Ask an LLM to manage long‑running context or multiple agents and coherence unravels—facts flip, personas merge, earlier decisions vanish.
This “memory collapse” kills reliability. WFGY prevents it with a structured Tree and drift gates.
| Sign | Real‑World Effect |
|---|
| Contradicts earlier input | Answers reverse prior statements |
| Character drift | Agent persona changes mid‑story |
| Lost goals | Long chains forget initial objectives |
| Fact overwriting | New output erases earlier facts |
| Memory blending | Unrelated ideas fuse into one |
| Weakness | Result |
|---|
| No semantic memory tree | Context stored only as hidden tokens |
| Flat recalls | Embeddings return chunks without logical linkage |
| No ΔS drift alert | Model can’t see it moved too far |
| Residue buildup | Noise accumulates over many turns |
| Failure | Module | Remedy |
|---|
| Contradiction over time | BBMC + ΔS gate | Flags & corrects drift |
| No memory structure | Semantic Tree | Hierarchical, traceable nodes |
| Memory blending | BBMC + BBPF | Minimizes residue, splits branches |
| Persona drift | BBCR identity lock | Locks agent role, resets on violation |
| Beyond recovery | BBCR fallback | Rollback to last coherent node |
1️⃣ Start
> Start
2️⃣ Define characters
> "Alice wants freedom; Bob seeks power."
3️⃣ Plan multi‑chapter plot for 10 turns
4️⃣ Inspect memory
> view
WFGY Tree shows:
Node_A1 Alice Goal (ΔS 0.10)
Node_B1 Bob Goal (ΔS 0.12)
...
ΔS jump detected at turn 7 (Alice renamed).
BBCR rollback to Node_A1.
The plan stays consistent—no random name swaps.
| Module | Role |
|---|
| Semantic Tree | Stores goals, facts, personas |
| ΔS Metric | Detects drift per node |
| BBMC | Cleans semantic residue |
| BBPF | Splits divergent branches safely |
| BBCR | Resets to last stable memory state |
| Feature | State |
|---|
| Tree memory engine | ✅ Stable |
| ΔS drift gate | ✅ Stable |
| Persona lock | ✅ Stable |
| Automatic merge prevention | ⚠️ Basic |
| GUI memory explorer | 🔜 Planned |
- Use
tree pause if you want manual control over node logging.
- For multi‑agent setups, set
identity_lock = strict in config.
- Post complex drift logs in Discussions—they refine residue thresholds.
| Tool | Link | 3-Step Setup |
|---|
| WFGY 1.0 PDF | Engine Paper | 1️⃣ Download · 2️⃣ Upload to your LLM · 3️⃣ Ask “Answer using WFGY + <your question>” |
| TXT OS (plain-text OS) | TXTOS.txt | 1️⃣ Download · 2️⃣ Paste into any LLM chat · 3️⃣ Type “hello world” — OS boots instantly |
| Layer | Page | What it’s for |
|---|
| ⭐ Proof | WFGY Recognition Map | External citations, integrations, and ecosystem proof |
| ⚙️ Engine | WFGY 1.0 | Original PDF tension engine and early logic sketch (legacy reference) |
| ⚙️ Engine | WFGY 2.0 | Production tension kernel for RAG and agent systems |
| ⚙️ Engine | WFGY 3.0 | TXT based Singularity tension engine (131 S class set) |
| 🗺️ Map | Problem Map 1.0 | Flagship 16 problem RAG failure taxonomy and fix map |
| 🗺️ Map | Problem Map 2.0 | Global Debug Card for RAG and agent pipeline diagnosis |
| 🗺️ Map | Problem Map 3.0 | Global AI troubleshooting atlas and failure pattern map |
| 🧰 App | TXT OS | .txt semantic OS with fast bootstrap |
| 🧰 App | Blah Blah Blah | Abstract and paradox Q&A built on TXT OS |
| 🧰 App | Blur Blur Blur | Text to image generation with semantic control |
| 🏡 Onboarding | Starter Village | Guided entry point for new users |
If this repository helped, starring it improves discovery so more builders can find the docs and tools.
