sajosam/spawnverse
Self-spawning AI agents born from tasks. Zero pre-built agents. Distributed memory. 4-layer guardrails. Fossil record. Groq + LLaMA.
Agents dynamically generated from tasks execute in isolated subprocess runtimes with 4-layer code guardrails, namespace-isolated distributed memory (SQLite with concurrent write safety), and ChromaDB-backed fossil records that accumulate task knowledge across runs. Supports Groq, OpenAI, Anthropic, and Ollama providers with pluggable LLM switching via single configuration change.
Stars
6
Forks
3
Language
Python
License
—
Category
Last pushed
Mar 28, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/sajosam/spawnverse"
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...