---
license: agpl-3.0
title: SnapKitty Sovereign Chat Harness
emoji: 🔐
colorFrom: green
colorTo: indigo
sdk: gradio
sdk_version: 4.40.0
app_file: app.py
pinned: true
tags:
- harness
- verification
- guardrails
- agent
- formal-verification
- hallucination-detection
- audit-log
- local-inference
- rlhf
- snapkitty
- agents
- python
short_description: If it can't prove it, it won't say it. ERE P1-P5 gates every response.
---

# SnapKitty Sovereign Chat Harness

> **If it can't prove it, it won't say it.**

Every response is checked by five deterministic ERE gates and sealed with a SHA-256 audit receipt before you see it.
Responses that fail are **blocked and explained** — not silently returned.

## How it works

```
prompt
  │
  ▼
P1 verify(prompt)     — MetaSum coherence check on prompt
  │
  ▼
LLM (Ollama local / HF Inference)
  │
  ▼
P2 verify(response)   — MetaSum coherence check on response
  │
  ▼
P3 curate(response)   — Dream Cycle recovery gate
  │
  ▼
P4 prove(joint)       — entropy invariant ≤ 0.20
  │
  ▼
P5 seal()             — WORM SHA-256 receipt
  │
  ▼
allowed? → show response + proof panel
blocked? → show why, suppress response
```

## Gate table

| Gate | External label | What it checks |
|------|---------------|----------------|
| P1 | `verify` | Prompt phase coherence: `|MetaSum(prompt)| ≥ τ` |
| P2 | `verify` | Response MetaSum: model output has sufficient signal |
| P3 | `curate` | Dream Cycle: coherence restored after low-MetaSum event |
| P4 | `prove`  | Joint entropy `≤ 0.20` — Weil-bound invariant |
| P5 | `seal`   | WORM SHA-256 receipt for audit chain |

## Why it doesn't hallucinate

The coherence threshold `τ = N/2 = 512` enforces that the MetaSum magnitude of any
response exceeds the Weyl bound `√(N·log Q) ≈ 89`. Responses below this bound are
recovered via Dream Cycle or blocked entirely.

Entropy invariant `H ≤ 0.20` is derived from the same bound: post-Dream-Cycle
entropy drops to `≈ 0.07`, well inside the safe zone.

## Local setup

```bash
git clone https://github.com/SNAPKITTYWEST/sovereign-chat-harness
cd sovereign-chat-harness
pip install -r requirements.txt
cp .env.example .env
# edit .env — set HF_TOKEN and/or start Ollama

# With Ollama (recommended):
ollama run snapkitty-merged  # or any GGUF model

# Without Ollama (HF Inference):
export HF_TOKEN=hf_...

python app.py
# open http://localhost:7860
```

## RTX 3080 Docker (8 GB VRAM)

See `Dockerfile` — one-command local sovereign stack with audit trail:

```bash
docker build -t snapkitty-chat .
docker run -p 7860:7860 --gpus device=0 \
  -e HF_TOKEN=$HF_TOKEN \
  snapkitty-chat
```

Every response prints a WORM hash. NVIDIA can't offer this.

## Terminology

Internal terms (code) map to external terms (README/tags/HF search):

| Internal | HF search term |
|----------|---------------|
| FSM pipeline | data curation / filtering |
| ERE gates P1-P5 | verification / guardrails |
| WORM sealing | reproducible audit log |
| SovMonster / Lean proof | formal verification |
| SoulVM JIT | local inference runtime |
| Dream Cycle | hallucination recovery |
| MetaSum | coherence scoring |

## Models

- **Ollama** (local, preferred): `snapkitty-merged` Q4_K_M GGUF, RTX 3080, 8 GB VRAM
- **HF Inference** (cloud): `Snapkitty/snapkitty-merged`
- Any Ollama-compatible model works — swap via `OLLAMA_MODEL` env var

## License

BSL-1.1 / AGPL-3.0 / MPL-2.0 — Patent Pending, BEL ESPRIT D ACCORD TRUST HOLDINGS INC.

### 💼 Commercial License

Snapkitty code is free and open under **AGPL-3.0** for open-source use. Building a commercial product or service? A **proprietary commercial license** from Snapkitty Collective LLC lets you ship this code without the AGPL's source-sharing and network-use obligations.

**[→ Get a commercial license](mailto:A.parr@belespritdaccord.uk?subject=Commercial%20license:%20sovereign-chat-harness)** · A.parr@belespritdaccord.uk