antiv/mate
Production-ready multi-agent orchestration engine built on Google ADK. Database-driven agent config, 50+ LLM providers, MCP protocol, persistent memory, web dashboard, RBAC.
Implements a tree-structured agent hierarchy where agents can dynamically create and modify other agents at runtime, enabling self-evolving multi-agent systems. Decouples agent configuration from code through a drag-and-drop visual builder and database-backed persistence, supporting both database-configured and hardcoded agents with runtime switching via environment variables. Includes comprehensive token accounting (4-type breakdown), MCP server dual-mode (consuming and exposing agents as MCP endpoints), and embeddable chat widgets for external integration.
Stars
30
Forks
3
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/antiv/mate"
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.
jeremiah-k/agor
AgentOrchestrator - Multi-agent development coordination platform. Transform AI assistants into...
rodmena-limited/stabilize
Queue-Based State Machine - A lightweight workflow execution engine with DAG-based stage...
avtomatika-ai/avtomatika
High-performance state-machine based orchestrator for managing complex AI agents and ...