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:Supervisor Scoring
Every task output is scored before acceptance:
Max retries: 2 (configurable in
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
Mesh Nodes
Node table and circuit breaker
Running the Mesh
Launch commands