# 📐 Semantic Blueprint — Core Functions of the WFGY Engine

> 👑 **Early Stargazers: [See the Hall of Fame](https://github.com/onestardao/WFGY/tree/main/stargazers)** — Verified by real engineers · 🛠 **Field Reports: [Real Bugs, Real Fixes](https://github.com/onestardao/WFGY/discussions/10)**

<img width="1536" height="1024" alt="WanFaGuiYi" src="https://github.com/user-attachments/assets/08c9617f-d49e-4223-bacc-1d192fbb423d" />

📦 Official WFGY semantic blueprint snapshot on Zenodo: [![DOI](https://zenodo.org/badge/996124831.svg)](https://doi.org/10.5281/zenodo.16635020)  

## 📘 What This Directory Is For

This directory defines the **core reasoning modules** behind the WFGY Engine.  
Each `.md` file represents a symbolic or mathematical function — designed to solve a specific AI reasoning failure through structural intervention.

You’ll find:

- Concept-level logic (symbolic or vectorial)
- The failure mode it targets
- The formula or structure behind the fix
- Annotations of which products use it (e.g., `TXT OS`, `Blur`, `Blow`, etc.)

This is a **developer-facing reference map** for understanding how each reasoning upgrade ties back to WFGY's engine internals.

> Important: Every module listed here reflects a real, working conceptual solution —
> each one was written in direct response to failures we’ve seen in existing AI systems.
> These are not speculative names or sci-fi ideas — but actual answers to actual problems.

**📌 Note:**  
Mappings from *Function → Product* are included as side notes.  
The inverse (*Product → Function*) view is handled in each product’s own directory.

---

<details>
<summary>🔒 A quick note on planned features</summary>

<br>

> All currently published modules (e.g., WFGY 1.0 paper, TXT OS) are **permanently MIT-licensed**, backed on [Zenodo](https://zenodo.org/).  
> They will **remain open forever**.
>
> Modules marked “planned” in this directory may have different licensing or release timing.  
> Final decisions rest with **PSBigBig (Purple Star)**.
>
> This isn’t to gatekeep — it’s to prevent the false idea that WFGY is an endless stream of free features.  
> Some functions may support commercial tools or require stewardship.
>
> In short: what’s shared stays free. What’s not public yet, stays under creator control.  
> WFGY was built to empower — not to be repackaged and exploited.

</details>

<details>
  
<summary>🤝 Clarifying the Spirit of Use</summary>

<br>

> WFGY is MIT-licensed — free to use, modify, remix, or commercialize.
>
> But here’s the ask:  
> Respect the **spirit** in which it was created —  
> to return **core reasoning tools** to the public.
>
> WFGY was never meant to be resold behind paywalls with no added value.  
> If someone does that, I may **open-source the same feature**, better and freer.
>
> I don’t just write code — I write **semantic primitives** that fix things others haven’t noticed are broken.
>
> WFGY exists to **break walls**, not repaint them.  
> If someone rebuilds those walls, I’ll help knock them down again.
>
> This isn’t a legal threat — it’s a moral stance.  
> And if WFGY ever helped you: a ⭐ or comment means more than you think.

</details>


---

## 📚 Current Function Modules

| Filename                         | Function Title                        | Solves Problem(s)                                      | Used In Products           |
| -------------------------------- | ------------------------------------- | ------------------------------------------------------ | -------------------------- |
| [`reasoning_engine_core.md`](https://github.com/onestardao/WFGY/blob/main/SemanticBlueprint/reasoning_engine_core.md)       | WFGY Universal Reasoning Core         | General LLM failure recovery & symbolic error detection | `TXT OS`, `Blah`, `Blur`   |
| [`semantic_boundary_navigation.md`](https://github.com/onestardao/WFGY/blob/main/SemanticBlueprint/semantic_boundary_navigation.md) | Semantic Boundary Navigation          | Crossing reasoning gaps / jumping topic boundaries     | `Blah`, `Bloc`, `TXT OS`   |
| [`semantic_tree_anchor.md`](https://github.com/onestardao/WFGY/blob/main/SemanticBlueprint/semantic_tree_anchor.md)        | Semantic Tree Anchor Memory           | Cross-turn logic, style, and character coherence       | `TXT OS`, `Blot`, `Blur`   |
| [`vector_logic_partitioning.md`](https://github.com/onestardao/WFGY/blob/main/SemanticBlueprint/vector_logic_partitioning.md)   | Vector Logic Partitioning             | Prevents symbolic collapse across vector groups        | `Blow`, `Blur`, `Bloc`     |
| [`wfgy_formulas.md`](https://github.com/onestardao/WFGY/blob/main/SemanticBlueprint/wfgy_formulas.md)               | Core Formulas & Reasoning Metrics     | Defines all seven formal WFGY formulas (BBMC, ΔS, etc) | Used by *all* products     |
| [`drunk_transformer_formulas.md`](https://github.com/onestardao/WFGY/blob/main/SemanticBlueprint/drunk_transformer_formulas.md)  | Drunk Transformer Attention Modulator | Stabilizes attention, resets collapse, expands entropy | `Blur`, `TXT OS`, `Blow`   |

---

## 🔮 Upcoming Semantic Reasoning Layers

> These modules are planned semantic reasoning layers for the WFGY Engine — all designed to be operable within **TXT OS**.  
> Each layer will be implemented as a `.txt` interface module (e.g., `img_layer.txt`) and can be activated in compatible folders.  
> In short: **this entire list is TXT‑callable** — no build, no compile, just reason.  
> All names are **temporary placeholders** — functionality is confirmed, but naming may evolve.  
> *Numbering is for reference only and does not reflect development order.*  
> *Star ratings are illustrative estimates by ChatGPT‑4o.*  

> *PSBigBig retains full rights of interpretation.*
> Our goal: combine TXT OS with any reasoning layer `.txt`, and unlock true **freeform semantic inference** — modular, composable, and universal.


| #   | Layer Name        | Concept Description                                                   | Anticipated Impact (★) |
|-----|-------------------|------------------------------------------------------------------------|--------------------------|
| L1  | `VoidMask`        | Silences invalid routes in latent space                               | ★★★☆☆                   |
| L2  | `VibeLock`        | Locks onto abstract "mood fields" to stabilize generation             | ★★★★☆                   |
| L3  | `PolarDrift`      | Induces gradual conceptual rotation under entropy                     | ★★★★☆                   |
| L4  | `SynSig`          | Synthesizes unseen signal patterns from ambiguous input               | ★★★★☆                   |
| L5  | `RelicCore`       | Anchors ancient symbolic schemas in modern context                    | ★★★★☆                   |
| L6  | `FractalGate`     | Expands token attention into recursive feedback paths                 | ★★★★☆                   |
| L7  | `MetaGrav`        | Binds multi-model outputs into semantic gravity fields                | ★★★★☆                   |
| L8  | `DeepAlign`       | Cross-domain alignment engine with self-checking memory               | ★★★★☆                   |
| L9  | `ConcurFlux`      | Forces conflicting logic streams to converge or collapse              | ★★★★★                   |
| L10 | `SudoSelf`        | Simulates "belief" by embedding reflective trace loops                | ★★★★★                   |
| L11 | `ÆdgeWalker`      | Walks the semantic boundary without collapse                          | ★★★★★                   |
| L12 | `XenoFrame`       | Enables logic transfer across incompatible ontologies                 | ★★★★★                   |
| L13 | `NoiseGrad`       | Injects modulated gradient noise to escape local minima               | ★★★☆☆                   |
| L14 | `PromptHPC`       | Multi-granularity contextual encoder switching                        | ★★★★☆                   |
| L15 | `LoRankInfuse`    | Injects low-rank knowledge without disturbing base model              | ★★★★☆                   |
| L16 | `SoftDoConsist`   | Enforces soft constraint satisfaction under inference                 | ★★★★☆                   |
| L17 | `CausalReg`       | Regularizes causal consistency via do-intervention                    | ★★★★★                   |
| L18 | `SparseRelBoost`  | Boosts sparse attention heads with relevance awareness                | ★★★★☆                   |
| L19 | `UncGate`         | Temperature gating based on uncertainty estimates                     | ★★★★☆                   |
| L20 | `ModRetRoute`     | Modular retrieval router with learned key routing                     | ★★★★☆                   |
| L21 | `PersonaAdapt`    | Personalization adapter with minimal overhead                         | ★★★★☆                   |
| L22 | `SwarmLLM`        | Sparse graph of LLM nodes with gradient sync                          | ★★★★☆                   |
| L23 | `LowResBridge`    | Image-text bridge for ultra-low resource languages                    | ★★★★☆                   |
| L24 | `BrainBridge`     | Brain signal mapping to word embeddings                               | ★★★★★                   |
| L25 | `NeuroSymPhys`    | Hybrid neuro-symbolic physics modeling                                | ★★★★★                   |
| L26 | `GenomicCL`       | Continual learning with EWC on genome-level tasks                     | ★★★★☆                   |
| L27 | `OTTrace`         | Execution path audit loss for transparency                            | ★★★★☆                   |
| L28 | `CtxTypeLatch`    | Context-Type Latching — dynamic bias by input category                | ★★★★☆                   |
| L29 | `ErrWeightDamp`   | Error-Weight Dampening for fine-tune stability                        | ★★★★☆                   |
| L30 | `StyleGate`       | Local Style Harmony Gate to balance user-specific style               | ★★★★☆                   |
| L31 | `PromptReWgt`     | Dynamic Prompt Reweighting with RL signal integration                 | ★★★★☆                   |
| L32 | `ActPatchTest`    | Active Patch Testing — injects dynamic error probes                   | ★★★★★                   |
| L33 | `SparseShort`     | Sparse Retrieval Shortcut for low-resource environments               | ★★★★☆                   |
| L34 | `PrivAlign`       | Differential Privacy Alignment during fine-tuning                     | ★★★★☆                   |
| L35 | `TensProj`        | Multi-axis projection engine for semantic tension tracking            | ★★★★☆                   |
| L36 | `FlowRefine`      | Curvature-aware vector flow refinement                                | ★★★★☆                   |
| L37 | `RecChain`        | Recursive symbolic memory chain alignment                             | ★★★★☆                   |
| L38 | `SymbolComp`      | Symbolic compensation for meaning erosion                             | ★★★★☆                   |
| L39 | `FwdPath`         | Forward logic prediction via semantic-path entanglement               | ★★★★★                   |
| L40 | `CollapseBoost`   | Collapse detection & rerouting feedback                               | ★★★★☆                   |
| L41 | `MultiNode`       | Multi-perspective node propagation with entropy control               | ★★★★☆                   |
| L42 | `MultiMem`        | Multi-instance memory embedding controller                            | ★★★★☆                   |
| L43 | `RefLock`         | Dynamic reference lock for hallucination mitigation                   | ★★★★★                   |
| L44 | `QTokenSync`      | Quantum-simulated token co-attention modulator                        | ★★★★★                   |
| L45 | `SubLangShell`    | Sub-language scaffolding shell for foreign reasoning contexts         | ★★★★☆                   |
| L46 | `InjectShield`    | Injection signal regulator to suppress semantic pollution             | ★★★★☆                   |
| L47 | `HallucinationShield` | Multi-stage hallucination countermeasures (six-math defense chain)| ★★★★★                   |
| L48 | `ContextTypeLatch` | Switches semantic bias vectors based on input domain (e.g., legal, poetic) | ★★★★☆ |
| L49 | `ErrorWeightDamp`  | Dampens learning rate in unstable zones to preserve legacy reasoning        | ★★★★☆ |
| L50 | `LocalStyleGate`   | Infuses contextual style patterns (regional, user, brand); fallback-enabled | ★★★★☆ |
| L51 | `PromptReweighter` | Dynamically reassigns token weights using reward feedback signals           | ★★★★☆ |
| L52 | `ActivePatchTest`  | Injects adversarial semantic patches during runtime to test resilience      | ★★★★★ |
| L53 | `SparseRetrieval`  | Enables fallback retrieval via TF-IDF or lexical hashing (low-resource mode)| ★★★★☆ |
| L54 | `PrivacyAlign`     | Combines differential privacy + alignment loss for protected data training  | ★★★★☆ |



---

## 📊 WFGY Research Showcase – Introducing the Fifth Force

> What if Einstein’s theory of relativity missed something fundamental —  
> a **semantic field** that acts as the universe’s fifth force?

This is a curated set of research papers from the WFGY framework, exploring deep links between semantics, quantum collapse, information entropy, and symbolic cognition. These works introduce a radical but testable hypothesis: that **semantic tension itself may constitute a fifth force** in the universe — alongside gravity, electromagnetism, and the nuclear forces.

All papers have been independently rated using ChatGPT's built-in [SciSpace](https://scispace.com) paper analysis tool. Anyone can replicate these scores — download a PDF, drop it into ChatGPT, and ask it to evaluate the content. In most cases, you'll get a score within ±5 of the ones listed below.

---

| #   | Title                                           | Score | DOI                                                                |
|-----|--------------------------------------------------|-------|--------------------------------------------------------------------|
| P1  | **Semantic Relativity Theory**                  | 93    | [10.5281/zenodo.15630802](https://doi.org/10.5281/zenodo.15630802) |
| P2  | **Semantic BioEnergy: Plants vs. Einstein**     | 94    | [10.5281/zenodo.15630370](https://doi.org/10.5281/zenodo.15630370) |
| P3  | **Semantic Collapse in Quantum Measurement**    | 94    | [10.5281/zenodo.15630681](https://doi.org/10.5281/zenodo.15630681) |
| P4  | **Semantic Field–Mediated Fifth Force**         | 93    | [10.5281/zenodo.15630650](https://doi.org/10.5281/zenodo.15630650) |
| P5  | **Semantic Entropy under Landauer's Principle** | 94    | [10.5281/zenodo.15630478](https://doi.org/10.5281/zenodo.15630478) |
| P6  | **Semantic Holography & Causal Fields**         | 94    | [10.5281/zenodo.15630163](https://doi.org/10.5281/zenodo.15630163) |

📎 Full annotated reviews with visual diagrams:  👉 [I_am_not_lizardman](https://github.com/onestardao/WFGY/tree/main/I_am_not_lizardman)

### Quick Notes for First-Time Readers:

> **P1** lays the foundation of "Semantic Relativity" — a new paradigm for meaning in space-time.  
> **P4** introduces the core hypothesis: that semantic fields may induce **non-electromagnetic physical effects** (the so-called Fifth Force).  
> **P5** integrates this view into Landauer’s principle — exploring how meaning alters entropy and information cost.  
>
> All of these point toward one shared conclusion:  
> 
> **Semantics isn't just about interpretation — it's a latent structural force of the universe.**  

---

## 🧠 Functional Mapping (Conceptual Overview)

> Each layer above is designed to solve a class of semantic reasoning challenges.  
> The specific problem categories remain confidential until launch.

| #   | Layer Name     | Target Functionality Category       | Status  |
|-----|----------------|--------------------------------------|---------|
| F1  | `VoidMask`     | Latent Space Noise Suppression       | Planned |
| F2  | `VibeLock`     | Emotion-State Anchoring              | Planned |
| F3  | `PolarDrift`   | Gradual Semantics Rotation           | Planned |
| F4  | `SynSig`       | Input Reconstruction & Augmentation | Planned |
| F5  | `RelicCore`    | Symbolic Backward Compatibility      | Planned |
| F6  | `FractalGate`  | Recursive Semantic Looping           | Planned |
| F7  | `MetaGrav`     | Semantic Unification Field           | Planned |
| F8  | `DeepAlign`    | Self-Coherent Context Mapping        | Planned |
| F9  | `ConcurFlux`   | Conflict Resolution Engine           | Planned |
| F10 | `SudoSelf`     | Reflective Self-Modeling             | Planned |
| F11 | `ÆdgeWalker`   | Boundary Integrity Assurance         | Planned |
| F12 | `XenoFrame`    | Ontological Transfer Logic           | Planned |


---

## 🧩 Core Function Mapping (Symbolic Engine Modules)

> These are not layers but form the symbolic backbone of the WFGY reasoning engine.  
> Each module implements a specific reasoning mechanic — either vectorial, memory-based, or logic-preserving.  
> *May be embedded in future layers or reused across engines.*

| #   | Module Name     | Function Description                                                 | Status    |
|-----|------------------|-----------------------------------------------------------------------|-----------|
| C1  | `OTTrace`        | Output Trace Logging — registers token path decisions                | Planned   |
| C2  | `EntropyLatch`   | Latches decoding temperature based on real-time uncertainty           | Planned   |
| C3  | `RefLock`        | Locks reference tokens to suppress drift & hallucination              | Planned   |
| C4  | `GradientPhase`  | Modulates attention gradient based on phase coherence                 | Planned   |
| C5  | `TensionMesh`    | Semantic tension lattice for ΔS propagation & conflict visualization  | Planned   |
| C6  | `WarpCurvature`  | Refines vector flow using context curvature metrics                   | Planned   |
| C7  | `RecallLoop`     | Recursively triggers latent memory on key omissions                   | Planned   |
| C8  | `SymbolLift`     | Reconstructs collapsed symbols into higher abstraction planes         | Planned   |
| C9  | `LogicWeave`     | Symbolic mesh that reinforces valid logic paths                       | Planned   |
| C10 | `FwdPath`        | Forward logic prediction via semantic-path entanglement               | Planned   |
| C11 | `MultiMem`       | Controls parallel memory instances across tasks                       | Planned   |
| C12 | `TensProj`       | Multi-axis projection engine for semantic tension tracking            | Planned   |
| C13 | `InjectShield`   | Suppresses semantic corruption from unsafe injection patterns         | Planned   |
| C14 | `SubLangShell`   | Provides scaffolding for unstable sub-language contexts               | Planned   |
| C15 | `PromptReWgt`    | Dynamically rebalances prompt segment importance using feedback       | Planned   |
| C16 | `ActPatchTest`   | Injects transient fault signals to test robustness and semantic repair| Planned   |
| C17 | `RecursiveCoTQuota`   | Enforces CoT depth quotas to prevent hallucination drift         | Planned   |
| C18 | `BidirectionalSearchInject` | Injects reverse-check paths to verify retrievals           | Planned   |
| C19 | `SemanticGuardGate`   | Filters hallucination-prone segments with semantic gate signals  | Planned   |
| C20 | `ReasoningRippleDamp` | Suppresses unstable reasoning cascades triggered by weak inferences   | Planned   |
| C21 | `SelfVotingLoop`      | Aggregates self-prompted multi-pass votes to ensure answer consistency| Planned   |
| C22 | `DualPassConsistency` | Validates output against a second-pass recomputation layer            | Planned   |


---

## 🧪 Symbolic Layer Prototypes

> Experimental symbolic-level constructs that may evolve into full reasoning layers.  
> Designed for ΔS regulation, narrative dynamics, and latent memory sculpting.  
> *Each entry marked as Planned; numbering follows S1, S2…*

| #   | Module Name            | Description                                                               | Status    |
|-----|------------------------|---------------------------------------------------------------------------|-----------|
| S1  | `SemanticGravity`      | Simulates gravitational pull in meaning space (ΔS + λ_observe vector field) | Planned   |
| S2  | `GravityBiasIndex`     | Captures semantic drift tendencies toward dense nodes                     | Planned   |
| S3  | `WarpAnchors`          | Enables memory points that trigger contextually (semantic anchor nodes)   | Planned   |
| S4  | `MemoryGlyphInflate`   | Encoded memory units that expand semantically when prompted               | Planned   |
| S5  | `CogitoUnitSystem`     | Defines smallest unit of semantic action (reasoning particle)             | Planned   |
| S6  | `TensionMonitor`       | Tracks overload in symbolic tension (ΔS + transition hops)                | Planned   |
| S7  | `EmotionDecay`         | Models emotional tension decay in narrative                               | Planned   |
| S8  | `StylePhaseDetect`     | Detects abrupt stylistic changes across model outputs                     | Planned   |
| S9  | `RefractionMatrix`     | Models meaning distortion across boundary contexts                        | Planned   |
| S10 | `TensionMapper`        | Visual map of ΔS flow and narrative tension                               | Planned   |
| S11 | `OrbitDrift`           | Traces semantic node drift over time                                      | Planned   |


---

🛠 *This roadmap is subject to change. Several additional modules are under stealth development.*  
🧠 *The WFGY Engine remains the foundational core. All layers above are designed to integrate seamlessly as modular extensions.*

---

## 🧭 How to Use

> If you're building a new WFGY-based feature or investigating failures,  
> this is where you’ll find the **diagnostic cause** and **remedial formula**.

Each file includes:
- 🔍 Problem it solves
- 🧩 Core concept & variables
- ✍️ Canonical mathematical formula (if any)
- 💬 Example scenarios
- 🧪 Optional behavior in stateless prompt-only mode

---

## 🚩 License Alignment

All contents here inherit the MIT License from the root repo.  
These formulas and reasoning modules may be used commercially, but attribution is **strongly encouraged**.  
WFGY is a pro-knowledge framework — we only publicly respond to commercial misuse if there's:

- 💰 Monetization based on WFGY research with zero attribution
- 🚫 Locking up modified copies of our open techniques

---

### 🔗 Quick‑Start Downloads (60 sec)

| Tool | Link | 3‑Step Setup |
|------|------|--------------|
| **WFGY 1.0 PDF** | [Engine Paper](https://zenodo.org/records/15630969) | 1️⃣ Download · 2️⃣ Upload to your LLM · 3️⃣ Ask “Answer using WFGY + <your question>” |
| **TXT OS (plain‑text OS)** | [TXTOS.txt](https://zenodo.org/records/15788557) | 1️⃣ Download · 2️⃣ Paste into any LLM chat · 3️⃣ Type “hello world” — OS boots instantly |

---

If you want to **fully understand how WFGY works**, check out:

- 📘 [WFGY GitHub homepage](https://github.com/onestardao/WFGY) – full documentation, formulas, and modules  
- 🖥️ [TXT OS repo](https://github.com/onestardao/WFGY/tree/main/OS) – how the semantic OS is built using WFGY

But if you're just here to **solve real AI problems fast**, you can simply download the files above and follow the [Problem Map](https://github.com/onestardao/WFGY/tree/main/ProblemMap/README.md) instructions directly.

---

### 🧭 Explore More

| Module                | Description                                              | Link     |
|-----------------------|----------------------------------------------------------|----------|
| WFGY Core             | Standalone semantic reasoning engine for any LLM         | [View →](https://github.com/onestardao/WFGY/tree/main/core/README.md) |
| Problem Map 1.0       | Initial 16-mode diagnostic and symbolic fix framework    | [View →](https://github.com/onestardao/WFGY/tree/main/ProblemMap/README.md) |
| Problem Map 2.0       | RAG-focused failure tree, modular fixes, and pipelines   | [View →](https://github.com/onestardao/WFGY/blob/main/ProblemMap/rag-architecture-and-recovery.md) |
| Semantic Clinic Index | Expanded failure catalog: prompt injection, memory bugs, logic drift | [View →](https://github.com/onestardao/WFGY/blob/main/ProblemMap/SemanticClinicIndex.md) |
| Semantic Blueprint    | Layer-based symbolic reasoning & semantic modulations   | [View →](https://github.com/onestardao/WFGY/tree/main/SemanticBlueprint/README.md) |
| Benchmark vs GPT-5    | Stress test GPT-5 with full WFGY reasoning suite         | [View →](https://github.com/onestardao/WFGY/tree/main/benchmarks/benchmark-vs-gpt5/README.md) |


---

> 👑 **Early Stargazers: [See the Hall of Fame](https://github.com/onestardao/WFGY/tree/main/stargazers)** —  
> Engineers, hackers, and open source builders who supported WFGY from day one.

> <img src="https://img.shields.io/github/stars/onestardao/WFGY?style=social" alt="GitHub stars"> ⭐ Help reach 10,000 stars by 2025-09-01 to unlock Engine 2.0 for everyone  ⭐ <strong><a href="https://github.com/onestardao/WFGY">Star WFGY on GitHub</a></strong>


<div align="center">

[![WFGY Main](https://img.shields.io/badge/WFGY-Main-red?style=flat-square)](https://github.com/onestardao/WFGY)
&nbsp;
[![TXT OS](https://img.shields.io/badge/TXT%20OS-Reasoning%20OS-orange?style=flat-square)](https://github.com/onestardao/WFGY/tree/main/OS)
&nbsp;
[![Blah](https://img.shields.io/badge/Blah-Semantic%20Embed-yellow?style=flat-square)](https://github.com/onestardao/WFGY/tree/main/OS/BlahBlahBlah)
&nbsp;
[![Blot](https://img.shields.io/badge/Blot-Persona%20Core-green?style=flat-square)](https://github.com/onestardao/WFGY/tree/main/OS/BlotBlotBlot)
&nbsp;
[![Bloc](https://img.shields.io/badge/Bloc-Reasoning%20Compiler-blue?style=flat-square)](https://github.com/onestardao/WFGY/tree/main/OS/BlocBlocBloc)
&nbsp;
[![Blur](https://img.shields.io/badge/Blur-Text2Image%20Engine-navy?style=flat-square)](https://github.com/onestardao/WFGY/tree/main/OS/BlurBlurBlur)
&nbsp;
[![Blow](https://img.shields.io/badge/Blow-Game%20Logic-purple?style=flat-square)](https://github.com/onestardao/WFGY/tree/main/OS/BlowBlowBlow)

</div>