philipp-lm/ViableOS
Organize your AI agent teams with the Viable System Model. The missing organizational layer for multi-agent systems.
Applies the Viable System Model—a cybernetic organizational framework—to decompose multi-agent systems into five hierarchical control layers (operations, coordination, optimization, audit, intelligence, identity), with automatic conflict detection, escalation chains, and mode-dependent autonomy rules. Generates OpenClaw-compatible deployment packages including per-agent behavioral specs (SOUL, SKILL, HEARTBEAT), anti-looping guardrails, and cross-provider model fallbacks, paired with a web wizard that uses LLM-guided assessment to auto-generate VSM configurations from organizational requirements and budget constraints (23 models across 7 providers).
Stars
5
Forks
1
Language
Python
License
MIT
Category
Last pushed
Mar 02, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/philipp-lm/ViableOS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
awslabs/agent-squad
Flexible and powerful framework for managing multiple AI agents and handling complex conversations
horizon-rl/strands-sglang
SGLang model provider for Strands Agents for on-policy agentic RL training.
rodmena-limited/stabilize
Queue-Based State Machine - A lightweight workflow execution engine with DAG-based stage...
jeremiah-k/agor
AgentOrchestrator - Multi-agent development coordination platform. Transform AI assistants into...
aws-solutions-library-samples/guidance-for-multi-agent-orchestration-on-aws
Enables developers to build, deploy, and manage multiple specialized agents that work together...