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:
- Perceive — read environment state, pending tasks, provider health
- Decide — route task to optimal node via MeshRouter
- Execute — run crew or single agent with governance pipeline
- Evaluate — Supervisor scores result; retry or escalate if needed
logs/daemon/cycles.jsonl
Task Routing
The mesh routes by task type to the primary node, with fallbacks in order:| Task type | Primary | Fallbacks |
|---|---|---|
code | deepseek-coder | minimax → sambanova-llama → nvidia-nim |
tests | sambanova-llama | cerebras-llama → groq-llama |
docs | cerebras-llama | gemini-flash → groq-llama |
analysis | minimax | cerebras-llama → groq-llama |
security | dof-guardian | local-agi-m4max → nvidia-nim |
Supervisor Scoring
Every task output is scored before acceptance:| Score | Verdict | Action |
|---|---|---|
| ≥ 7.0 | ACCEPT | Output accepted |
| 5.0–6.9 | RETRY | Re-run with different provider |
| < 5.0 | ESCALATE | Halt task, notify Soberano |
dof.constitution.yml)
Auto-Scaling
core/mesh_orchestrator.py computes a scaling decision every cycle:
MeshDaemon Configuration
core/session_resume.py — cycle count and
improvements survive restarts.
Claude Commander — 5 Modes
| Mode | Description |
|---|---|
| SDK | Direct Claude SDK calls |
| Spawn | Spawn worker agents |
| Team | Agent team with shared context |
| Debate | Multi-agent debate |
| Peers | Peer-to-peer coordination |
Mesh Nodes
Node table and circuit breaker
Running the Mesh
Launch commands