/operators

What if every agent run had an audit trail?

The artifacts on this page do. Multi-agent orchestration over MCP, hybrid retrieval, citation validation, and execution that resumes from the last completed stage.

Flagship

Shipped

Demo coming soonTwo-minute demo of agentic-rag-pipeline. Walkthrough of a five-agent RAG run, from team spawn through retriever dispatch, synthesizer commit, and lead-side verification of the write.

Shipped /projects/agentic-rag-pipeline

agentic-rag-pipeline

Stateful agentic RAG with citation-grounded synthesis.

A multi-agent retrieval pipeline I built for fun, used daily. A lead session runs a backend pre-flight, spawns five specialist teammates in parallel over a custom MCP server, and hands off to an aggregator that runs a 7-stage pipeline. Three retrievers cover dense-vector, knowledge-graph, and external-API modes; a synthesizer commits the final output to a persistent local wiki. Citation validation happens through a separate MCP, and the lead independently re-verifies every write.

MCPMulti-agent orchestrationChromaDBLightRAGMilvusHybrid retrieval

Open project →

Companion artifact

One step adjacent

Gated preview/projects/loom

loom

Where Claude Code sessions get a context engine.

BunHonoReact 19Vite 6Tailwind v4

Open →