Vibe Coding Discoverneuro-san
View on GitHubNeuro AI System of Agent Networks
Neuro SAN is a Python library and HTTP server for building data-driven multi-agent networks defined in HOCON. Agents can call LangChain-based CodedTools, use per-agent or fallback LLMs, expose the network via MCP, and ship with tracing and test tooling.
Use Cases
Build multi-agent networks declared in HOCON config filesServe agent networks over HTTP or as an MCP serverGive each agent its own LLM and fallback modelPass private data (sly_data) outside the LLM chat streamCall external APIs and code via CodedToolsTest and assess agent network failures with data-driven test casesTrace agent runs with LangSmith/Langfuse/Phoenix/HoneyHiveLink distributed agent webs across hostsPer-user authorization of agent networks with OpenFGABring-your-own-key client deployments
Built With
- Language
- Python
- Frameworks
- LangChain · MCP · LangSmith · Langfuse · Arize Phoenix · HoneyHive · OpenFGA · Docker · Ollama
Tags
multi-agent · agent-networks · agentic-framework · hocon · data-driven · llm-agnostic · mcp-server · coded-tools · sly-data · observability · tracing · distributed-agents · byok · agent-testing · python