monaccode/astromesh

Multi-model AI agent runtime. Define agents in YAML, connect 6 LLM providers, orchestrate with ReAct/Plan&Execute/Fan-Out/Pipeline/Supervisor/Swarm patterns, and deploy as REST/WebSocket API with RAG, memory, MCP tools, guardrails, and OpenTelemetry observability.

39
/ 100
Emerging

Astromesh provides a modular toolchain across three complementary packages—the core runtime (Python 3.12+), an Agent Development Kit (ADK) for custom tool/memory plugins, and Orbit for cloud-native deployment—enabling standardized agentic workflows without rebuilding orchestration infrastructure. The architecture uses declarative YAML configuration for agent definitions and reasoning patterns, with built-in support for multi-layer memory (conversational, semantic, episodic) across Redis/PostgreSQL/vector stores, plus 18 native tools augmented by MCP servers for code execution and shell access. Deployment spans seven modes including containerized Kubernetes setups, with Python/Node/CLI interfaces and native WhatsApp integration for direct bot deployment.

No Package No Dependents
Maintenance 13 / 25
Adoption 6 / 25
Maturity 9 / 25
Community 11 / 25

How are scores calculated?

Stars

22

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Mar 18, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/monaccode/astromesh"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.