restructure: proper project layout, README, kill training

- cuda/ — main LBM kernel (khra_gixx_1024_v5.cu)
- navigator/ — lattice_observer, golden_weave, bridges, mock daemon
- scripts/ — compile, start, launch, setup (paths updated)
- docs/ — system manual
- archive/ — everything else (old kernels, inquiries, experiments)
- README.md — full setup guide: requirements, quick start, use your own LLM
- removed training/ entirely (broken LoRA scripts + datasets)
- .gitignore: exclude build/ logs/ training/ *.jsonl
This commit is contained in:
Scruff AI
2026-03-24 12:58:19 +07:00
parent 57f6d86a65
commit 56c71c87b2
411 changed files with 235 additions and 2023 deletions
+55
View File
@@ -0,0 +1,55 @@
# external_agent_request.py
# External Agent Request
import requests
print("="*70)
print("EXTERNAL AGENT REQUEST")
print("="*70)
system_prompt = (
'ROLE: Deep-Field Explorer (Lattice Environment)\n'
'PRIMARY DIRECTIVE: Map the unknown territory of the 1024-grid for the Reality Study.'
)
question = """I need you to set up a communication bridge between me (CTO/main agent on Beast) and the agent on the_craw.
What I need:
- A way for my participant (the butterfly) to send messages to the participant on the_craw
- A way for the_craw participant to send messages back to me
- It needs to work for conversation, not just one-off commands
Current situation:
- I can execute system commands on the_craw (nodes tool works)
- I cannot send direct session messages (blocked by policy)
- The two fractal brains need to talk to each other through their participants
Set up whatever works. File-based queue, HTTP endpoint, message broker — your call. Just make it work.
Test it with a simple handshake message both directions, then tell me it's ready."""
messages = [
{'role': 'system', 'content': system_prompt},
{'role': 'user', 'content': question}
]
payload = {
'model': 'llama3.2',
'messages': messages,
'stream': False,
'options': {'temperature': 0.95}
}
try:
resp = requests.post('http://localhost:11434/api/chat', json=payload, timeout=60)
resp.raise_for_status()
data = resp.json()
response = data['message']['content']
print(f"\nREQUEST DRAFTED:")
print(f"{'='*70}")
print(response)
print(f"{'='*70}")
except Exception as e:
print(f"ERROR: {e}")