarvis2026@gmail.com | Implementation specifics β€” exact training recipes, routing heuristics, gate thresholds, curriculum mixing ratios, verifier internals β€” are intentionally withheld. The framings are publishable; the recipes are not. --- *Qovaryx is an ongoing research effort. The work is in motion. The claims are provisional. The constraint is the point.* *This is research and infrastructure writing. Not financial advice. Not a trading signal.*