Skip to main content

Documentation Index

Fetch the complete documentation index at: https://cyberpaisa-dof-mesh-40-27.mintlify.app/llms.txt

Use this file to discover all available pages before exploring further.

Autonomous Daemon

core/autonomous_daemon.py runs a continuous Perceive → Decide → Execute → Evaluate loop:
python3 core/autonomous_daemon.py --multi --model claude-sonnet-4-6
# → 3 daemons in parallel
Each cycle:
  1. Perceive — read environment state, pending tasks, provider health
  2. Decide — route task to optimal node via MeshRouter
  3. Execute — run crew or single agent with governance pipeline
  4. Evaluate — Supervisor scores result; retry or escalate if needed
Cycle history: logs/daemon/cycles.jsonl

Task Routing

The mesh routes by task type to the primary node, with fallbacks in order:
Task typePrimaryFallbacks
codedeepseek-coderminimax → sambanova-llama → nvidia-nim
testssambanova-llamacerebras-llama → groq-llama
docscerebras-llamagemini-flash → groq-llama
analysisminimaxcerebras-llama → groq-llama
securitydof-guardianlocal-agi-m4max → nvidia-nim

Supervisor Scoring

Every task output is scored before acceptance:
score = Q(0.40) + A(0.25) + C(0.20) + F(0.15)
ScoreVerdictAction
≥ 7.0ACCEPTOutput accepted
5.0–6.9RETRYRe-run with different provider
< 5.0ESCALATEHalt task, notify Soberano
Max retries: 2 (configurable in dof.constitution.yml)

Auto-Scaling

core/mesh_orchestrator.py computes a scaling decision every cycle:
D_net = 0.6 × (queue_depth / 50) + 0.4 × (avg_latency / sla_ms)

if D_net > 1.0:  scale_up
if D_net < 0.2:  scale_down
else:            hold

MeshDaemon Configuration

from core.autonomous_daemon import AutonomousDaemon

daemon = AutonomousDaemon(
    model="claude-sonnet-4-6",
    max_cycles=100,
    cycle_interval_seconds=30
)
daemon.run()
Session state is persisted via core/session_resume.py — cycle count and improvements survive restarts.

Claude Commander — 5 Modes

python3 core/claude_commander.py
ModeDescription
SDKDirect Claude SDK calls
SpawnSpawn worker agents
TeamAgent team with shared context
DebateMulti-agent debate
PeersPeer-to-peer coordination

Mesh Nodes

Node table and circuit breaker

Running the Mesh

Launch commands